Token | , |
Token ID | 11 |
Feature activation | +3.49e-03 |
Pos logit contributions | |
friends | +0.016 |
marched | +0.015 |
brothers | +0.014 |
sisters | +0.014 |
mo | +0.014 |
Neg logit contributions | |
Here | -0.026 |
chard | -0.025 |
ours | -0.025 |
right | -0.023 |
redd | -0.023 |
Token | he |
Token ID | 339 |
Feature activation | -8.38e-03 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.003 |
, | +0.003 |
came | +0.003 |
sisters | +0.003 |
Neg logit contributions | |
Here | -0.008 |
chard | -0.007 |
ours | -0.007 |
right | -0.007 |
redd | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
Here | +0.019 |
chard | +0.019 |
ours | +0.019 |
redd | +0.018 |
right | +0.018 |
Neg logit contributions | |
friends | -0.007 |
marched | -0.007 |
sisters | -0.006 |
, | -0.006 |
brothers | -0.006 |
Token | no |
Token ID | 645 |
Feature activation | +5.24e-03 |
Pos logit contributions | |
friends | +0.011 |
marched | +0.010 |
sisters | +0.009 |
, | +0.009 |
came | +0.009 |
Neg logit contributions | |
Here | -0.023 |
chard | -0.023 |
ours | -0.023 |
right | -0.022 |
redd | -0.022 |
Token | longer |
Token ID | 2392 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
friends | +0.008 |
, | +0.007 |
marched | +0.007 |
brothers | +0.007 |
sisters | +0.007 |
Neg logit contributions | |
Here | -0.010 |
chard | -0.010 |
ours | -0.009 |
rily | -0.009 |
redd | -0.009 |
Token | sh |
Token ID | 427 |
Feature activation | +7.17e-02 |
Pos logit contributions | |
friends | +0.043 |
marched | +0.040 |
sisters | +0.036 |
brothers | +0.036 |
, | +0.036 |
Neg logit contributions | |
Here | -0.085 |
chard | -0.084 |
ours | -0.082 |
right | -0.079 |
redd | -0.079 |
Token | ivering |
Token ID | 35598 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
friends | +0.111 |
marched | +0.104 |
, | +0.098 |
sisters | +0.098 |
came | +0.097 |
Neg logit contributions | |
Here | -0.122 |
chard | -0.119 |
ours | -0.117 |
redd | -0.112 |
right | -0.111 |
Token | . |
Token ID | 13 |
Feature activation | -7.69e-04 |
Pos logit contributions | |
friends | +0.014 |
marched | +0.013 |
sisters | +0.011 |
brothers | +0.010 |
came | +0.010 |
Neg logit contributions | |
Here | -0.051 |
chard | -0.050 |
ours | -0.049 |
right | -0.048 |
redd | -0.048 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
ours | +0.002 |
chard | +0.002 |
redd | +0.002 |
right | +0.002 |
Here | +0.002 |
Neg logit contributions | |
friends | -0.001 |
, | -0.001 |
marched | -0.001 |
brothers | -0.001 |
family | -0.001 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.27e-03 |
Pos logit contributions | |
friends | +0.016 |
sisters | +0.015 |
marched | +0.014 |
marching | +0.014 |
helpers | +0.013 |
Neg logit contributions | |
Here | -0.025 |
chard | -0.023 |
right | -0.022 |
ours | -0.021 |
rily | -0.021 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
friends | +0.005 |
, | +0.004 |
marched | +0.004 |
came | +0.004 |
family | +0.004 |
Neg logit contributions | |
Here | -0.003 |
chard | -0.003 |
ours | -0.003 |
redd | -0.003 |
right | -0.003 |
Token | calm |
Token ID | 9480 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
sisters | +0.039 |
marched | +0.039 |
came | +0.038 |
mo | +0.038 |
rec | +0.037 |
Neg logit contributions | |
ours | -0.049 |
chard | -0.045 |
Here | -0.043 |
afar | -0.043 |
rily | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | -3.66e-03 |
Pos logit contributions | |
friends | +0.014 |
marched | +0.013 |
sisters | +0.013 |
mo | +0.012 |
brothers | +0.012 |
Neg logit contributions | |
Here | -0.034 |
ours | -0.033 |
chard | -0.033 |
rily | -0.032 |
right | -0.032 |
Token | even |
Token ID | 772 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
Here | +0.008 |
ours | +0.008 |
chard | +0.008 |
redd | +0.007 |
right | +0.007 |
Neg logit contributions | |
friends | -0.004 |
marched | -0.004 |
sisters | -0.003 |
came | -0.003 |
brothers | -0.003 |
Token | when |
Token ID | 618 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
Here | +0.030 |
ours | +0.028 |
rily | +0.028 |
chard | +0.028 |
aman | +0.028 |
Neg logit contributions | |
friends | -0.025 |
marched | -0.022 |
, | -0.022 |
came | -0.021 |
marching | -0.021 |
Token | things |
Token ID | 1243 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
marched | +0.023 |
friends | +0.023 |
sisters | +0.022 |
came | +0.021 |
brothers | +0.021 |
Neg logit contributions | |
Here | -0.032 |
ours | -0.032 |
chard | -0.031 |
redd | -0.029 |
right | -0.028 |
Token | seem |
Token ID | 1283 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
friends | +0.022 |
sisters | +0.021 |
brothers | +0.020 |
marched | +0.020 |
family | +0.019 |
Neg logit contributions | |
Here | -0.028 |
ours | -0.028 |
chard | -0.028 |
right | -0.026 |
redd | -0.025 |
Token | scary |
Token ID | 14343 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
friends | +0.095 |
marched | +0.091 |
sisters | +0.087 |
brothers | +0.084 |
came | +0.082 |
Neg logit contributions | |
ours | -0.126 |
chard | -0.125 |
Here | -0.122 |
redd | -0.117 |
right | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | +2.75e-03 |
Pos logit contributions | |
friends | +0.024 |
sisters | +0.022 |
mo | +0.022 |
marched | +0.022 |
brothers | +0.021 |
Neg logit contributions | |
ours | -0.076 |
Here | -0.075 |
chard | -0.071 |
right | -0.070 |
rily | -0.068 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.48e-03 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.002 |
sisters | +0.002 |
came | +0.002 |
marching | +0.002 |
Neg logit contributions | |
Here | -0.006 |
chard | -0.006 |
ours | -0.006 |
redd | -0.006 |
right | -0.006 |
Token | Once |
Token ID | 7454 |
Feature activation | +6.63e-03 |
Pos logit contributions | |
friends | +0.009 |
sisters | +0.009 |
marched | +0.009 |
helpers | +0.008 |
mo | +0.008 |
Neg logit contributions | |
Here | -0.014 |
chard | -0.013 |
right | -0.013 |
ours | -0.012 |
rily | -0.012 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
friends | +0.014 |
marched | +0.013 |
sisters | +0.013 |
brothers | +0.013 |
came | +0.013 |
Neg logit contributions | |
Here | -0.007 |
chard | -0.007 |
ours | -0.007 |
right | -0.006 |
redd | -0.006 |
Token | friends |
Token ID | 2460 |
Feature activation | -7.79e-03 |
Pos logit contributions | |
Here | +0.009 |
ours | +0.009 |
chard | +0.009 |
redd | +0.009 |
right | +0.009 |
Neg logit contributions | |
marched | -0.003 |
came | -0.003 |
friends | -0.003 |
sisters | -0.002 |
marching | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +4.95e-03 |
Pos logit contributions | |
Here | +0.018 |
chard | +0.018 |
ours | +0.018 |
right | +0.017 |
rily | +0.017 |
Neg logit contributions | |
friends | -0.006 |
marched | -0.006 |
sisters | -0.005 |
came | -0.005 |
brothers | -0.005 |
Token | There |
Token ID | 1318 |
Feature activation | +5.36e-03 |
Pos logit contributions | |
friends | +0.007 |
marched | +0.007 |
, | +0.007 |
brothers | +0.007 |
sisters | +0.007 |
Neg logit contributions | |
chard | -0.008 |
ours | -0.008 |
Here | -0.008 |
redd | -0.008 |
right | -0.008 |
Token | is |
Token ID | 318 |
Feature activation | -3.15e-03 |
Pos logit contributions | |
friends | +0.006 |
marched | +0.005 |
sisters | +0.005 |
, | +0.005 |
came | +0.005 |
Neg logit contributions | |
Here | -0.012 |
chard | -0.011 |
ours | -0.011 |
right | -0.011 |
redd | -0.011 |
Token | nothing |
Token ID | 2147 |
Feature activation | +9.47e-03 |
Pos logit contributions | |
Here | +0.007 |
chard | +0.007 |
rily | +0.007 |
ited | +0.007 |
redd | +0.007 |
Neg logit contributions | |
friends | -0.004 |
, | -0.003 |
marched | -0.003 |
family | -0.003 |
came | -0.003 |
Token | r |
Token ID | 374 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
friends | +0.010 |
marched | +0.009 |
sisters | +0.009 |
brothers | +0.009 |
came | +0.008 |
Neg logit contributions | |
ours | -0.020 |
Here | -0.020 |
chard | -0.020 |
right | -0.019 |
redd | -0.019 |
Token | uder |
Token ID | 26651 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
friends | +0.119 |
marched | +0.115 |
sisters | +0.108 |
came | +0.108 |
family | +0.107 |
Neg logit contributions | |
Here | -0.103 |
chard | -0.101 |
ours | -0.099 |
right | -0.096 |
redd | -0.093 |
Token | than |
Token ID | 621 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
friends | +0.057 |
marched | +0.054 |
sisters | +0.051 |
brothers | +0.050 |
came | +0.049 |
Neg logit contributions | |
Here | -0.088 |
chard | -0.087 |
ours | -0.087 |
redd | -0.082 |
right | -0.082 |
Token | not |
Token ID | 407 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
Here | +0.028 |
chard | +0.027 |
redd | +0.027 |
rily | +0.026 |
ours | +0.026 |
Neg logit contributions | |
friends | -0.015 |
marched | -0.013 |
, | -0.013 |
came | -0.012 |
sisters | -0.012 |
Token | saying |
Token ID | 2282 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
friends | +0.025 |
marched | +0.023 |
, | +0.021 |
came | +0.021 |
sisters | +0.021 |
Neg logit contributions | |
Here | -0.051 |
chard | -0.050 |
ours | -0.048 |
redd | -0.047 |
right | -0.047 |
Token | goodbye |
Token ID | 24829 |
Feature activation | +5.82e-03 |
Pos logit contributions | |
marched | +0.025 |
friends | +0.025 |
sisters | +0.023 |
brothers | +0.022 |
marching | +0.021 |
Neg logit contributions | |
Here | -0.053 |
ours | -0.053 |
chard | -0.052 |
rily | -0.049 |
redd | -0.049 |
Token | brave |
Token ID | 14802 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
marched | +0.023 |
friends | +0.021 |
sisters | +0.021 |
came | +0.021 |
mo | +0.021 |
Neg logit contributions | |
ours | -0.041 |
chard | -0.039 |
Here | -0.039 |
redd | -0.037 |
right | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | -3.54e-03 |
Pos logit contributions | |
marched | +0.017 |
friends | +0.015 |
mo | +0.014 |
marching | +0.013 |
came | +0.013 |
Neg logit contributions | |
ours | -0.057 |
Here | -0.057 |
right | -0.054 |
rily | -0.054 |
chard | -0.054 |
Token | especially |
Token ID | 2592 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
Here | +0.007 |
chard | +0.007 |
ours | +0.007 |
right | +0.007 |
redd | +0.007 |
Neg logit contributions | |
friends | -0.004 |
marched | -0.004 |
, | -0.003 |
sisters | -0.003 |
came | -0.003 |
Token | when |
Token ID | 618 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
Here | +0.050 |
aman | +0.047 |
ours | +0.047 |
chard | +0.047 |
rily | +0.046 |
Neg logit contributions | |
friends | -0.031 |
, | -0.028 |
. | -0.026 |
marched | -0.025 |
brothers | -0.025 |
Token | things |
Token ID | 1243 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
friends | +0.017 |
marched | +0.016 |
sisters | +0.015 |
brothers | +0.014 |
came | +0.014 |
Neg logit contributions | |
Here | -0.026 |
chard | -0.026 |
ours | -0.025 |
right | -0.024 |
redd | -0.024 |
Token | seem |
Token ID | 1283 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
friends | +0.018 |
marched | +0.016 |
sisters | +0.016 |
brothers | +0.015 |
family | +0.015 |
Neg logit contributions | |
Here | -0.031 |
chard | -0.031 |
ours | -0.031 |
right | -0.029 |
redd | -0.029 |
Token | scary |
Token ID | 14343 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
friends | +0.079 |
marched | +0.075 |
sisters | +0.070 |
brothers | +0.068 |
came | +0.067 |
Neg logit contributions | |
chard | -0.135 |
Here | -0.135 |
ours | -0.134 |
redd | -0.128 |
right | -0.128 |
Token | ." |
Token ID | 526 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
friends | +0.020 |
marched | +0.019 |
sisters | +0.017 |
mo | +0.016 |
brothers | +0.016 |
Neg logit contributions | |
Here | -0.078 |
ours | -0.077 |
chard | -0.075 |
right | -0.073 |
rily | -0.072 |
Token | |
Token ID | 220 |
Feature activation | +6.45e-04 |
Pos logit contributions | |
friends | +0.002 |
marched | +0.001 |
, | +0.001 |
sisters | +0.001 |
came | +0.001 |
Neg logit contributions | |
ours | -0.004 |
chard | -0.004 |
Here | -0.004 |
redd | -0.004 |
right | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.44e-03 |
Pos logit contributions | |
friends | +0.000 |
marched | +0.000 |
, | +0.000 |
sisters | +0.000 |
brothers | +0.000 |
Neg logit contributions | |
Here | -0.002 |
chard | -0.002 |
ours | -0.002 |
redd | -0.002 |
right | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +2.51e-03 |
Pos logit contributions | |
ours | +0.004 |
chard | +0.004 |
redd | +0.004 |
Here | +0.004 |
rily | +0.004 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
, | -0.001 |
family | -0.000 |
brothers | -0.000 |
Token | determined |
Token ID | 5295 |
Feature activation | +5.21e-03 |
Pos logit contributions | |
marched | +0.034 |
came | +0.034 |
sisters | +0.033 |
mo | +0.033 |
friends | +0.032 |
Neg logit contributions | |
ours | -0.046 |
chard | -0.044 |
Here | -0.042 |
rily | -0.041 |
right | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | -8.13e-03 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.003 |
sisters | +0.003 |
brothers | +0.003 |
came | +0.003 |
Neg logit contributions | |
Here | -0.013 |
chard | -0.012 |
ours | -0.012 |
right | -0.012 |
redd | -0.012 |
Token | even |
Token ID | 772 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
Here | +0.018 |
chard | +0.017 |
ours | +0.017 |
right | +0.016 |
redd | +0.016 |
Neg logit contributions | |
friends | -0.009 |
marched | -0.008 |
, | -0.007 |
sisters | -0.007 |
came | -0.007 |
Token | when |
Token ID | 618 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
Here | +0.041 |
rily | +0.039 |
ours | +0.039 |
aman | +0.038 |
chard | +0.038 |
Neg logit contributions | |
friends | -0.032 |
, | -0.029 |
marched | -0.027 |
. | -0.026 |
family | -0.026 |
Token | things |
Token ID | 1243 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
friends | +0.018 |
marched | +0.018 |
sisters | +0.016 |
came | +0.016 |
brothers | +0.016 |
Neg logit contributions | |
Here | -0.023 |
ours | -0.023 |
chard | -0.023 |
right | -0.021 |
redd | -0.021 |
Token | seem |
Token ID | 1283 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
friends | +0.020 |
sisters | +0.018 |
marched | +0.018 |
brothers | +0.018 |
family | +0.017 |
Neg logit contributions | |
Here | -0.027 |
ours | -0.026 |
chard | -0.026 |
right | -0.025 |
redd | -0.024 |
Token | tough |
Token ID | 5802 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
friends | +0.093 |
marched | +0.089 |
sisters | +0.085 |
brothers | +0.082 |
came | +0.081 |
Neg logit contributions | |
ours | -0.119 |
chard | -0.119 |
Here | -0.119 |
redd | -0.112 |
right | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | +6.28e-03 |
Pos logit contributions | |
friends | +0.020 |
marched | +0.019 |
mo | +0.017 |
sisters | +0.017 |
brothers | +0.016 |
Neg logit contributions | |
Here | -0.067 |
ours | -0.067 |
chard | -0.064 |
right | -0.064 |
rily | -0.061 |
Token | It |
Token ID | 632 |
Feature activation | +1.59e-03 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.004 |
, | +0.004 |
family | +0.004 |
brothers | +0.004 |
Neg logit contributions | |
chard | -0.015 |
ours | -0.015 |
Here | -0.015 |
redd | -0.015 |
rily | -0.015 |
Token | 's |
Token ID | 338 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
friends | +0.002 |
marched | +0.002 |
sisters | +0.002 |
marching | +0.002 |
mo | +0.002 |
Neg logit contributions | |
Here | -0.003 |
ours | -0.003 |
right | -0.003 |
redd | -0.003 |
chard | -0.003 |
Token | an |
Token ID | 281 |
Feature activation | -4.39e-04 |
Pos logit contributions | |
Here | +0.024 |
chard | +0.023 |
ours | +0.022 |
rily | +0.022 |
redd | +0.022 |
Neg logit contributions | |
friends | -0.012 |
, | -0.011 |
marched | -0.010 |
brothers | -0.010 |
sisters | -0.010 |
Token | she |
Token ID | 673 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
friends | +0.016 |
, | +0.014 |
came | +0.013 |
marched | +0.013 |
family | +0.012 |
Neg logit contributions | |
Here | -0.036 |
chard | -0.034 |
ours | -0.034 |
redd | -0.033 |
rily | -0.033 |
Token | heard |
Token ID | 2982 |
Feature activation | +5.64e-04 |
Pos logit contributions | |
friends | +0.012 |
sisters | +0.011 |
marching | +0.011 |
helpers | +0.011 |
brothers | +0.011 |
Neg logit contributions | |
chard | -0.022 |
ited | -0.021 |
curiously | -0.021 |
rily | -0.021 |
aman | -0.020 |
Token | her |
Token ID | 607 |
Feature activation | -5.38e-03 |
Pos logit contributions | |
friends | +0.001 |
, | +0.000 |
marched | +0.000 |
came | +0.000 |
sisters | +0.000 |
Neg logit contributions | |
Here | -0.001 |
chard | -0.001 |
ours | -0.001 |
redd | -0.001 |
right | -0.001 |
Token | mom |
Token ID | 1995 |
Feature activation | +5.09e-03 |
Pos logit contributions | |
Here | +0.010 |
chard | +0.010 |
ours | +0.010 |
rily | +0.009 |
right | +0.009 |
Neg logit contributions | |
marched | -0.006 |
came | -0.006 |
friends | -0.006 |
mo | -0.005 |
brothers | -0.005 |
Token | calling |
Token ID | 4585 |
Feature activation | -7.26e-03 |
Pos logit contributions | |
friends | +0.006 |
marched | +0.005 |
sisters | +0.005 |
brothers | +0.005 |
helpers | +0.005 |
Neg logit contributions | |
Here | -0.010 |
chard | -0.010 |
ours | -0.010 |
aman | -0.010 |
right | -0.010 |
Token | from |
Token ID | 422 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
Here | +0.014 |
chard | +0.014 |
ours | +0.014 |
right | +0.013 |
redd | +0.013 |
Neg logit contributions | |
friends | -0.009 |
marched | -0.008 |
sisters | -0.008 |
brothers | -0.008 |
, | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
friends | +0.066 |
, | +0.058 |
marched | +0.057 |
. | +0.052 |
came | +0.052 |
Neg logit contributions | |
Here | -0.156 |
chard | -0.150 |
ours | -0.149 |
redd | -0.147 |
right | -0.143 |
Token | house |
Token ID | 2156 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
friends | +0.024 |
marched | +0.024 |
came | +0.021 |
sisters | +0.021 |
, | +0.021 |
Neg logit contributions | |
chard | -0.036 |
Here | -0.036 |
ours | -0.035 |
redd | -0.034 |
right | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +2.82e-03 |
Pos logit contributions | |
friends | +0.013 |
marched | +0.011 |
sisters | +0.009 |
brothers | +0.009 |
family | +0.007 |
Neg logit contributions | |
chard | -0.056 |
Here | -0.055 |
ours | -0.054 |
right | -0.054 |
rily | -0.054 |
Token |
|
Token ID | 198 |
Feature activation | -6.65e-04 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.003 |
, | +0.003 |
came | +0.002 |
sisters | +0.002 |
Neg logit contributions | |
chard | -0.006 |
ours | -0.006 |
Here | -0.006 |
redd | -0.006 |
right | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +5.36e-03 |
Pos logit contributions | |
Here | +0.002 |
chard | +0.002 |
ours | +0.002 |
right | +0.002 |
redd | +0.002 |
Neg logit contributions | |
friends | -0.000 |
marched | -0.000 |
sisters | -0.000 |
, | -0.000 |
brothers | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +9.90e-03 |
Pos logit contributions | |
chard | +0.040 |
Here | +0.040 |
curiously | +0.039 |
right | +0.039 |
ours | +0.037 |
Neg logit contributions | |
friends | -0.011 |
marched | -0.010 |
sisters | -0.010 |
brothers | -0.009 |
siblings | -0.008 |
Token | Jack |
Token ID | 3619 |
Feature activation | -6.71e-03 |
Pos logit contributions | |
friends | +0.012 |
, | +0.011 |
marched | +0.011 |
came | +0.010 |
brothers | +0.010 |
Neg logit contributions | |
Here | -0.021 |
ours | -0.020 |
chard | -0.020 |
redd | -0.020 |
right | -0.019 |
Token | 's |
Token ID | 338 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
chard | +0.012 |
curiously | +0.011 |
ited | +0.011 |
redd | +0.011 |
aman | +0.011 |
Neg logit contributions | |
friends | -0.008 |
helpers | -0.008 |
sisters | -0.007 |
brothers | -0.007 |
siblings | -0.007 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.25e-04 |
Pos logit contributions | |
chard | +0.020 |
redd | +0.019 |
aman | +0.019 |
right | +0.019 |
Here | +0.019 |
Neg logit contributions | |
marched | -0.010 |
comes | -0.010 |
came | -0.010 |
sisters | -0.009 |
' | -0.009 |
Token | called |
Token ID | 1444 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
friends | +0.000 |
helpers | +0.000 |
marched | +0.000 |
sisters | +0.000 |
brothers | +0.000 |
Neg logit contributions | |
chard | -0.000 |
aman | -0.000 |
ited | -0.000 |
curiously | -0.000 |
Here | -0.000 |
Token | from |
Token ID | 422 |
Feature activation | +6.72e-02 |
Pos logit contributions | |
chard | +0.023 |
Here | +0.022 |
ours | +0.022 |
right | +0.021 |
rily | +0.020 |
Neg logit contributions | |
friends | -0.020 |
marched | -0.019 |
sisters | -0.018 |
brothers | -0.018 |
family | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
friends | +0.058 |
marched | +0.051 |
, | +0.048 |
came | +0.045 |
brothers | +0.044 |
Neg logit contributions | |
Here | -0.162 |
chard | -0.157 |
ours | -0.155 |
redd | -0.154 |
right | -0.150 |
Token | doorway |
Token ID | 32439 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
friends | +0.018 |
marched | +0.017 |
brothers | +0.016 |
sisters | +0.016 |
, | +0.015 |
Neg logit contributions | |
chard | -0.031 |
Here | -0.030 |
redd | -0.029 |
ours | -0.028 |
aman | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +6.88e-03 |
Pos logit contributions | |
friends | +0.008 |
marched | +0.007 |
sisters | +0.006 |
brothers | +0.006 |
marching | +0.006 |
Neg logit contributions | |
Here | -0.036 |
chard | -0.036 |
right | -0.035 |
ours | -0.034 |
rily | -0.034 |
Token | " |
Token ID | 366 |
Feature activation | +2.99e-03 |
Pos logit contributions | |
friends | +0.010 |
marched | +0.009 |
sisters | +0.008 |
brothers | +0.008 |
marching | +0.008 |
Neg logit contributions | |
Here | -0.013 |
chard | -0.012 |
ours | -0.012 |
right | -0.012 |
redd | -0.011 |
Token | Jack |
Token ID | 14295 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.004 |
came | +0.004 |
sisters | +0.004 |
family | +0.003 |
Neg logit contributions | |
Here | -0.006 |
chard | -0.006 |
ours | -0.006 |
rily | -0.005 |
redd | -0.005 |
Token | any |
Token ID | 597 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.003 |
, | +0.003 |
came | +0.003 |
sisters | +0.003 |
Neg logit contributions | |
Here | -0.009 |
chard | -0.008 |
aman | -0.008 |
ours | -0.008 |
right | -0.008 |
Token | letter |
Token ID | 3850 |
Feature activation | -6.06e-03 |
Pos logit contributions | |
friends | +0.019 |
, | +0.017 |
marched | +0.017 |
sisters | +0.016 |
brothers | +0.016 |
Neg logit contributions | |
Here | -0.019 |
chard | -0.019 |
ours | -0.017 |
redd | -0.017 |
right | -0.017 |
Token | or |
Token ID | 393 |
Feature activation | -1.24e-03 |
Pos logit contributions | |
Here | +0.015 |
chard | +0.015 |
ours | +0.015 |
right | +0.014 |
redd | +0.014 |
Neg logit contributions | |
friends | -0.004 |
marched | -0.004 |
sisters | -0.003 |
brothers | -0.003 |
marching | -0.003 |
Token | phone |
Token ID | 3072 |
Feature activation | +1.18e-03 |
Pos logit contributions | |
Here | +0.003 |
right | +0.002 |
rily | +0.002 |
chard | +0.002 |
redd | +0.002 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.001 |
, | -0.001 |
came | -0.001 |
sisters | -0.001 |
Token | call |
Token ID | 869 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
friends | +0.001 |
marched | +0.001 |
sisters | +0.000 |
brothers | +0.000 |
marching | +0.000 |
Neg logit contributions | |
Here | -0.003 |
chard | -0.003 |
ours | -0.003 |
right | -0.003 |
redd | -0.003 |
Token | from |
Token ID | 422 |
Feature activation | +6.72e-02 |
Pos logit contributions | |
friends | +0.013 |
, | +0.012 |
marched | +0.011 |
. | +0.011 |
came | +0.011 |
Neg logit contributions | |
Here | -0.034 |
chard | -0.033 |
redd | -0.033 |
ours | -0.032 |
right | -0.032 |
Token | grandma |
Token ID | 49890 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
friends | +0.058 |
, | +0.050 |
. | +0.048 |
family | +0.044 |
marched | +0.043 |
Neg logit contributions | |
Here | -0.170 |
redd | -0.163 |
chard | -0.160 |
ours | -0.158 |
right | -0.156 |
Token | . |
Token ID | 13 |
Feature activation | +8.88e-04 |
Pos logit contributions | |
friends | +0.009 |
marched | +0.009 |
marching | +0.006 |
sisters | +0.006 |
brothers | +0.006 |
Neg logit contributions | |
Here | -0.057 |
chard | -0.057 |
ours | -0.057 |
right | -0.055 |
rily | -0.055 |
Token | She |
Token ID | 1375 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
friends | +0.001 |
, | +0.001 |
marched | +0.001 |
. | +0.001 |
came | +0.001 |
Neg logit contributions | |
chard | -0.002 |
ours | -0.002 |
Here | -0.002 |
redd | -0.002 |
rily | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +5.49e-03 |
Pos logit contributions | |
friends | +0.013 |
marched | +0.012 |
came | +0.011 |
, | +0.011 |
sisters | +0.010 |
Neg logit contributions | |
Here | -0.034 |
chard | -0.033 |
ours | -0.033 |
redd | -0.032 |
right | -0.032 |
Token | confused |
Token ID | 10416 |
Feature activation | -5.52e-04 |
Pos logit contributions | |
friends | +0.006 |
marched | +0.006 |
, | +0.005 |
sisters | +0.005 |
brothers | +0.005 |
Neg logit contributions | |
chard | -0.011 |
Here | -0.011 |
ours | -0.011 |
right | -0.010 |
redd | -0.010 |
Token | done |
Token ID | 1760 |
Feature activation | +8.72e-03 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.004 |
sisters | +0.004 |
brothers | +0.004 |
came | +0.003 |
Neg logit contributions | |
ours | -0.008 |
chard | -0.008 |
Here | -0.008 |
right | -0.008 |
redd | -0.008 |
Token | by |
Token ID | 416 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
marched | +0.007 |
friends | +0.006 |
mo | +0.006 |
sisters | +0.006 |
came | +0.005 |
Neg logit contributions | |
ours | -0.021 |
chard | -0.020 |
Here | -0.020 |
right | -0.020 |
rily | -0.020 |
Token | asking |
Token ID | 4737 |
Feature activation | +9.64e-03 |
Pos logit contributions | |
friends | +0.018 |
marched | +0.018 |
came | +0.017 |
sisters | +0.017 |
brothers | +0.016 |
Neg logit contributions | |
Here | -0.022 |
chard | -0.021 |
ours | -0.021 |
right | -0.020 |
redd | -0.020 |
Token | for |
Token ID | 329 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
friends | +0.007 |
, | +0.006 |
marched | +0.006 |
sisters | +0.005 |
brothers | +0.005 |
Neg logit contributions | |
Here | -0.024 |
chard | -0.024 |
ours | -0.024 |
redd | -0.023 |
right | -0.023 |
Token | help |
Token ID | 1037 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
marched | +0.029 |
friends | +0.028 |
came | +0.026 |
sisters | +0.026 |
brothers | +0.025 |
Neg logit contributions | |
Here | -0.058 |
ours | -0.058 |
chard | -0.057 |
right | -0.054 |
redd | -0.053 |
Token | from |
Token ID | 422 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
friends | +0.016 |
marched | +0.015 |
sisters | +0.012 |
brothers | +0.012 |
came | +0.011 |
Neg logit contributions | |
Here | -0.067 |
chard | -0.066 |
ours | -0.066 |
right | -0.064 |
redd | -0.063 |
Token | others |
Token ID | 1854 |
Feature activation | +8.58e-03 |
Pos logit contributions | |
friends | +0.082 |
marched | +0.070 |
, | +0.069 |
brothers | +0.066 |
family | +0.066 |
Neg logit contributions | |
Here | -0.141 |
chard | -0.134 |
redd | -0.133 |
ours | -0.131 |
right | -0.130 |
Token | . |
Token ID | 13 |
Feature activation | +7.22e-03 |
Pos logit contributions | |
marched | +0.005 |
friends | +0.005 |
came | +0.004 |
mo | +0.004 |
sisters | +0.004 |
Neg logit contributions | |
Here | -0.022 |
ours | -0.022 |
chard | -0.022 |
right | -0.021 |
rily | -0.020 |
Token | And |
Token ID | 843 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
friends | +0.004 |
brothers | +0.003 |
, | +0.003 |
marched | +0.003 |
family | +0.003 |
Neg logit contributions | |
chard | -0.019 |
ours | -0.019 |
redd | -0.019 |
rily | -0.019 |
Here | -0.018 |
Token | sometimes |
Token ID | 3360 |
Feature activation | +3.01e-03 |
Pos logit contributions | |
Here | +0.045 |
chard | +0.045 |
ours | +0.044 |
redd | +0.042 |
right | +0.042 |
Neg logit contributions | |
friends | -0.025 |
marched | -0.022 |
, | -0.021 |
sisters | -0.021 |
brothers | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +4.44e-03 |
Pos logit contributions | |
marched | +0.002 |
friends | +0.002 |
mo | +0.002 |
sisters | +0.002 |
came | +0.001 |
Neg logit contributions | |
ours | -0.007 |
Here | -0.007 |
chard | -0.007 |
right | -0.007 |
redd | -0.007 |
Token | if |
Token ID | 611 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
Here | +0.042 |
ours | +0.041 |
chard | +0.040 |
aman | +0.040 |
ited | +0.039 |
Neg logit contributions | |
friends | -0.022 |
, | -0.019 |
marched | -0.019 |
. | -0.018 |
brothers | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +5.21e-03 |
Pos logit contributions | |
friends | +0.025 |
marched | +0.023 |
, | +0.022 |
came | +0.021 |
sisters | +0.021 |
Neg logit contributions | |
Here | -0.038 |
chard | -0.038 |
ours | -0.037 |
redd | -0.036 |
right | -0.036 |
Token | say |
Token ID | 910 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
friends | +0.006 |
marched | +0.006 |
, | +0.006 |
came | +0.005 |
sisters | +0.005 |
Neg logit contributions | |
Here | -0.011 |
chard | -0.010 |
ours | -0.010 |
redd | -0.010 |
right | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +4.92e-03 |
Pos logit contributions | |
friends | +0.015 |
marched | +0.014 |
sisters | +0.013 |
, | +0.013 |
came | +0.013 |
Neg logit contributions | |
Here | -0.024 |
chard | -0.023 |
ours | -0.023 |
redd | -0.022 |
right | -0.022 |
Token | " |
Token ID | 366 |
Feature activation | +3.06e-03 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.004 |
, | +0.004 |
sisters | +0.004 |
came | +0.004 |
Neg logit contributions | |
Here | -0.011 |
chard | -0.011 |
ours | -0.011 |
redd | -0.010 |
right | -0.010 |
Token | sh |
Token ID | 1477 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
marched | +0.004 |
friends | +0.004 |
came | +0.004 |
cl | +0.004 |
' | +0.004 |
Neg logit contributions | |
ours | -0.006 |
chard | -0.005 |
Here | -0.005 |
rily | -0.005 |
aly | -0.005 |
Token | hhhh |
Token ID | 36607 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
friends | +0.099 |
, | +0.094 |
marched | +0.092 |
brothers | +0.087 |
came | +0.087 |
Neg logit contributions | |
chard | -0.118 |
Here | -0.115 |
ours | -0.113 |
redd | -0.109 |
rily | -0.106 |
Token | ". |
Token ID | 1911 |
Feature activation | -3.25e-03 |
Pos logit contributions | |
friends | +0.046 |
marched | +0.044 |
sisters | +0.042 |
brothers | +0.041 |
marching | +0.041 |
Neg logit contributions | |
Here | -0.048 |
right | -0.045 |
chard | -0.045 |
ours | -0.044 |
aman | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | -6.36e-04 |
Pos logit contributions | |
ours | +0.007 |
redd | +0.007 |
chard | +0.007 |
ited | +0.007 |
right | +0.007 |
Neg logit contributions | |
friends | -0.003 |
, | -0.003 |
marched | -0.003 |
. | -0.003 |
brothers | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +3.40e-03 |
Pos logit contributions | |
chard | +0.002 |
ours | +0.002 |
redd | +0.002 |
Here | +0.002 |
rily | +0.002 |
Neg logit contributions | |
friends | -0.000 |
marched | -0.000 |
, | -0.000 |
brothers | -0.000 |
came | -0.000 |
Token | Mom |
Token ID | 29252 |
Feature activation | -2.65e-03 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.005 |
brothers | +0.004 |
sisters | +0.004 |
, | +0.004 |
Neg logit contributions | |
ours | -0.006 |
chard | -0.006 |
Here | -0.006 |
redd | -0.006 |
rily | -0.006 |
Token | prepared |
Token ID | 5597 |
Feature activation | -9.74e-04 |
Pos logit contributions | |
marched | +0.016 |
sisters | +0.014 |
friends | +0.014 |
brothers | +0.014 |
mo | +0.013 |
Neg logit contributions | |
ours | -0.027 |
chard | -0.026 |
Here | -0.025 |
right | -0.024 |
redd | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -2.08e-03 |
Pos logit contributions | |
Here | +0.002 |
chard | +0.002 |
ours | +0.002 |
redd | +0.002 |
right | +0.002 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
, | -0.001 |
sisters | -0.001 |
came | -0.001 |
Token | even |
Token ID | 772 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
Here | +0.004 |
chard | +0.004 |
ours | +0.004 |
right | +0.004 |
redd | +0.004 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.002 |
, | -0.002 |
sisters | -0.002 |
came | -0.002 |
Token | when |
Token ID | 618 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
Here | +0.037 |
chard | +0.035 |
ours | +0.035 |
rily | +0.034 |
aman | +0.034 |
Neg logit contributions | |
friends | -0.029 |
, | -0.025 |
marched | -0.025 |
sisters | -0.024 |
marching | -0.023 |
Token | things |
Token ID | 1243 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
friends | +0.023 |
marched | +0.022 |
sisters | +0.021 |
came | +0.020 |
brothers | +0.020 |
Neg logit contributions | |
Here | -0.028 |
chard | -0.027 |
ours | -0.027 |
right | -0.025 |
redd | -0.025 |
Token | seem |
Token ID | 1283 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
friends | +0.016 |
sisters | +0.015 |
marched | +0.015 |
brothers | +0.015 |
family | +0.014 |
Neg logit contributions | |
Here | -0.025 |
ours | -0.024 |
chard | -0.024 |
right | -0.023 |
redd | -0.022 |
Token | mild |
Token ID | 11607 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
friends | +0.086 |
marched | +0.081 |
sisters | +0.075 |
brothers | +0.074 |
came | +0.073 |
Neg logit contributions | |
Here | -0.126 |
chard | -0.126 |
ours | -0.124 |
right | -0.118 |
redd | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | +6.82e-03 |
Pos logit contributions | |
friends | +0.022 |
marched | +0.020 |
sisters | +0.018 |
brothers | +0.017 |
family | +0.017 |
Neg logit contributions | |
Here | -0.059 |
ours | -0.059 |
right | -0.057 |
chard | -0.057 |
rily | -0.056 |
Token | â |
Token ID | 22940 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
friends | +0.006 |
marched | +0.005 |
, | +0.005 |
brothers | +0.005 |
sisters | +0.005 |
Neg logit contributions | |
chard | -0.016 |
ours | -0.016 |
Here | -0.015 |
redd | -0.015 |
right | -0.015 |
Token | € |
Token ID | 26391 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
Here | +0.038 |
chard | +0.036 |
ours | +0.035 |
right | +0.034 |
redd | +0.033 |
Neg logit contributions | |
friends | -0.046 |
marched | -0.043 |
sisters | -0.042 |
brothers | -0.041 |
family | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | -4.42e-03 |
Pos logit contributions | |
sisters | +0.019 |
friends | +0.018 |
marched | +0.018 |
marching | +0.017 |
helpers | +0.017 |
Neg logit contributions | |
Here | -0.028 |
ours | -0.026 |
aman | -0.025 |
chard | -0.024 |
right | -0.024 |
Token | she |
Token ID | 673 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
friends | +0.032 |
, | +0.031 |
came | +0.028 |
marched | +0.028 |
family | +0.027 |
Neg logit contributions | |
Here | -0.060 |
ours | -0.057 |
redd | -0.056 |
rily | -0.056 |
chard | -0.054 |
Token | heard |
Token ID | 2982 |
Feature activation | -5.05e-04 |
Pos logit contributions | |
friends | +0.011 |
marched | +0.010 |
sisters | +0.010 |
brothers | +0.009 |
marching | +0.009 |
Neg logit contributions | |
chard | -0.024 |
Here | -0.023 |
redd | -0.022 |
ours | -0.022 |
right | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | -5.51e-03 |
Pos logit contributions | |
Here | +0.001 |
chard | +0.001 |
ours | +0.001 |
redd | +0.001 |
rily | +0.001 |
Neg logit contributions | |
friends | -0.000 |
marched | -0.000 |
, | -0.000 |
came | -0.000 |
sisters | -0.000 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.88e-03 |
Pos logit contributions | |
Here | +0.012 |
chard | +0.011 |
ours | +0.011 |
right | +0.011 |
curiously | +0.011 |
Neg logit contributions | |
marched | -0.005 |
friends | -0.004 |
came | -0.004 |
brothers | -0.004 |
sisters | -0.004 |
Token | calling |
Token ID | 4585 |
Feature activation | -7.60e-03 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.004 |
brothers | +0.004 |
sisters | +0.004 |
helpers | +0.004 |
Neg logit contributions | |
Here | -0.008 |
chard | -0.008 |
ours | -0.007 |
right | -0.007 |
aman | -0.007 |
Token | from |
Token ID | 422 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
Here | +0.014 |
chard | +0.014 |
ours | +0.014 |
right | +0.013 |
rily | +0.013 |
Neg logit contributions | |
friends | -0.010 |
marched | -0.009 |
brothers | -0.009 |
sisters | -0.009 |
family | -0.008 |
Token | inside |
Token ID | 2641 |
Feature activation | +7.34e-03 |
Pos logit contributions | |
friends | +0.065 |
marched | +0.057 |
, | +0.056 |
came | +0.051 |
marching | +0.051 |
Neg logit contributions | |
Here | -0.154 |
chard | -0.148 |
ours | -0.146 |
redd | -0.145 |
right | -0.141 |
Token | the |
Token ID | 262 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.004 |
sisters | +0.004 |
brothers | +0.004 |
came | +0.003 |
Neg logit contributions | |
Here | -0.018 |
chard | -0.018 |
ours | -0.018 |
right | -0.018 |
aman | -0.017 |
Token | house |
Token ID | 2156 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
friends | +0.016 |
marched | +0.015 |
brothers | +0.014 |
came | +0.013 |
sisters | +0.013 |
Neg logit contributions | |
Here | -0.032 |
chard | -0.032 |
ours | -0.031 |
redd | -0.030 |
right | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +4.79e-03 |
Pos logit contributions | |
friends | +0.010 |
marched | +0.009 |
sisters | +0.007 |
brothers | +0.007 |
marching | +0.006 |
Neg logit contributions | |
Here | -0.052 |
chard | -0.052 |
ours | -0.051 |
right | -0.051 |
aman | -0.050 |
Token | |
Token ID | 220 |
Feature activation | -5.47e-03 |
Pos logit contributions | |
friends | +0.006 |
, | +0.006 |
marched | +0.006 |
came | +0.005 |
. | +0.005 |
Neg logit contributions | |
chard | -0.009 |
ours | -0.009 |
Here | -0.009 |
redd | -0.009 |
right | -0.009 |
Token | hurt |
Token ID | 5938 |
Feature activation | +8.49e-03 |
Pos logit contributions | |
marched | +0.026 |
friends | +0.026 |
came | +0.023 |
sisters | +0.023 |
, | +0.023 |
Neg logit contributions | |
ours | -0.049 |
Here | -0.048 |
chard | -0.048 |
right | -0.045 |
redd | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-03 |
Pos logit contributions | |
marched | +0.007 |
friends | +0.006 |
sisters | +0.005 |
mo | +0.005 |
came | +0.005 |
Neg logit contributions | |
chard | -0.020 |
ours | -0.020 |
Here | -0.020 |
right | -0.019 |
rily | -0.019 |
Token | Just |
Token ID | 2329 |
Feature activation | +7.11e-03 |
Pos logit contributions | |
chard | +0.003 |
Here | +0.003 |
ours | +0.003 |
redd | +0.002 |
rily | +0.002 |
Neg logit contributions | |
friends | -0.003 |
marched | -0.002 |
brothers | -0.002 |
, | -0.002 |
sisters | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -3.85e-04 |
Pos logit contributions | |
friends | +0.008 |
, | +0.007 |
marched | +0.007 |
. | +0.006 |
came | +0.006 |
Neg logit contributions | |
rily | -0.016 |
chard | -0.016 |
Here | -0.015 |
aman | -0.015 |
redd | -0.015 |
Token | little |
Token ID | 1310 |
Feature activation | -7.43e-03 |
Pos logit contributions | |
Here | +0.001 |
chard | +0.001 |
ours | +0.001 |
redd | +0.001 |
right | +0.001 |
Neg logit contributions | |
friends | -0.000 |
marched | -0.000 |
sisters | -0.000 |
, | -0.000 |
came | -0.000 |
Token | bru |
Token ID | 18145 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
Here | +0.014 |
chard | +0.014 |
ours | +0.014 |
right | +0.013 |
redd | +0.013 |
Neg logit contributions | |
friends | -0.010 |
marched | -0.009 |
, | -0.009 |
sisters | -0.008 |
came | -0.008 |
Token | ise |
Token ID | 786 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
marched | +0.092 |
friends | +0.090 |
sisters | +0.083 |
blast | +0.082 |
family | +0.080 |
Neg logit contributions | |
chard | -0.110 |
Here | -0.108 |
ours | -0.104 |
afar | -0.102 |
rily | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e-03 |
Pos logit contributions | |
friends | +0.012 |
marched | +0.010 |
sisters | +0.008 |
brothers | +0.008 |
came | +0.008 |
Neg logit contributions | |
Here | -0.057 |
chard | -0.056 |
ours | -0.056 |
right | -0.054 |
redd | -0.054 |
Token | Be |
Token ID | 1355 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
friends | +0.002 |
marched | +0.002 |
brothers | +0.002 |
, | +0.002 |
sisters | +0.002 |
Neg logit contributions | |
chard | -0.003 |
ours | -0.003 |
aman | -0.002 |
rily | -0.002 |
redd | -0.002 |
Token | careful |
Token ID | 8161 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
friends | +0.016 |
marched | +0.016 |
sisters | +0.014 |
came | +0.014 |
marching | +0.014 |
Neg logit contributions | |
Here | -0.029 |
ours | -0.028 |
chard | -0.028 |
right | -0.028 |
redd | -0.027 |
Token | next |
Token ID | 1306 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
marched | +0.008 |
friends | +0.008 |
sisters | +0.006 |
came | +0.006 |
mo | +0.006 |
Neg logit contributions | |
Here | -0.025 |
ours | -0.025 |
chard | -0.025 |
right | -0.024 |
rily | -0.024 |
Token | faith |
Token ID | 4562 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
marched | +0.009 |
marching | +0.009 |
friends | +0.009 |
mo | +0.009 |
brothers | +0.008 |
Neg logit contributions | |
ours | -0.011 |
Here | -0.011 |
chard | -0.011 |
redd | -0.011 |
right | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +6.32e-04 |
Pos logit contributions | |
friends | +0.010 |
marched | +0.009 |
, | +0.008 |
sisters | +0.008 |
came | +0.007 |
Neg logit contributions | |
Here | -0.029 |
chard | -0.028 |
ours | -0.028 |
redd | -0.027 |
right | -0.027 |
Token | even |
Token ID | 772 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
friends | +0.001 |
marched | +0.001 |
, | +0.001 |
sisters | +0.001 |
came | +0.001 |
Neg logit contributions | |
Here | -0.001 |
chard | -0.001 |
ours | -0.001 |
right | -0.001 |
redd | -0.001 |
Token | when |
Token ID | 618 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
Here | +0.037 |
ours | +0.035 |
rily | +0.035 |
aman | +0.035 |
icer | +0.034 |
Neg logit contributions | |
friends | -0.025 |
, | -0.023 |
. | -0.021 |
on | -0.021 |
marched | -0.020 |
Token | things |
Token ID | 1243 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
friends | +0.018 |
marched | +0.017 |
sisters | +0.016 |
, | +0.015 |
brothers | +0.015 |
Neg logit contributions | |
Here | -0.028 |
chard | -0.028 |
ours | -0.027 |
right | -0.026 |
redd | -0.026 |
Token | seem |
Token ID | 1283 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
friends | +0.016 |
sisters | +0.015 |
marched | +0.015 |
brothers | +0.015 |
family | +0.014 |
Neg logit contributions | |
Here | -0.025 |
chard | -0.025 |
ours | -0.024 |
right | -0.024 |
redd | -0.023 |
Token | impossible |
Token ID | 5340 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
friends | +0.091 |
marched | +0.087 |
sisters | +0.082 |
brothers | +0.080 |
came | +0.078 |
Neg logit contributions | |
chard | -0.118 |
Here | -0.117 |
ours | -0.117 |
redd | -0.111 |
right | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | +2.15e-03 |
Pos logit contributions | |
friends | +0.008 |
marched | +0.007 |
brothers | +0.006 |
sisters | +0.006 |
mo | +0.005 |
Neg logit contributions | |
Here | -0.035 |
ours | -0.035 |
chard | -0.035 |
right | -0.034 |
redd | -0.033 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +5.13e-03 |
Pos logit contributions | |
friends | +0.002 |
marched | +0.001 |
sisters | +0.001 |
, | +0.001 |
came | +0.001 |
Neg logit contributions | |
Here | -0.005 |
chard | -0.005 |
ours | -0.005 |
right | -0.005 |
redd | -0.005 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
friends | +0.007 |
sisters | +0.006 |
marched | +0.006 |
helpers | +0.006 |
marching | +0.006 |
Neg logit contributions | |
Here | -0.009 |
chard | -0.009 |
right | -0.008 |
rily | -0.008 |
Here | -0.008 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
friends | +0.008 |
, | +0.007 |
marched | +0.007 |
came | +0.007 |
family | +0.007 |
Neg logit contributions | |
Here | -0.005 |
chard | -0.004 |
ours | -0.004 |
redd | -0.004 |
right | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
friends | +0.000 |
marched | +0.000 |
sisters | +0.000 |
brothers | +0.000 |
marching | +0.000 |
Neg logit contributions | |
Here | -0.003 |
chard | -0.003 |
ours | -0.002 |
right | -0.002 |
redd | -0.002 |
Token | Daniel |
Token ID | 7806 |
Feature activation | +5.44e-03 |
Pos logit contributions | |
friends | +0.035 |
marched | +0.033 |
, | +0.031 |
came | +0.030 |
brothers | +0.029 |
Neg logit contributions | |
Here | -0.059 |
chard | -0.057 |
ours | -0.056 |
redd | -0.054 |
right | -0.054 |
Token | heard |
Token ID | 2982 |
Feature activation | -6.01e-03 |
Pos logit contributions | |
friends | +0.006 |
sisters | +0.005 |
marching | +0.005 |
brothers | +0.005 |
marched | +0.005 |
Neg logit contributions | |
chard | -0.011 |
Here | -0.010 |
ited | -0.010 |
rily | -0.010 |
right | -0.010 |
Token | someone |
Token ID | 2130 |
Feature activation | +2.97e-03 |
Pos logit contributions | |
Here | +0.013 |
chard | +0.013 |
ours | +0.013 |
redd | +0.012 |
right | +0.012 |
Neg logit contributions | |
friends | -0.006 |
marched | -0.006 |
, | -0.005 |
came | -0.005 |
brothers | -0.005 |
Token | calling |
Token ID | 4585 |
Feature activation | -5.26e-03 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.003 |
sisters | +0.003 |
brothers | +0.003 |
family | +0.003 |
Neg logit contributions | |
chard | -0.006 |
Here | -0.006 |
ours | -0.006 |
right | -0.006 |
rily | -0.006 |
Token | from |
Token ID | 422 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
Here | +0.009 |
chard | +0.009 |
ours | +0.009 |
rily | +0.008 |
right | +0.008 |
Neg logit contributions | |
friends | -0.008 |
sisters | -0.007 |
marched | -0.007 |
brothers | -0.007 |
family | -0.006 |
Token | another |
Token ID | 1194 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
friends | +0.065 |
, | +0.057 |
marched | +0.057 |
. | +0.053 |
marching | +0.052 |
Neg logit contributions | |
Here | -0.153 |
chard | -0.147 |
ours | -0.145 |
redd | -0.145 |
right | -0.140 |
Token | room |
Token ID | 2119 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
friends | +0.016 |
marched | +0.015 |
sisters | +0.013 |
came | +0.012 |
brothers | +0.012 |
Neg logit contributions | |
Here | -0.054 |
chard | -0.053 |
ours | -0.052 |
right | -0.051 |
redd | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +7.76e-03 |
Pos logit contributions | |
friends | +0.013 |
marched | +0.011 |
sisters | +0.011 |
brothers | +0.009 |
marching | +0.008 |
Neg logit contributions | |
chard | -0.047 |
right | -0.046 |
aman | -0.046 |
Here | -0.045 |
ours | -0.045 |
Token | It |
Token ID | 632 |
Feature activation | -8.20e-03 |
Pos logit contributions | |
friends | +0.011 |
marched | +0.011 |
, | +0.010 |
came | +0.010 |
brothers | +0.010 |
Neg logit contributions | |
chard | -0.014 |
Here | -0.014 |
ours | -0.014 |
redd | -0.013 |
right | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
chard | +0.015 |
right | +0.015 |
curiously | +0.015 |
Here | +0.015 |
aman | +0.015 |
Neg logit contributions | |
friends | -0.009 |
sisters | -0.008 |
helpers | -0.008 |
brothers | -0.008 |
siblings | -0.007 |
Token | lips |
Token ID | 11914 |
Feature activation | +1.07e-03 |
Pos logit contributions | |
Here | +0.019 |
chard | +0.019 |
ours | +0.019 |
redd | +0.018 |
right | +0.018 |
Neg logit contributions | |
friends | -0.012 |
marched | -0.012 |
came | -0.011 |
sisters | -0.011 |
brothers | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +2.11e-03 |
Pos logit contributions | |
, | +0.000 |
friends | +0.000 |
marched | +0.000 |
. | +0.000 |
came | +0.000 |
Neg logit contributions | |
Here | -0.003 |
ours | -0.003 |
chard | -0.003 |
redd | -0.003 |
right | -0.003 |
Token | made |
Token ID | 925 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
friends | +0.002 |
marched | +0.002 |
sisters | +0.002 |
brothers | +0.002 |
marching | +0.002 |
Neg logit contributions | |
chard | -0.005 |
Here | -0.005 |
ours | -0.004 |
redd | -0.004 |
right | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -5.28e-03 |
Pos logit contributions | |
chard | +0.035 |
Here | +0.034 |
ours | +0.033 |
redd | +0.032 |
right | +0.032 |
Neg logit contributions | |
friends | -0.018 |
marched | -0.015 |
brothers | -0.014 |
came | -0.014 |
, | -0.014 |
Token | " |
Token ID | 366 |
Feature activation | +1.41e-03 |
Pos logit contributions | |
Here | +0.012 |
chard | +0.012 |
ours | +0.011 |
right | +0.011 |
redd | +0.011 |
Neg logit contributions | |
friends | -0.006 |
marched | -0.005 |
sisters | -0.005 |
, | -0.005 |
family | -0.005 |
Token | sh |
Token ID | 1477 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
friends | +0.002 |
marched | +0.002 |
came | +0.002 |
cl | +0.002 |
. | +0.002 |
Neg logit contributions | |
ours | -0.002 |
Here | -0.002 |
chard | -0.002 |
aman | -0.002 |
rily | -0.002 |
Token | hh |
Token ID | 12337 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
friends | +0.101 |
, | +0.096 |
marched | +0.093 |
came | +0.090 |
. | +0.088 |
Neg logit contributions | |
chard | -0.115 |
Here | -0.113 |
ours | -0.107 |
redd | -0.104 |
rily | -0.101 |
Token | " |
Token ID | 1 |
Feature activation | +8.24e-03 |
Pos logit contributions | |
friends | +0.025 |
marched | +0.023 |
sisters | +0.021 |
, | +0.021 |
came | +0.021 |
Neg logit contributions | |
Here | -0.046 |
chard | -0.046 |
ours | -0.045 |
redd | -0.043 |
right | -0.043 |
Token | sound |
Token ID | 2128 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
friends | +0.006 |
marched | +0.005 |
, | +0.005 |
came | +0.005 |
brothers | +0.005 |
Neg logit contributions | |
Here | -0.021 |
chard | -0.020 |
ours | -0.020 |
redd | -0.019 |
right | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +2.42e-03 |
Pos logit contributions | |
friends | +0.020 |
marched | +0.018 |
sisters | +0.016 |
brothers | +0.016 |
marching | +0.015 |
Neg logit contributions | |
Here | -0.055 |
chard | -0.054 |
ours | -0.053 |
right | -0.052 |
rily | -0.052 |
Token | All |
Token ID | 1439 |
Feature activation | +9.31e-03 |
Pos logit contributions | |
friends | +0.002 |
marched | +0.002 |
, | +0.002 |
brothers | +0.002 |
sisters | +0.002 |
Neg logit contributions | |
Here | -0.006 |
chard | -0.006 |
ours | -0.006 |
redd | -0.005 |
right | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +8.57e-03 |
Pos logit contributions | |
friends | +0.002 |
marched | +0.001 |
sisters | +0.001 |
came | +0.001 |
brothers | +0.001 |
Neg logit contributions | |
Here | -0.005 |
chard | -0.005 |
ours | -0.005 |
right | -0.005 |
redd | -0.005 |
Token | You |
Token ID | 921 |
Feature activation | +6.73e-03 |
Pos logit contributions | |
friends | +0.012 |
marched | +0.012 |
, | +0.011 |
brothers | +0.011 |
sisters | +0.011 |
Neg logit contributions | |
chard | -0.015 |
ours | -0.014 |
ited | -0.014 |
redd | -0.014 |
right | -0.014 |
Token | just |
Token ID | 655 |
Feature activation | +4.90e-03 |
Pos logit contributions | |
friends | +0.007 |
marched | +0.007 |
sisters | +0.006 |
, | +0.006 |
brothers | +0.006 |
Neg logit contributions | |
Here | -0.014 |
chard | -0.014 |
ours | -0.014 |
right | -0.013 |
redd | -0.013 |
Token | have |
Token ID | 423 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.005 |
came | +0.004 |
, | +0.004 |
sisters | +0.004 |
Neg logit contributions | |
chard | -0.011 |
Here | -0.011 |
rily | -0.011 |
ours | -0.010 |
aman | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +2.13e-03 |
Pos logit contributions | |
friends | +0.009 |
marched | +0.009 |
sisters | +0.008 |
brothers | +0.007 |
marching | +0.007 |
Neg logit contributions | |
Here | -0.023 |
ours | -0.023 |
chard | -0.023 |
right | -0.022 |
redd | -0.022 |
Token | bru |
Token ID | 18145 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.003 |
sisters | +0.002 |
, | +0.002 |
brothers | +0.002 |
Neg logit contributions | |
Here | -0.004 |
chard | -0.004 |
ours | -0.004 |
redd | -0.004 |
right | -0.004 |
Token | ise |
Token ID | 786 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
friends | +0.089 |
marched | +0.087 |
sisters | +0.081 |
family | +0.078 |
marching | +0.078 |
Neg logit contributions | |
Here | -0.112 |
chard | -0.111 |
ours | -0.108 |
right | -0.106 |
ited | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | +4.06e-03 |
Pos logit contributions | |
friends | +0.023 |
, | +0.020 |
marched | +0.019 |
came | +0.018 |
sisters | +0.017 |
Neg logit contributions | |
Here | -0.068 |
chard | -0.067 |
ours | -0.065 |
redd | -0.064 |
right | -0.063 |
Token | You |
Token ID | 921 |
Feature activation | +8.47e-03 |
Pos logit contributions | |
friends | +0.006 |
marched | +0.006 |
, | +0.006 |
sisters | +0.006 |
brothers | +0.006 |
Neg logit contributions | |
chard | -0.007 |
ours | -0.006 |
Here | -0.006 |
redd | -0.006 |
rily | -0.006 |
Token | can |
Token ID | 460 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
friends | +0.009 |
marched | +0.008 |
sisters | +0.008 |
, | +0.008 |
brothers | +0.008 |
Neg logit contributions | |
Here | -0.018 |
chard | -0.018 |
ours | -0.017 |
right | -0.017 |
redd | -0.017 |
Token | go |
Token ID | 467 |
Feature activation | +8.87e-03 |
Pos logit contributions | |
Here | +0.029 |
chard | +0.029 |
ours | +0.028 |
redd | +0.027 |
right | +0.027 |
Neg logit contributions | |
friends | -0.015 |
marched | -0.014 |
, | -0.013 |
sisters | -0.013 |
came | -0.013 |
Token | behind |
Token ID | 2157 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
friends | +0.012 |
, | +0.011 |
marched | +0.010 |
. | +0.009 |
came | +0.009 |
Neg logit contributions | |
Here | -0.032 |
chard | -0.030 |
redd | -0.029 |
right | -0.029 |
ours | -0.029 |
Token | something |
Token ID | 1223 |
Feature activation | -1.32e-03 |
Pos logit contributions | |
friends | +0.017 |
, | +0.015 |
marched | +0.014 |
. | +0.013 |
sisters | +0.013 |
Neg logit contributions | |
Here | -0.037 |
chard | -0.036 |
redd | -0.035 |
right | -0.035 |
ours | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | +6.42e-03 |
Pos logit contributions | |
Here | +0.003 |
chard | +0.003 |
ours | +0.003 |
redd | +0.003 |
right | +0.003 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.001 |
, | -0.001 |
sisters | -0.001 |
came | -0.001 |
Token | say |
Token ID | 910 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
friends | +0.007 |
marched | +0.006 |
, | +0.006 |
sisters | +0.006 |
family | +0.006 |
Neg logit contributions | |
Here | -0.014 |
chard | -0.014 |
right | -0.013 |
aman | -0.013 |
rily | -0.013 |
Token | ' |
Token ID | 705 |
Feature activation | -1.43e-03 |
Pos logit contributions | |
friends | +0.028 |
marched | +0.027 |
brothers | +0.026 |
sisters | +0.025 |
marching | +0.025 |
Neg logit contributions | |
Here | -0.033 |
ours | -0.031 |
chard | -0.030 |
right | -0.028 |
redd | -0.028 |
Token | v |
Token ID | 85 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
ours | +0.002 |
Here | +0.002 |
rily | +0.002 |
chard | +0.002 |
redd | +0.002 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.002 |
came | -0.002 |
, | -0.002 |
' | -0.002 |
Token | anish |
Token ID | 7115 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
friends | +0.099 |
marched | +0.099 |
marching | +0.095 |
came | +0.091 |
sisters | +0.090 |
Neg logit contributions | |
Here | -0.104 |
right | -0.099 |
rily | -0.098 |
ours | -0.096 |
chard | -0.096 |
Token | !' |
Token ID | 13679 |
Feature activation | -2.79e-03 |
Pos logit contributions | |
friends | +0.021 |
marched | +0.019 |
, | +0.018 |
sisters | +0.018 |
came | +0.018 |
Neg logit contributions | |
Here | -0.028 |
chard | -0.028 |
ours | -0.027 |
redd | -0.026 |
right | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -8.40e-04 |
Pos logit contributions | |
chard | +0.006 |
ours | +0.005 |
Here | +0.005 |
redd | +0.005 |
right | +0.005 |
Neg logit contributions | |
friends | -0.004 |
, | -0.003 |
marched | -0.003 |
. | -0.003 |
sisters | -0.003 |
Token | then |
Token ID | 788 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
chard | +0.002 |
Here | +0.002 |
ours | +0.002 |
redd | +0.002 |
right | +0.002 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
, | -0.001 |
came | -0.001 |
sisters | -0.001 |
Token | come |
Token ID | 1282 |
Feature activation | -1.82e-03 |
Pos logit contributions | |
Here | +0.027 |
chard | +0.027 |
ours | +0.026 |
redd | +0.025 |
right | +0.025 |
Neg logit contributions | |
friends | -0.015 |
marched | -0.014 |
sisters | -0.013 |
brothers | -0.013 |
marching | -0.013 |
Token | can |
Token ID | 460 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.004 |
sisters | +0.004 |
marching | +0.004 |
brothers | +0.004 |
Neg logit contributions | |
Here | -0.007 |
chard | -0.007 |
ours | -0.007 |
right | -0.007 |
redd | -0.006 |
Token | always |
Token ID | 1464 |
Feature activation | -7.95e-03 |
Pos logit contributions | |
Here | +0.024 |
chard | +0.023 |
right | +0.023 |
ours | +0.022 |
aman | +0.022 |
Neg logit contributions | |
marched | -0.015 |
friends | -0.015 |
sisters | -0.015 |
brothers | -0.014 |
helpers | -0.013 |
Token | ask |
Token ID | 1265 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
Here | +0.016 |
ours | +0.015 |
chard | +0.015 |
right | +0.015 |
aman | +0.014 |
Neg logit contributions | |
marched | -0.009 |
friends | -0.008 |
sisters | -0.008 |
brothers | -0.008 |
mo | -0.008 |
Token | for |
Token ID | 329 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
friends | +0.027 |
, | +0.024 |
marched | +0.023 |
sisters | +0.022 |
brothers | +0.022 |
Neg logit contributions | |
Here | -0.043 |
chard | -0.043 |
redd | -0.043 |
ours | -0.042 |
rily | -0.040 |
Token | help |
Token ID | 1037 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
friends | +0.021 |
marched | +0.019 |
sisters | +0.016 |
came | +0.016 |
, | +0.016 |
Neg logit contributions | |
Here | -0.070 |
chard | -0.069 |
ours | -0.069 |
right | -0.066 |
redd | -0.066 |
Token | from |
Token ID | 422 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
friends | +0.022 |
marched | +0.020 |
, | +0.019 |
sisters | +0.018 |
brothers | +0.018 |
Neg logit contributions | |
Here | -0.044 |
chard | -0.044 |
ours | -0.043 |
redd | -0.042 |
right | -0.041 |
Token | God |
Token ID | 1793 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
friends | +0.079 |
marched | +0.067 |
, | +0.066 |
brothers | +0.064 |
sisters | +0.064 |
Neg logit contributions | |
Here | -0.139 |
chard | -0.134 |
redd | -0.133 |
ours | -0.131 |
rily | -0.128 |
Token | .' |
Token ID | 2637 |
Feature activation | -3.35e-03 |
Pos logit contributions | |
friends | +0.041 |
marched | +0.038 |
, | +0.035 |
sisters | +0.035 |
brothers | +0.034 |
Neg logit contributions | |
Here | -0.078 |
chard | -0.077 |
ours | -0.075 |
redd | -0.073 |
right | -0.073 |
Token | So |
Token ID | 1406 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
ours | +0.008 |
chard | +0.007 |
redd | +0.007 |
Here | +0.007 |
rily | +0.007 |
Neg logit contributions | |
friends | -0.003 |
, | -0.003 |
marched | -0.003 |
brothers | -0.003 |
. | -0.003 |
Token | Jack |
Token ID | 3619 |
Feature activation | -6.75e-03 |
Pos logit contributions | |
Here | +0.066 |
chard | +0.065 |
ours | +0.064 |
redd | +0.062 |
right | +0.062 |
Neg logit contributions | |
friends | -0.027 |
marched | -0.024 |
, | -0.022 |
sisters | -0.022 |
brothers | -0.021 |
Token | closed |
Token ID | 4838 |
Feature activation | -2.19e-03 |
Pos logit contributions | |
Here | +0.014 |
chard | +0.014 |
right | +0.014 |
rily | +0.013 |
aman | +0.013 |
Neg logit contributions | |
friends | -0.006 |
marching | -0.006 |
marched | -0.006 |
sisters | -0.005 |
brothers | -0.005 |
Token | things |
Token ID | 1243 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
marched | +0.020 |
friends | +0.020 |
sisters | +0.018 |
brothers | +0.018 |
came | +0.018 |
Neg logit contributions | |
Here | -0.038 |
ours | -0.038 |
chard | -0.038 |
right | -0.035 |
redd | -0.035 |
Token | are |
Token ID | 389 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
friends | +0.017 |
marched | +0.015 |
sisters | +0.015 |
brothers | +0.014 |
, | +0.014 |
Neg logit contributions | |
Here | -0.026 |
chard | -0.026 |
ours | -0.025 |
right | -0.024 |
redd | -0.024 |
Token | not |
Token ID | 407 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
friends | +0.022 |
marched | +0.020 |
sisters | +0.019 |
brothers | +0.019 |
came | +0.019 |
Neg logit contributions | |
Here | -0.034 |
chard | -0.034 |
ours | -0.033 |
redd | -0.032 |
right | -0.032 |
Token | what |
Token ID | 644 |
Feature activation | +7.90e-03 |
Pos logit contributions | |
friends | +0.041 |
marched | +0.037 |
, | +0.036 |
sisters | +0.035 |
came | +0.035 |
Neg logit contributions | |
Here | -0.057 |
chard | -0.056 |
ours | -0.053 |
redd | -0.052 |
right | -0.052 |
Token | they |
Token ID | 484 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
friends | +0.011 |
marched | +0.010 |
sisters | +0.009 |
brothers | +0.009 |
came | +0.009 |
Neg logit contributions | |
Here | -0.015 |
chard | -0.014 |
ours | -0.014 |
right | -0.013 |
redd | -0.013 |
Token | seem |
Token ID | 1283 |
Feature activation | +6.53e-02 |
Pos logit contributions | |
friends | +0.013 |
marched | +0.012 |
, | +0.011 |
sisters | +0.011 |
came | +0.011 |
Neg logit contributions | |
Here | -0.021 |
chard | -0.020 |
ours | -0.020 |
redd | -0.019 |
right | -0.019 |
Token | ," |
Token ID | 553 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
friends | +0.055 |
marched | +0.053 |
sisters | +0.047 |
brothers | +0.045 |
came | +0.043 |
Neg logit contributions | |
ours | -0.151 |
Here | -0.149 |
chard | -0.148 |
right | -0.142 |
redd | -0.142 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.42e-04 |
Pos logit contributions | |
friends | +0.014 |
, | +0.012 |
marched | +0.012 |
family | +0.012 |
came | +0.011 |
Neg logit contributions | |
ours | -0.028 |
Here | -0.028 |
chard | -0.027 |
redd | -0.027 |
right | -0.027 |
Token | said |
Token ID | 531 |
Feature activation | +1.69e-03 |
Pos logit contributions | |
friends | +0.000 |
marched | +0.000 |
sisters | +0.000 |
, | +0.000 |
brothers | +0.000 |
Neg logit contributions | |
Here | -0.001 |
chard | -0.001 |
ours | -0.001 |
right | -0.001 |
redd | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -2.27e-03 |
Pos logit contributions | |
friends | +0.001 |
marched | +0.001 |
brothers | +0.001 |
sisters | +0.001 |
marching | +0.001 |
Neg logit contributions | |
Here | -0.005 |
chard | -0.005 |
right | -0.004 |
ours | -0.004 |
rily | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -3.33e-03 |
Pos logit contributions | |
Here | +0.005 |
chard | +0.005 |
ours | +0.005 |
right | +0.005 |
aman | +0.005 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.002 |
sisters | -0.002 |
brothers | -0.002 |
marching | -0.002 |
Token | together |
Token ID | 1978 |
Feature activation | +8.16e-03 |
Pos logit contributions | |
ires | +0.008 |
Here | +0.008 |
right | +0.008 |
like | +0.008 |
ours | +0.008 |
Neg logit contributions | |
fore | -0.005 |
Pig | -0.005 |
parent | -0.004 |
sisters | -0.004 |
parents | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e-03 |
Pos logit contributions | |
sisters | +0.008 |
brothers | +0.008 |
helpers | +0.007 |
marched | +0.007 |
rac | +0.007 |
Neg logit contributions | |
chard | -0.015 |
right | -0.014 |
ours | -0.014 |
curiously | -0.014 |
Here | -0.014 |
Token | They |
Token ID | 1119 |
Feature activation | -3.22e-03 |
Pos logit contributions | |
friends | +0.002 |
marched | +0.002 |
, | +0.002 |
sisters | +0.002 |
came | +0.002 |
Neg logit contributions | |
chard | -0.003 |
ours | -0.003 |
Here | -0.002 |
right | -0.002 |
redd | -0.002 |
Token | played |
Token ID | 2826 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
chard | +0.008 |
Here | +0.007 |
ours | +0.007 |
redd | +0.007 |
nam | +0.007 |
Neg logit contributions | |
friends | -0.003 |
brothers | -0.002 |
sisters | -0.002 |
helpers | -0.002 |
marched | -0.002 |
Token | hop |
Token ID | 1725 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
marched | +0.011 |
sisters | +0.011 |
brothers | +0.011 |
friends | +0.011 |
family | +0.011 |
Neg logit contributions | |
Here | -0.022 |
ours | -0.021 |
chard | -0.021 |
redd | -0.020 |
right | -0.020 |
Token | sc |
Token ID | 1416 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
Here | +0.032 |
chard | +0.032 |
ours | +0.031 |
right | +0.031 |
redd | +0.030 |
Neg logit contributions | |
friends | -0.016 |
marched | -0.015 |
sisters | -0.014 |
brothers | -0.014 |
family | -0.014 |
Token | ot |
Token ID | 313 |
Feature activation | +5.22e-03 |
Pos logit contributions | |
chard | +0.151 |
Here | +0.149 |
redd | +0.140 |
ours | +0.140 |
aman | +0.136 |
Neg logit contributions | |
friends | -0.099 |
marched | -0.090 |
, | -0.088 |
sisters | -0.082 |
came | -0.081 |
Token | ch |
Token ID | 354 |
Feature activation | -5.58e-03 |
Pos logit contributions | |
friends | +0.009 |
brothers | +0.009 |
sisters | +0.009 |
family | +0.009 |
helpers | +0.008 |
Neg logit contributions | |
Here | -0.006 |
right | -0.006 |
ours | -0.006 |
finder | -0.006 |
fy | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
Here | +0.010 |
right | +0.010 |
ours | +0.010 |
chard | +0.009 |
rily | +0.009 |
Neg logit contributions | |
friends | -0.006 |
marched | -0.006 |
sisters | -0.006 |
brothers | -0.006 |
family | -0.006 |
Token | picked |
Token ID | 6497 |
Feature activation | +7.76e-03 |
Pos logit contributions | |
friends | +0.005 |
brothers | +0.005 |
sisters | +0.004 |
helpers | +0.004 |
marched | +0.004 |
Neg logit contributions | |
chard | -0.013 |
Here | -0.013 |
redd | -0.012 |
ours | -0.012 |
nam | -0.012 |
Token | more |
Token ID | 517 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
friends | +0.011 |
marched | +0.010 |
, | +0.009 |
sisters | +0.009 |
came | +0.009 |
Neg logit contributions | |
Here | -0.015 |
chard | -0.015 |
ours | -0.014 |
right | -0.014 |
redd | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e-03 |
Pos logit contributions | |
Here | +0.013 |
chard | +0.013 |
right | +0.013 |
ours | +0.013 |
aman | +0.012 |
Neg logit contributions | |
friends | -0.004 |
marched | -0.003 |
sisters | -0.003 |
brothers | -0.003 |
marching | -0.003 |
Token | He |
Token ID | 679 |
Feature activation | +1.79e-03 |
Pos logit contributions | |
friends | +0.001 |
, | +0.001 |
marched | +0.001 |
. | +0.001 |
came | +0.001 |
Neg logit contributions | |
chard | -0.002 |
ours | -0.002 |
Here | -0.002 |
redd | -0.002 |
rily | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +1.05e-03 |
Pos logit contributions | |
friends | +0.002 |
marched | +0.002 |
sisters | +0.001 |
brothers | +0.001 |
, | +0.001 |
Neg logit contributions | |
Here | -0.004 |
chard | -0.004 |
ours | -0.004 |
right | -0.004 |
redd | -0.004 |
Token | wearing |
Token ID | 5762 |
Feature activation | +4.73e-03 |
Pos logit contributions | |
friends | +0.001 |
marched | +0.001 |
sisters | +0.001 |
, | +0.001 |
came | +0.001 |
Neg logit contributions | |
chard | -0.002 |
Here | -0.002 |
ours | -0.002 |
right | -0.002 |
redd | -0.002 |
Token | his |
Token ID | 465 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.005 |
sisters | +0.005 |
came | +0.005 |
brothers | +0.005 |
Neg logit contributions | |
Here | -0.010 |
chard | -0.010 |
ours | -0.009 |
redd | -0.009 |
right | -0.009 |
Token | brand |
Token ID | 4508 |
Feature activation | -7.52e-02 |
Pos logit contributions | |
Here | +0.020 |
chard | +0.020 |
ours | +0.019 |
redd | +0.019 |
right | +0.018 |
Neg logit contributions | |
friends | -0.018 |
marched | -0.018 |
sisters | -0.017 |
came | -0.016 |
, | -0.016 |
Token | new |
Token ID | 649 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
chard | +0.164 |
Here | +0.159 |
ours | +0.158 |
redd | +0.149 |
right | +0.149 |
Neg logit contributions | |
friends | -0.092 |
, | -0.080 |
marched | -0.074 |
. | -0.072 |
family | -0.070 |
Token | icy |
Token ID | 30284 |
Feature activation | +5.06e-03 |
Pos logit contributions | |
Here | +0.030 |
ours | +0.029 |
chard | +0.029 |
redd | +0.028 |
right | +0.028 |
Neg logit contributions | |
marched | -0.020 |
friends | -0.019 |
brothers | -0.018 |
came | -0.018 |
sisters | -0.018 |
Token | blue |
Token ID | 4171 |
Feature activation | +9.55e-04 |
Pos logit contributions | |
friends | +0.006 |
marched | +0.006 |
sisters | +0.005 |
brothers | +0.005 |
marching | +0.005 |
Neg logit contributions | |
Here | -0.009 |
right | -0.009 |
shirt | -0.009 |
ours | -0.009 |
chard | -0.009 |
Token | jacket |
Token ID | 15224 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
friends | +0.001 |
marched | +0.001 |
sisters | +0.001 |
brothers | +0.001 |
marching | +0.001 |
Neg logit contributions | |
Here | -0.002 |
chard | -0.002 |
ours | -0.002 |
right | -0.002 |
shirt | -0.002 |
Token | as |
Token ID | 355 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
Here | +0.032 |
chard | +0.031 |
ours | +0.031 |
redd | +0.030 |
right | +0.030 |
Neg logit contributions | |
friends | -0.006 |
marched | -0.005 |
, | -0.004 |
came | -0.004 |
sisters | -0.004 |
Token | day |
Token ID | 1110 |
Feature activation | -1.98e-03 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.003 |
, | +0.002 |
family | +0.002 |
brothers | +0.002 |
Neg logit contributions | |
Here | -0.006 |
chard | -0.006 |
ours | -0.006 |
rily | -0.006 |
redd | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
Here | +0.005 |
chard | +0.005 |
ours | +0.005 |
right | +0.005 |
aman | +0.005 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
sisters | -0.001 |
brothers | -0.001 |
marching | -0.000 |
Token | they |
Token ID | 484 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
friends | +0.022 |
, | +0.020 |
marched | +0.018 |
came | +0.017 |
family | +0.017 |
Neg logit contributions | |
Here | -0.053 |
chard | -0.053 |
rily | -0.052 |
redd | -0.051 |
ours | -0.050 |
Token | play |
Token ID | 711 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
friends | +0.021 |
sisters | +0.018 |
marched | +0.018 |
brothers | +0.018 |
helpers | +0.018 |
Neg logit contributions | |
chard | -0.027 |
Here | -0.026 |
ours | -0.026 |
redd | -0.024 |
right | -0.023 |
Token | hop |
Token ID | 1725 |
Feature activation | -8.37e-03 |
Pos logit contributions | |
friends | +0.021 |
marched | +0.021 |
sisters | +0.019 |
marching | +0.019 |
brothers | +0.019 |
Neg logit contributions | |
Here | -0.036 |
chard | -0.035 |
ours | -0.034 |
right | -0.033 |
redd | -0.032 |
Token | sc |
Token ID | 1416 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
Here | +0.018 |
chard | +0.018 |
ours | +0.018 |
right | +0.017 |
redd | +0.017 |
Neg logit contributions | |
friends | -0.009 |
marched | -0.008 |
sisters | -0.007 |
, | -0.007 |
brothers | -0.007 |
Token | ot |
Token ID | 313 |
Feature activation | +7.46e-03 |
Pos logit contributions | |
chard | +0.139 |
Here | +0.138 |
ours | +0.131 |
redd | +0.130 |
aman | +0.127 |
Neg logit contributions | |
friends | -0.096 |
marched | -0.088 |
, | -0.085 |
sisters | -0.081 |
brothers | -0.080 |
Token | ch |
Token ID | 354 |
Feature activation | -1.91e-03 |
Pos logit contributions | |
friends | +0.011 |
sisters | +0.011 |
family | +0.010 |
brothers | +0.010 |
marched | +0.010 |
Neg logit contributions | |
Here | -0.012 |
right | -0.011 |
ours | -0.011 |
chard | -0.010 |
finder | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +3.75e-03 |
Pos logit contributions | |
Here | +0.004 |
right | +0.004 |
ours | +0.004 |
chard | +0.004 |
rily | +0.004 |
Neg logit contributions | |
marched | -0.001 |
friends | -0.001 |
sisters | -0.001 |
family | -0.001 |
helpers | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | +3.33e-03 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.004 |
, | +0.004 |
came | +0.003 |
cl | +0.003 |
Neg logit contributions | |
chard | -0.008 |
ours | -0.008 |
Here | -0.008 |
aman | -0.008 |
rily | -0.008 |
Token | draw |
Token ID | 3197 |
Feature activation | -7.83e-04 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.003 |
sisters | +0.003 |
brothers | +0.003 |
helpers | +0.003 |
Neg logit contributions | |
chard | -0.007 |
Here | -0.007 |
ours | -0.006 |
redd | -0.006 |
right | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | +1.50e-03 |
Pos logit contributions | |
friends | +0.008 |
marched | +0.007 |
, | +0.007 |
sisters | +0.007 |
came | +0.007 |
Neg logit contributions | |
Here | -0.010 |
chard | -0.010 |
ours | -0.010 |
redd | -0.010 |
right | -0.009 |
Token | started |
Token ID | 2067 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
friends | +0.001 |
brothers | +0.001 |
sisters | +0.001 |
helpers | +0.001 |
marching | +0.001 |
Neg logit contributions | |
chard | -0.003 |
Here | -0.003 |
redd | -0.003 |
right | -0.003 |
ours | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -3.01e-03 |
Pos logit contributions | |
brothers | +0.013 |
friends | +0.012 |
sisters | +0.012 |
helpers | +0.011 |
siblings | +0.011 |
Neg logit contributions | |
right | -0.019 |
chard | -0.019 |
Here | -0.018 |
like | -0.018 |
curiously | -0.018 |
Token | play |
Token ID | 711 |
Feature activation | +8.72e-03 |
Pos logit contributions | |
chard | +0.005 |
Here | +0.005 |
ours | +0.005 |
right | +0.005 |
redd | +0.005 |
Neg logit contributions | |
friends | -0.004 |
brothers | -0.004 |
marched | -0.004 |
sisters | -0.003 |
helpers | -0.003 |
Token | hop |
Token ID | 1725 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
marched | +0.010 |
lee | +0.010 |
sisters | +0.010 |
brothers | +0.009 |
marching | +0.009 |
Neg logit contributions | |
Here | -0.015 |
chard | -0.015 |
ours | -0.014 |
curiously | -0.014 |
right | -0.014 |
Token | sc |
Token ID | 1416 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
Here | +0.021 |
chard | +0.021 |
ours | +0.021 |
right | +0.020 |
redd | +0.020 |
Neg logit contributions | |
friends | -0.015 |
sisters | -0.014 |
marched | -0.014 |
brothers | -0.014 |
family | -0.013 |
Token | ot |
Token ID | 313 |
Feature activation | +6.42e-03 |
Pos logit contributions | |
chard | +0.140 |
Here | +0.138 |
redd | +0.130 |
ours | +0.130 |
aman | +0.126 |
Neg logit contributions | |
friends | -0.091 |
marched | -0.083 |
, | -0.082 |
sisters | -0.074 |
came | -0.074 |
Token | ch |
Token ID | 354 |
Feature activation | -2.35e-03 |
Pos logit contributions | |
friends | +0.012 |
sisters | +0.011 |
family | +0.011 |
brothers | +0.011 |
helpers | +0.011 |
Neg logit contributions | |
right | -0.008 |
Here | -0.007 |
like | -0.007 |
ours | -0.007 |
fy | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +8.61e-03 |
Pos logit contributions | |
right | +0.005 |
Here | +0.005 |
ours | +0.005 |
rily | +0.005 |
like | +0.005 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.002 |
sisters | -0.002 |
family | -0.002 |
helpers | -0.002 |
Token | had |
Token ID | 550 |
Feature activation | +1.63e-03 |
Pos logit contributions | |
friends | +0.009 |
brothers | +0.008 |
sisters | +0.008 |
marched | +0.008 |
helpers | +0.008 |
Neg logit contributions | |
chard | -0.018 |
Here | -0.017 |
ours | -0.017 |
redd | -0.017 |
right | -0.016 |
Token | lots |
Token ID | 6041 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
friends | +0.002 |
marched | +0.002 |
sisters | +0.002 |
brothers | +0.002 |
marching | +0.002 |
Neg logit contributions | |
ours | -0.003 |
Here | -0.003 |
redd | -0.003 |
chard | -0.003 |
right | -0.003 |
Token | would |
Token ID | 561 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
chard | +0.000 |
Here | +0.000 |
redd | +0.000 |
right | +0.000 |
ours | +0.000 |
Neg logit contributions | |
friends | -0.000 |
sisters | -0.000 |
helpers | -0.000 |
marched | -0.000 |
brothers | -0.000 |
Token | play |
Token ID | 711 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
Here | +0.032 |
chard | +0.032 |
ours | +0.031 |
redd | +0.030 |
right | +0.030 |
Neg logit contributions | |
friends | -0.017 |
marched | -0.016 |
sisters | -0.014 |
, | -0.014 |
brothers | -0.014 |
Token | tag |
Token ID | 7621 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
friends | +0.015 |
marched | +0.014 |
sisters | +0.014 |
brothers | +0.013 |
family | +0.013 |
Neg logit contributions | |
Here | -0.024 |
chard | -0.024 |
ours | -0.023 |
right | -0.022 |
redd | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -2.09e-03 |
Pos logit contributions | |
Here | +0.037 |
chard | +0.036 |
ours | +0.036 |
redd | +0.035 |
aman | +0.035 |
Neg logit contributions | |
friends | -0.007 |
, | -0.006 |
marched | -0.006 |
came | -0.005 |
. | -0.004 |
Token | hop |
Token ID | 1725 |
Feature activation | -6.87e-03 |
Pos logit contributions | |
Here | +0.005 |
chard | +0.005 |
ours | +0.005 |
right | +0.005 |
rily | +0.005 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.002 |
, | -0.002 |
sisters | -0.002 |
came | -0.002 |
Token | sc |
Token ID | 1416 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
Here | +0.015 |
chard | +0.014 |
ours | +0.014 |
right | +0.014 |
redd | +0.013 |
Neg logit contributions | |
friends | -0.008 |
marched | -0.007 |
sisters | -0.007 |
brothers | -0.006 |
came | -0.006 |
Token | ot |
Token ID | 313 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
chard | +0.140 |
Here | +0.136 |
redd | +0.129 |
ours | +0.128 |
aman | +0.127 |
Neg logit contributions | |
friends | -0.089 |
marched | -0.081 |
, | -0.080 |
sisters | -0.072 |
brothers | -0.072 |
Token | ch |
Token ID | 354 |
Feature activation | +4.87e-04 |
Pos logit contributions | |
friends | +0.033 |
sisters | +0.031 |
family | +0.031 |
brothers | +0.030 |
helpers | +0.030 |
Neg logit contributions | |
Here | -0.023 |
right | -0.021 |
ours | -0.020 |
fy | -0.020 |
shirt | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -4.65e-03 |
Pos logit contributions | |
friends | +0.000 |
family | +0.000 |
marched | +0.000 |
sisters | +0.000 |
helpers | +0.000 |
Neg logit contributions | |
Here | -0.001 |
right | -0.001 |
ours | -0.001 |
rily | -0.001 |
like | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +1.97e-04 |
Pos logit contributions | |
Here | +0.011 |
chard | +0.011 |
ours | +0.011 |
redd | +0.011 |
right | +0.011 |
Neg logit contributions | |
friends | -0.003 |
marched | -0.003 |
sisters | -0.003 |
brothers | -0.003 |
family | -0.003 |
Token | many |
Token ID | 867 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
friends | +0.000 |
marched | +0.000 |
, | +0.000 |
sisters | +0.000 |
came | +0.000 |
Neg logit contributions | |
Here | -0.000 |
chard | -0.000 |
ours | -0.000 |
redd | -0.000 |
right | -0.000 |
Token | When |
Token ID | 1649 |
Feature activation | +8.34e-03 |
Pos logit contributions | |
chard | +0.004 |
ours | +0.004 |
redd | +0.004 |
right | +0.004 |
Here | +0.004 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.002 |
, | -0.002 |
came | -0.002 |
brothers | -0.002 |
Token | Daisy |
Token ID | 40355 |
Feature activation | -6.29e-03 |
Pos logit contributions | |
friends | +0.010 |
marched | +0.009 |
sisters | +0.009 |
brothers | +0.009 |
, | +0.008 |
Neg logit contributions | |
Here | -0.017 |
chard | -0.016 |
ours | -0.016 |
right | -0.015 |
redd | -0.015 |
Token | put |
Token ID | 1234 |
Feature activation | +1.96e-03 |
Pos logit contributions | |
Here | +0.015 |
chard | +0.014 |
ours | +0.014 |
right | +0.014 |
redd | +0.014 |
Neg logit contributions | |
friends | -0.006 |
marched | -0.005 |
sisters | -0.005 |
brothers | -0.004 |
marching | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -1.61e-03 |
Pos logit contributions | |
friends | +0.001 |
, | +0.001 |
marched | +0.001 |
came | +0.001 |
brothers | +0.001 |
Neg logit contributions | |
Here | -0.005 |
chard | -0.005 |
ours | -0.005 |
right | -0.005 |
redd | -0.005 |
Token | magn |
Token ID | 7842 |
Feature activation | +4.91e-03 |
Pos logit contributions | |
Here | +0.003 |
chard | +0.003 |
ours | +0.003 |
rily | +0.003 |
aman | +0.003 |
Neg logit contributions | |
friends | -0.002 |
, | -0.002 |
family | -0.002 |
sisters | -0.002 |
brothers | -0.002 |
Token | ifying |
Token ID | 4035 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
, | +0.011 |
on | +0.011 |
marched | +0.010 |
friends | +0.010 |
came | +0.010 |
Neg logit contributions | |
Here | -0.005 |
chard | -0.005 |
ours | -0.005 |
aman | -0.004 |
redd | -0.004 |
Token | glass |
Token ID | 5405 |
Feature activation | -1.90e-03 |
Pos logit contributions | |
Here | +0.126 |
chard | +0.123 |
ours | +0.119 |
right | +0.117 |
nam | +0.116 |
Neg logit contributions | |
, | -0.093 |
friends | -0.089 |
. | -0.082 |
p | -0.080 |
came | -0.078 |
Token | down |
Token ID | 866 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
Here | +0.005 |
chard | +0.005 |
ours | +0.005 |
right | +0.005 |
redd | +0.005 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
marching | -0.001 |
sisters | -0.001 |
brothers | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -2.80e-03 |
Pos logit contributions | |
Here | +0.074 |
chard | +0.072 |
ours | +0.071 |
redd | +0.070 |
right | +0.069 |
Neg logit contributions | |
friends | -0.012 |
, | -0.009 |
marched | -0.008 |
came | -0.007 |
sisters | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -5.35e-03 |
Pos logit contributions | |
Here | +0.006 |
chard | +0.006 |
ours | +0.005 |
right | +0.005 |
redd | +0.005 |
Neg logit contributions | |
friends | -0.003 |
marched | -0.003 |
, | -0.003 |
came | -0.003 |
sisters | -0.003 |
Token | cater |
Token ID | 20825 |
Feature activation | +3.03e-03 |
Pos logit contributions | |
Here | +0.011 |
ours | +0.011 |
chard | +0.011 |
rily | +0.010 |
right | +0.010 |
Neg logit contributions | |
friends | -0.007 |
sisters | -0.006 |
family | -0.006 |
, | -0.006 |
marched | -0.006 |
Token | and |
Token ID | 392 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
ours | +0.006 |
Here | +0.006 |
chard | +0.006 |
aman | +0.006 |
rily | +0.006 |
Neg logit contributions | |
friends | -0.005 |
marched | -0.005 |
came | -0.005 |
, | -0.004 |
. | -0.004 |
Token | - |
Token ID | 12 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
Here | +0.044 |
chard | +0.043 |
ours | +0.043 |
right | +0.042 |
redd | +0.041 |
Neg logit contributions | |
friends | -0.018 |
marched | -0.017 |
sisters | -0.016 |
brothers | -0.016 |
came | -0.015 |
Token | seek |
Token ID | 36163 |
Feature activation | -1.34e-03 |
Pos logit contributions | |
ours | +0.033 |
Here | +0.033 |
chard | +0.032 |
rily | +0.031 |
redd | +0.031 |
Neg logit contributions | |
friends | -0.018 |
marched | -0.017 |
, | -0.017 |
came | -0.016 |
. | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +5.64e-03 |
Pos logit contributions | |
chard | +0.003 |
right | +0.003 |
Here | +0.003 |
ours | +0.003 |
rily | +0.003 |
Neg logit contributions | |
marched | -0.001 |
friends | -0.001 |
sisters | -0.001 |
brothers | -0.001 |
marching | -0.001 |
Token | hop |
Token ID | 1725 |
Feature activation | -7.83e-03 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.004 |
brothers | +0.004 |
sisters | +0.004 |
helpers | +0.004 |
Neg logit contributions | |
chard | -0.013 |
Here | -0.012 |
ours | -0.012 |
redd | -0.012 |
nam | -0.012 |
Token | sc |
Token ID | 1416 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
Here | +0.014 |
chard | +0.014 |
right | +0.014 |
ours | +0.014 |
rily | +0.014 |
Neg logit contributions | |
friends | -0.009 |
sisters | -0.009 |
brothers | -0.009 |
family | -0.008 |
marched | -0.008 |
Token | ot |
Token ID | 313 |
Feature activation | +8.34e-03 |
Pos logit contributions | |
chard | +0.140 |
Here | +0.135 |
redd | +0.128 |
ours | +0.126 |
aman | +0.125 |
Neg logit contributions | |
friends | -0.088 |
marched | -0.079 |
, | -0.079 |
sisters | -0.072 |
brothers | -0.071 |
Token | ch |
Token ID | 354 |
Feature activation | +2.58e-03 |
Pos logit contributions | |
friends | +0.014 |
brothers | +0.014 |
sisters | +0.014 |
family | +0.014 |
helpers | +0.013 |
Neg logit contributions | |
Here | -0.011 |
right | -0.010 |
fy | -0.010 |
like | -0.010 |
finder | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +4.02e-03 |
Pos logit contributions | |
marched | +0.002 |
friends | +0.002 |
family | +0.002 |
sisters | +0.002 |
brothers | +0.002 |
Neg logit contributions | |
Here | -0.005 |
right | -0.005 |
ours | -0.005 |
rily | -0.005 |
chard | -0.005 |
Token | Then |
Token ID | 3244 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
friends | +0.007 |
marched | +0.006 |
, | +0.006 |
brothers | +0.006 |
came | +0.006 |
Neg logit contributions | |
chard | -0.007 |
ours | -0.006 |
Here | -0.006 |
right | -0.006 |
aman | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
Here | +0.032 |
chard | +0.031 |
curiously | +0.031 |
ours | +0.031 |
nam | +0.031 |
Neg logit contributions | |
helpers | -0.010 |
sisters | -0.010 |
mo | -0.009 |
brothers | -0.008 |
az | -0.008 |
Token | She |
Token ID | 1375 |
Feature activation | +5.69e-03 |
Pos logit contributions | |
friends | +0.007 |
, | +0.007 |
marched | +0.007 |
. | +0.006 |
came | +0.006 |
Neg logit contributions | |
chard | -0.009 |
ours | -0.009 |
redd | -0.009 |
Here | -0.009 |
ited | -0.009 |
Token | played |
Token ID | 2826 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.005 |
sisters | +0.005 |
brothers | +0.005 |
, | +0.004 |
Neg logit contributions | |
Here | -0.012 |
chard | -0.012 |
ours | -0.012 |
redd | -0.012 |
right | -0.012 |
Token | tag |
Token ID | 7621 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
friends | +0.013 |
marched | +0.012 |
brothers | +0.012 |
sisters | +0.012 |
family | +0.011 |
Neg logit contributions | |
Here | -0.026 |
chard | -0.025 |
ours | -0.024 |
rily | -0.024 |
redd | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +5.24e-03 |
Pos logit contributions | |
Here | +0.053 |
chard | +0.052 |
ours | +0.051 |
redd | +0.050 |
right | +0.049 |
Neg logit contributions | |
friends | -0.011 |
, | -0.009 |
marched | -0.008 |
came | -0.007 |
sisters | -0.006 |
Token | hop |
Token ID | 1725 |
Feature activation | -8.51e-03 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.004 |
sisters | +0.004 |
, | +0.004 |
brothers | +0.004 |
Neg logit contributions | |
Here | -0.012 |
chard | -0.012 |
ours | -0.012 |
redd | -0.011 |
right | -0.011 |
Token | sc |
Token ID | 1416 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
Here | +0.019 |
chard | +0.018 |
ours | +0.018 |
right | +0.018 |
redd | +0.017 |
Neg logit contributions | |
friends | -0.008 |
marched | -0.008 |
sisters | -0.007 |
brothers | -0.007 |
family | -0.007 |
Token | ot |
Token ID | 313 |
Feature activation | +7.84e-03 |
Pos logit contributions | |
chard | +0.149 |
Here | +0.141 |
redd | +0.135 |
ours | +0.132 |
aman | +0.131 |
Neg logit contributions | |
friends | -0.081 |
, | -0.073 |
marched | -0.071 |
. | -0.064 |
sisters | -0.064 |
Token | ch |
Token ID | 354 |
Feature activation | +2.18e-03 |
Pos logit contributions | |
friends | +0.013 |
sisters | +0.012 |
brothers | +0.012 |
marched | +0.012 |
family | +0.011 |
Neg logit contributions | |
Here | -0.012 |
right | -0.011 |
chard | -0.011 |
ours | -0.011 |
redd | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +6.48e-03 |
Pos logit contributions | |
friends | +0.002 |
marched | +0.002 |
sisters | +0.002 |
family | +0.002 |
brothers | +0.002 |
Neg logit contributions | |
Here | -0.005 |
right | -0.004 |
ours | -0.004 |
chard | -0.004 |
rily | -0.004 |
Token | pretended |
Token ID | 36766 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
friends | +0.006 |
marched | +0.006 |
sisters | +0.005 |
brothers | +0.005 |
, | +0.005 |
Neg logit contributions | |
Here | -0.014 |
chard | -0.014 |
ours | -0.014 |
redd | -0.013 |
right | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -9.25e-03 |
Pos logit contributions | |
Here | +0.032 |
chard | +0.032 |
ours | +0.031 |
right | +0.030 |
redd | +0.030 |
Neg logit contributions | |
friends | -0.017 |
marched | -0.016 |
brothers | -0.015 |
sisters | -0.015 |
family | -0.014 |
Token | also |
Token ID | 635 |
Feature activation | +9.97e-03 |
Pos logit contributions | |
marched | +0.001 |
marching | +0.001 |
friends | +0.001 |
came | +0.001 |
, | +0.001 |
Neg logit contributions | |
chard | -0.007 |
Here | -0.007 |
redd | -0.007 |
ours | -0.007 |
ited | -0.007 |
Token | played |
Token ID | 2826 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
friends | +0.009 |
brothers | +0.008 |
marched | +0.008 |
marching | +0.008 |
sisters | +0.007 |
Neg logit contributions | |
Here | -0.021 |
chard | -0.021 |
redd | -0.021 |
ours | -0.020 |
right | -0.020 |
Token | tag |
Token ID | 7621 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
marched | +0.016 |
marching | +0.015 |
brothers | +0.015 |
friends | +0.014 |
sisters | +0.014 |
Neg logit contributions | |
Here | -0.032 |
ours | -0.031 |
chard | -0.031 |
rily | -0.031 |
redd | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +1.81e-03 |
Pos logit contributions | |
Here | +0.049 |
chard | +0.048 |
ours | +0.048 |
redd | +0.046 |
right | +0.046 |
Neg logit contributions | |
friends | -0.013 |
marched | -0.011 |
, | -0.010 |
sisters | -0.010 |
came | -0.010 |
Token | hop |
Token ID | 1725 |
Feature activation | -9.14e-03 |
Pos logit contributions | |
friends | +0.001 |
marched | +0.001 |
sisters | +0.001 |
, | +0.001 |
brothers | +0.001 |
Neg logit contributions | |
Here | -0.004 |
chard | -0.004 |
ours | -0.004 |
redd | -0.004 |
right | -0.004 |
Token | sc |
Token ID | 1416 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
Here | +0.017 |
chard | +0.017 |
ours | +0.017 |
rily | +0.017 |
right | +0.017 |
Neg logit contributions | |
friends | -0.011 |
brothers | -0.010 |
sisters | -0.010 |
marched | -0.010 |
family | -0.010 |
Token | ot |
Token ID | 313 |
Feature activation | +8.38e-03 |
Pos logit contributions | |
chard | +0.147 |
Here | +0.137 |
redd | +0.132 |
aman | +0.129 |
ited | +0.126 |
Neg logit contributions | |
friends | -0.083 |
, | -0.074 |
marched | -0.072 |
. | -0.065 |
sisters | -0.064 |
Token | ch |
Token ID | 354 |
Feature activation | +1.18e-03 |
Pos logit contributions | |
friends | +0.013 |
brothers | +0.012 |
sisters | +0.012 |
marched | +0.012 |
family | +0.012 |
Neg logit contributions | |
Here | -0.013 |
right | -0.012 |
chard | -0.012 |
ours | -0.012 |
redd | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +2.94e-03 |
Pos logit contributions | |
marched | +0.001 |
friends | +0.001 |
brothers | +0.001 |
sisters | +0.001 |
family | +0.001 |
Neg logit contributions | |
right | -0.002 |
Here | -0.002 |
ours | -0.002 |
rily | -0.002 |
chard | -0.002 |
Token | They |
Token ID | 1119 |
Feature activation | -1.12e-03 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.003 |
, | +0.003 |
brothers | +0.003 |
sisters | +0.003 |
Neg logit contributions | |
chard | -0.006 |
ours | -0.006 |
Here | -0.006 |
redd | -0.006 |
rily | -0.006 |
Token | laughed |
Token ID | 13818 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
chard | +0.003 |
Here | +0.003 |
ours | +0.002 |
redd | +0.002 |
right | +0.002 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
brothers | -0.001 |
sisters | -0.001 |
, | -0.001 |
Token | love |
Token ID | 1842 |
Feature activation | -9.76e-05 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.002 |
, | +0.002 |
sisters | +0.002 |
brothers | +0.002 |
Neg logit contributions | |
Here | -0.005 |
chard | -0.005 |
ours | -0.005 |
right | -0.004 |
redd | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -4.72e-04 |
Pos logit contributions | |
Here | +0.000 |
ours | +0.000 |
chard | +0.000 |
right | +0.000 |
redd | +0.000 |
Neg logit contributions | |
marched | -0.000 |
friends | -0.000 |
sisters | -0.000 |
brothers | -0.000 |
marching | -0.000 |
Token | They |
Token ID | 1119 |
Feature activation | +1.14e-03 |
Pos logit contributions | |
chard | +0.001 |
ours | +0.001 |
Here | +0.001 |
redd | +0.001 |
right | +0.001 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
, | -0.001 |
brothers | -0.001 |
sisters | -0.001 |
Token | played |
Token ID | 2826 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
friends | +0.001 |
sisters | +0.001 |
brothers | +0.001 |
marched | +0.001 |
helpers | +0.001 |
Neg logit contributions | |
chard | -0.002 |
Here | -0.002 |
ours | -0.002 |
redd | -0.002 |
right | -0.002 |
Token | hop |
Token ID | 1725 |
Feature activation | -8.54e-03 |
Pos logit contributions | |
sisters | +0.016 |
friends | +0.016 |
marched | +0.016 |
brothers | +0.016 |
family | +0.015 |
Neg logit contributions | |
Here | -0.029 |
ours | -0.028 |
chard | -0.028 |
right | -0.026 |
rily | -0.026 |
Token | sc |
Token ID | 1416 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
Here | +0.018 |
chard | +0.018 |
ours | +0.018 |
right | +0.017 |
redd | +0.017 |
Neg logit contributions | |
friends | -0.009 |
marched | -0.008 |
sisters | -0.008 |
brothers | -0.008 |
family | -0.007 |
Token | ot |
Token ID | 313 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
chard | +0.139 |
Here | +0.133 |
redd | +0.128 |
ours | +0.125 |
aman | +0.124 |
Neg logit contributions | |
friends | -0.083 |
marched | -0.076 |
, | -0.076 |
sisters | -0.068 |
came | -0.067 |
Token | ch |
Token ID | 354 |
Feature activation | +1.61e-03 |
Pos logit contributions | |
friends | +0.020 |
sisters | +0.019 |
brothers | +0.018 |
family | +0.018 |
marched | +0.018 |
Neg logit contributions | |
Here | -0.016 |
right | -0.015 |
ours | -0.015 |
fy | -0.014 |
chard | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -4.89e-03 |
Pos logit contributions | |
friends | +0.001 |
sisters | +0.001 |
marched | +0.001 |
brothers | +0.001 |
family | +0.001 |
Neg logit contributions | |
Here | -0.003 |
right | -0.003 |
ours | -0.003 |
rily | -0.003 |
chard | -0.003 |
Token | jumped |
Token ID | 11687 |
Feature activation | -7.35e-03 |
Pos logit contributions | |
Here | +0.012 |
chard | +0.012 |
ours | +0.011 |
redd | +0.011 |
right | +0.011 |
Neg logit contributions | |
friends | -0.004 |
marched | -0.003 |
sisters | -0.003 |
brothers | -0.003 |
, | -0.003 |
Token | rope |
Token ID | 17182 |
Feature activation | -8.55e-03 |
Pos logit contributions | |
Here | +0.016 |
ours | +0.016 |
chard | +0.016 |
rily | +0.015 |
right | +0.015 |
Neg logit contributions | |
friends | -0.007 |
marched | -0.007 |
sisters | -0.007 |
brothers | -0.006 |
family | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +7.09e-03 |
Pos logit contributions | |
Here | +0.007 |
rily | +0.007 |
finder | +0.006 |
right | +0.006 |
chard | +0.006 |
Neg logit contributions | |
friends | -0.003 |
marched | -0.003 |
sisters | -0.003 |
brothers | -0.002 |
family | -0.002 |
Token | |
Token ID | 220 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
friends | +0.009 |
marched | +0.008 |
, | +0.008 |
brothers | +0.007 |
sisters | +0.007 |
Neg logit contributions | |
ours | -0.014 |
chard | -0.014 |
right | -0.014 |
Here | -0.014 |
redd | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +8.43e-04 |
Pos logit contributions | |
Here | +0.012 |
chard | +0.011 |
ours | +0.011 |
right | +0.011 |
redd | +0.011 |
Neg logit contributions | |
friends | -0.004 |
marched | -0.003 |
sisters | -0.003 |
, | -0.003 |
came | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +6.95e-03 |
Pos logit contributions | |
friends | +0.001 |
marched | +0.001 |
, | +0.000 |
sisters | +0.000 |
brothers | +0.000 |
Neg logit contributions | |
Here | -0.002 |
chard | -0.002 |
ours | -0.002 |
redd | -0.002 |
right | -0.002 |
Token | Hop |
Token ID | 23483 |
Feature activation | -6.24e-04 |
Pos logit contributions | |
friends | +0.012 |
marched | +0.011 |
sisters | +0.011 |
, | +0.011 |
came | +0.011 |
Neg logit contributions | |
Here | -0.011 |
chard | -0.010 |
ours | -0.010 |
redd | -0.010 |
right | -0.010 |
Token | sc |
Token ID | 1416 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
Here | +0.001 |
chard | +0.001 |
ours | +0.001 |
right | +0.001 |
rily | +0.001 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.000 |
sisters | -0.000 |
brothers | -0.000 |
, | -0.000 |
Token | ot |
Token ID | 313 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
chard | +0.139 |
redd | +0.126 |
Here | +0.125 |
nam | +0.122 |
aman | +0.121 |
Neg logit contributions | |
friends | -0.089 |
marched | -0.080 |
, | -0.079 |
sisters | -0.070 |
spl | -0.069 |
Token | ch |
Token ID | 354 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
friends | +0.025 |
marched | +0.023 |
sisters | +0.022 |
brothers | +0.022 |
family | +0.021 |
Neg logit contributions | |
Here | -0.031 |
chard | -0.030 |
right | -0.029 |
ours | -0.029 |
redd | -0.029 |
Token | thanked |
Token ID | 26280 |
Feature activation | -6.53e-04 |
Pos logit contributions | |
friends | +0.015 |
marched | +0.014 |
sisters | +0.013 |
, | +0.013 |
brothers | +0.013 |
Neg logit contributions | |
Here | -0.023 |
chard | -0.023 |
ours | -0.023 |
right | -0.022 |
redd | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +3.83e-03 |
Pos logit contributions | |
Here | +0.001 |
chard | +0.001 |
ours | +0.001 |
rily | +0.001 |
right | +0.001 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
sisters | -0.001 |
came | -0.001 |
brothers | -0.001 |
Token | magical |
Token ID | 10883 |
Feature activation | +1.78e-03 |
Pos logit contributions | |
marched | +0.005 |
friends | +0.005 |
came | +0.004 |
, | +0.004 |
sisters | +0.004 |
Neg logit contributions | |
Here | -0.007 |
chard | -0.007 |
redd | -0.007 |
ours | -0.007 |
right | -0.007 |
Token | play |
Token ID | 711 |
Feature activation | +7.78e-03 |
Pos logit contributions | |
Here | +0.001 |
ours | +0.001 |
right | +0.001 |
chard | +0.001 |
redd | +0.001 |
Neg logit contributions | |
friends | -0.000 |
marched | -0.000 |
sisters | -0.000 |
brothers | -0.000 |
helpers | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
brothers | +0.010 |
sisters | +0.010 |
lee | +0.009 |
marched | +0.009 |
siblings | +0.009 |
Neg logit contributions | |
Here | -0.013 |
chard | -0.013 |
right | -0.012 |
ours | -0.012 |
curiously | -0.012 |
Token | game |
Token ID | 983 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
Here | +0.051 |
chard | +0.048 |
ours | +0.048 |
rily | +0.046 |
right | +0.046 |
Neg logit contributions | |
friends | -0.025 |
marched | -0.022 |
, | -0.021 |
family | -0.021 |
marching | -0.020 |
Token | of |
Token ID | 286 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
Here | +0.046 |
right | +0.045 |
chard | +0.045 |
ours | +0.044 |
finder | +0.042 |
Neg logit contributions | |
friends | -0.026 |
marched | -0.025 |
brothers | -0.024 |
sisters | -0.024 |
family | -0.023 |
Token | hop |
Token ID | 1725 |
Feature activation | -6.71e-03 |
Pos logit contributions | |
Here | +0.047 |
ours | +0.047 |
chard | +0.046 |
right | +0.044 |
redd | +0.044 |
Neg logit contributions | |
friends | -0.027 |
marched | -0.026 |
sisters | -0.025 |
brothers | -0.024 |
came | -0.024 |
Token | sc |
Token ID | 1416 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
Here | +0.013 |
chard | +0.013 |
ours | +0.013 |
right | +0.013 |
redd | +0.013 |
Neg logit contributions | |
friends | -0.008 |
marched | -0.007 |
sisters | -0.007 |
brothers | -0.007 |
family | -0.007 |
Token | ot |
Token ID | 313 |
Feature activation | +9.85e-03 |
Pos logit contributions | |
Here | +0.120 |
chard | +0.119 |
ours | +0.115 |
redd | +0.111 |
right | +0.110 |
Neg logit contributions | |
friends | -0.088 |
marched | -0.082 |
, | -0.078 |
sisters | -0.076 |
came | -0.076 |
Token | ch |
Token ID | 354 |
Feature activation | +2.45e-03 |
Pos logit contributions | |
friends | +0.019 |
sisters | +0.019 |
family | +0.018 |
brothers | +0.018 |
helpers | +0.018 |
Neg logit contributions | |
Here | -0.010 |
right | -0.010 |
like | -0.009 |
fy | -0.009 |
shirt | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -6.30e-03 |
Pos logit contributions | |
sisters | +0.002 |
friends | +0.002 |
family | +0.002 |
helpers | +0.002 |
marched | +0.002 |
Neg logit contributions | |
right | -0.005 |
Here | -0.005 |
like | -0.004 |
ours | -0.004 |
rily | -0.004 |
Token | but |
Token ID | 475 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
Here | +0.014 |
chard | +0.014 |
ours | +0.013 |
right | +0.013 |
redd | +0.013 |
Neg logit contributions | |
friends | -0.006 |
marched | -0.006 |
, | -0.005 |
sisters | -0.005 |
came | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
Here | +0.033 |
chard | +0.031 |
ours | +0.031 |
rily | +0.030 |
redd | +0.030 |
Neg logit contributions | |
friends | -0.018 |
marched | -0.016 |
, | -0.016 |
came | -0.015 |
sisters | -0.014 |
Token | on |
Token ID | 319 |
Feature activation | -2.10e-03 |
Pos logit contributions | |
Here | +0.017 |
ours | +0.016 |
chard | +0.016 |
right | +0.016 |
redd | +0.015 |
Neg logit contributions | |
friends | -0.007 |
, | -0.007 |
came | -0.006 |
marched | -0.006 |
. | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | -8.06e-03 |
Pos logit contributions | |
Here | +0.006 |
ours | +0.006 |
chard | +0.006 |
ited | +0.005 |
mediately | +0.005 |
Neg logit contributions | |
, | -0.001 |
friends | -0.001 |
. | -0.001 |
came | -0.001 |
family | -0.001 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.71e-03 |
Pos logit contributions | |
Here | +0.014 |
chard | +0.013 |
ours | +0.013 |
redd | +0.013 |
right | +0.012 |
Neg logit contributions | |
friends | -0.012 |
marched | -0.012 |
came | -0.011 |
sisters | -0.011 |
brothers | -0.011 |
Token | my |
Token ID | 1820 |
Feature activation | +6.64e-03 |
Pos logit contributions | |
Here | +0.011 |
ours | +0.011 |
chard | +0.011 |
redd | +0.011 |
right | +0.010 |
Neg logit contributions | |
friends | -0.004 |
, | -0.004 |
. | -0.004 |
came | -0.004 |
marched | -0.004 |
Token | 's |
Token ID | 338 |
Feature activation | -5.20e-03 |
Pos logit contributions | |
, | +0.004 |
friends | +0.003 |
. | +0.003 |
marched | +0.002 |
came | +0.002 |
Neg logit contributions | |
Here | -0.019 |
chard | -0.018 |
ours | -0.018 |
redd | -0.018 |
right | -0.017 |
Token | brand |
Token ID | 4508 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
Here | +0.009 |
chard | +0.009 |
ours | +0.009 |
right | +0.009 |
redd | +0.009 |
Neg logit contributions | |
friends | -0.008 |
marched | -0.007 |
, | -0.007 |
sisters | -0.007 |
brothers | -0.007 |
Token | new |
Token ID | 649 |
Feature activation | -6.16e-03 |
Pos logit contributions | |
chard | +0.148 |
ours | +0.141 |
Here | +0.138 |
ited | +0.137 |
right | +0.134 |
Neg logit contributions | |
friends | -0.074 |
, | -0.062 |
. | -0.059 |
family | -0.054 |
came | -0.053 |
Token | table |
Token ID | 3084 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
Here | +0.011 |
chard | +0.010 |
ours | +0.010 |
redd | +0.010 |
right | +0.010 |
Neg logit contributions | |
friends | -0.009 |
marched | -0.009 |
sisters | -0.008 |
brothers | -0.008 |
came | -0.008 |
Token | ! |
Token ID | 0 |
Feature activation | -6.04e-03 |
Pos logit contributions | |
Here | +0.009 |
chard | +0.009 |
ours | +0.009 |
right | +0.008 |
redd | +0.008 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.001 |
sisters | -0.001 |
brothers | -0.001 |
came | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
chard | +0.013 |
ours | +0.013 |
Here | +0.013 |
redd | +0.012 |
right | +0.012 |
Neg logit contributions | |
friends | -0.006 |
marched | -0.006 |
, | -0.006 |
came | -0.005 |
sisters | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +5.67e-03 |
Pos logit contributions | |
chard | +0.005 |
Here | +0.005 |
ours | +0.005 |
redd | +0.005 |
right | +0.005 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
, | -0.001 |
came | -0.001 |
family | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.22e-03 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.003 |
sisters | +0.002 |
brothers | +0.002 |
came | +0.002 |
Neg logit contributions | |
Here | -0.023 |
chard | -0.023 |
ours | -0.022 |
right | -0.022 |
redd | -0.022 |
Token | |
Token ID | 220 |
Feature activation | -6.44e-04 |
Pos logit contributions | |
friends | +0.002 |
, | +0.002 |
marched | +0.002 |
came | +0.002 |
family | +0.002 |
Neg logit contributions | |
ours | -0.005 |
chard | -0.005 |
redd | -0.005 |
Here | -0.005 |
right | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +1.45e-03 |
Pos logit contributions | |
chard | +0.002 |
Here | +0.002 |
ours | +0.002 |
redd | +0.002 |
right | +0.002 |
Neg logit contributions | |
friends | -0.000 |
marched | -0.000 |
, | -0.000 |
brothers | -0.000 |
came | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +6.42e-03 |
Pos logit contributions | |
friends | +0.001 |
marched | +0.001 |
, | +0.001 |
came | +0.001 |
family | +0.000 |
Neg logit contributions | |
chard | -0.004 |
ours | -0.004 |
Here | -0.004 |
redd | -0.004 |
rily | -0.004 |
Token | Hop |
Token ID | 23483 |
Feature activation | +6.29e-03 |
Pos logit contributions | |
friends | +0.009 |
marched | +0.009 |
, | +0.008 |
came | +0.008 |
marching | +0.008 |
Neg logit contributions | |
chard | -0.011 |
ours | -0.011 |
Here | -0.011 |
redd | -0.011 |
rily | -0.011 |
Token | sc |
Token ID | 1416 |
Feature activation | -6.34e-02 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.005 |
sisters | +0.004 |
, | +0.004 |
brothers | +0.004 |
Neg logit contributions | |
Here | -0.015 |
chard | -0.015 |
ours | -0.015 |
right | -0.014 |
redd | -0.014 |
Token | ot |
Token ID | 313 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
chard | +0.136 |
redd | +0.124 |
Here | +0.121 |
aman | +0.120 |
nam | +0.117 |
Neg logit contributions | |
friends | -0.087 |
, | -0.079 |
marched | -0.077 |
came | -0.067 |
brothers | -0.067 |
Token | ch |
Token ID | 354 |
Feature activation | +7.59e-03 |
Pos logit contributions | |
friends | +0.020 |
marched | +0.018 |
sisters | +0.017 |
brothers | +0.017 |
family | +0.016 |
Neg logit contributions | |
Here | -0.031 |
chard | -0.031 |
right | -0.030 |
ours | -0.030 |
rily | -0.029 |
Token | hopped |
Token ID | 45230 |
Feature activation | -8.55e-03 |
Pos logit contributions | |
friends | +0.010 |
marched | +0.009 |
sisters | +0.009 |
brothers | +0.009 |
family | +0.009 |
Neg logit contributions | |
Here | -0.013 |
right | -0.013 |
chard | -0.013 |
rily | -0.013 |
ours | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
Here | +0.019 |
chard | +0.018 |
ours | +0.018 |
right | +0.018 |
redd | +0.018 |
Neg logit contributions | |
friends | -0.009 |
marched | -0.008 |
sisters | -0.007 |
brothers | -0.007 |
, | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -7.50e-03 |
Pos logit contributions | |
Here | +0.041 |
chard | +0.041 |
ours | +0.040 |
redd | +0.039 |
rily | +0.038 |
Neg logit contributions | |
friends | -0.011 |
marched | -0.009 |
, | -0.009 |
family | -0.008 |
marching | -0.008 |
Token | flashlight |
Token ID | 38371 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
friends | +0.002 |
marched | +0.002 |
, | +0.002 |
sisters | +0.002 |
family | +0.002 |
Neg logit contributions | |
Here | -0.003 |
chard | -0.003 |
ours | -0.003 |
right | -0.003 |
rily | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
friends | +0.010 |
marched | +0.009 |
sisters | +0.008 |
brothers | +0.008 |
family | +0.007 |
Neg logit contributions | |
Here | -0.032 |
chard | -0.032 |
ours | -0.031 |
right | -0.030 |
rily | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -1.69e-03 |
Pos logit contributions | |
Here | +0.034 |
chard | +0.033 |
ours | +0.032 |
right | +0.032 |
aman | +0.032 |
Neg logit contributions | |
friends | -0.008 |
marched | -0.007 |
, | -0.007 |
came | -0.006 |
. | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -2.03e-03 |
Pos logit contributions | |
Here | +0.004 |
chard | +0.004 |
ours | +0.004 |
right | +0.004 |
aman | +0.004 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.002 |
, | -0.001 |
came | -0.001 |
sisters | -0.001 |
Token | magn |
Token ID | 7842 |
Feature activation | +9.72e-03 |
Pos logit contributions | |
Here | +0.004 |
chard | +0.004 |
ours | +0.004 |
right | +0.004 |
redd | +0.004 |
Neg logit contributions | |
friends | -0.003 |
marched | -0.002 |
, | -0.002 |
sisters | -0.002 |
family | -0.002 |
Token | ifying |
Token ID | 4035 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
friends | +0.022 |
marched | +0.022 |
, | +0.022 |
came | +0.022 |
. | +0.021 |
Neg logit contributions | |
Here | -0.009 |
chard | -0.008 |
ours | -0.008 |
redd | -0.007 |
right | -0.007 |
Token | glass |
Token ID | 5405 |
Feature activation | -8.58e-04 |
Pos logit contributions | |
Here | +0.113 |
chard | +0.109 |
ours | +0.105 |
right | +0.103 |
rily | +0.101 |
Neg logit contributions | |
friends | -0.091 |
, | -0.090 |
came | -0.083 |
marched | -0.082 |
. | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e-04 |
Pos logit contributions | |
chard | +0.002 |
Here | +0.002 |
ours | +0.002 |
rily | +0.002 |
redd | +0.002 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
sisters | -0.000 |
brothers | -0.000 |
marching | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -4.24e-05 |
Pos logit contributions | |
ours | +0.000 |
chard | +0.000 |
ited | +0.000 |
redd | +0.000 |
right | +0.000 |
Neg logit contributions | |
friends | -0.000 |
marched | -0.000 |
, | -0.000 |
came | -0.000 |
sisters | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +4.33e-03 |
Pos logit contributions | |
chard | +0.000 |
ours | +0.000 |
redd | +0.000 |
Here | +0.000 |
rily | +0.000 |
Neg logit contributions | |
friends | -0.000 |
marched | -0.000 |
, | -0.000 |
came | -0.000 |
. | -0.000 |
Token | As |
Token ID | 1722 |
Feature activation | +8.78e-03 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.004 |
, | +0.003 |
sisters | +0.003 |
came | +0.003 |
Neg logit contributions | |
chard | -0.010 |
ours | -0.010 |
Here | -0.010 |
redd | -0.009 |
rily | -0.009 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.17e-03 |
Pos logit contributions | |
chard | +0.015 |
ited | +0.014 |
curiously | +0.014 |
rily | +0.014 |
right | +0.014 |
Neg logit contributions | |
friends | -0.008 |
sisters | -0.008 |
helpers | -0.007 |
marching | -0.007 |
marched | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -2.10e-03 |
Pos logit contributions | |
friends | +0.002 |
, | +0.002 |
marched | +0.002 |
came | +0.002 |
brothers | +0.002 |
Neg logit contributions | |
Here | -0.005 |
ours | -0.005 |
chard | -0.005 |
redd | -0.005 |
right | -0.005 |
Token | monster |
Token ID | 9234 |
Feature activation | +7.65e-03 |
Pos logit contributions | |
Here | +0.005 |
chard | +0.005 |
ours | +0.005 |
redd | +0.004 |
right | +0.004 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.002 |
sisters | -0.002 |
, | -0.002 |
brothers | -0.002 |
Token | again |
Token ID | 757 |
Feature activation | +7.58e-03 |
Pos logit contributions | |
friends | +0.006 |
marched | +0.005 |
sisters | +0.005 |
brothers | +0.005 |
family | +0.005 |
Neg logit contributions | |
chard | -0.018 |
Here | -0.018 |
ours | -0.017 |
right | -0.017 |
rily | -0.017 |
Token | - |
Token ID | 532 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
friends | +0.004 |
sisters | +0.004 |
marched | +0.004 |
brothers | +0.004 |
marching | +0.003 |
Neg logit contributions | |
chard | -0.019 |
Here | -0.019 |
ours | -0.018 |
right | -0.018 |
aman | -0.018 |
Token | sc |
Token ID | 1416 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
Here | +0.027 |
chard | +0.026 |
ours | +0.026 |
right | +0.025 |
rily | +0.025 |
Neg logit contributions | |
friends | -0.013 |
marched | -0.012 |
, | -0.012 |
came | -0.011 |
brothers | -0.011 |
Token | ur |
Token ID | 333 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
chard | +0.129 |
redd | +0.118 |
Here | +0.117 |
aman | +0.113 |
nam | +0.111 |
Neg logit contributions | |
friends | -0.089 |
, | -0.080 |
marched | -0.079 |
brothers | -0.070 |
came | -0.070 |
Token | rying |
Token ID | 14992 |
Feature activation | +5.68e-03 |
Pos logit contributions | |
friends | +0.038 |
marched | +0.035 |
sisters | +0.035 |
brothers | +0.035 |
family | +0.035 |
Neg logit contributions | |
chard | -0.025 |
ours | -0.022 |
rily | -0.022 |
right | -0.022 |
Here | -0.022 |
Token | away |
Token ID | 1497 |
Feature activation | +2.02e-03 |
Pos logit contributions | |
friends | +0.006 |
marched | +0.005 |
, | +0.005 |
came | +0.005 |
marching | +0.005 |
Neg logit contributions | |
Here | -0.013 |
chard | -0.012 |
ours | -0.012 |
redd | -0.012 |
right | -0.012 |
Token | from |
Token ID | 422 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
friends | +0.002 |
marched | +0.002 |
sisters | +0.002 |
brothers | +0.001 |
marching | +0.001 |
Neg logit contributions | |
Here | -0.005 |
chard | -0.004 |
ours | -0.004 |
right | -0.004 |
rily | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +4.60e-03 |
Pos logit contributions | |
friends | +0.025 |
, | +0.020 |
marched | +0.018 |
marching | +0.018 |
family | +0.017 |
Neg logit contributions | |
Here | -0.081 |
chard | -0.076 |
redd | -0.076 |
aman | -0.075 |
ours | -0.074 |
Token | group |
Token ID | 1448 |
Feature activation | +2.04e-03 |
Pos logit contributions | |
friends | +0.008 |
marched | +0.008 |
sisters | +0.007 |
, | +0.007 |
brothers | +0.007 |
Neg logit contributions | |
Here | -0.014 |
chard | -0.014 |
ours | -0.014 |
redd | -0.013 |
right | -0.013 |
Token | of |
Token ID | 286 |
Feature activation | -7.36e-03 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.003 |
brothers | +0.002 |
sisters | +0.002 |
helpers | +0.002 |
Neg logit contributions | |
ours | -0.004 |
chard | -0.004 |
Here | -0.003 |
right | -0.003 |
redd | -0.003 |
Token | girls |
Token ID | 4813 |
Feature activation | +6.98e-05 |
Pos logit contributions | |
Here | +0.017 |
chard | +0.017 |
ours | +0.017 |
right | +0.016 |
redd | +0.016 |
Neg logit contributions | |
friends | -0.007 |
marched | -0.006 |
sisters | -0.005 |
, | -0.005 |
brothers | -0.005 |
Token | playing |
Token ID | 2712 |
Feature activation | -3.28e-03 |
Pos logit contributions | |
marched | +0.000 |
brothers | +0.000 |
friends | +0.000 |
helpers | +0.000 |
came | +0.000 |
Neg logit contributions | |
chard | -0.000 |
ours | -0.000 |
Here | -0.000 |
curiously | -0.000 |
rily | -0.000 |
Token | hop |
Token ID | 1725 |
Feature activation | -1.26e-03 |
Pos logit contributions | |
Here | +0.007 |
chard | +0.007 |
ours | +0.007 |
right | +0.007 |
redd | +0.006 |
Neg logit contributions | |
friends | -0.003 |
marched | -0.003 |
sisters | -0.003 |
brothers | -0.003 |
family | -0.003 |
Token | sc |
Token ID | 1416 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
Here | +0.001 |
chard | +0.001 |
ours | +0.001 |
right | +0.001 |
redd | +0.001 |
Neg logit contributions | |
friends | -0.003 |
marched | -0.002 |
sisters | -0.002 |
brothers | -0.002 |
family | -0.002 |
Token | ot |
Token ID | 313 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
Here | +0.112 |
chard | +0.111 |
ours | +0.107 |
redd | +0.104 |
right | +0.102 |
Neg logit contributions | |
friends | -0.091 |
marched | -0.085 |
, | -0.081 |
sisters | -0.080 |
came | -0.079 |
Token | ch |
Token ID | 354 |
Feature activation | +2.22e-03 |
Pos logit contributions | |
friends | +0.027 |
sisters | +0.026 |
family | +0.025 |
brothers | +0.025 |
helpers | +0.024 |
Neg logit contributions | |
Here | -0.021 |
right | -0.020 |
ours | -0.019 |
fy | -0.018 |
like | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +4.08e-03 |
Pos logit contributions | |
friends | +0.002 |
marched | +0.002 |
sisters | +0.002 |
family | +0.002 |
helpers | +0.001 |
Neg logit contributions | |
right | -0.005 |
Here | -0.005 |
ours | -0.005 |
chard | -0.005 |
rily | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | -7.23e-04 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.005 |
, | +0.005 |
sisters | +0.004 |
came | +0.004 |
Neg logit contributions | |
chard | -0.008 |
Here | -0.008 |
ours | -0.008 |
right | -0.008 |
redd | -0.008 |
Token | joined |
Token ID | 5399 |
Feature activation | -2.98e-03 |
Pos logit contributions | |
chard | +0.001 |
redd | +0.001 |
ours | +0.001 |
nam | +0.001 |
ited | +0.001 |
Neg logit contributions | |
friends | -0.001 |
helpers | -0.001 |
brothers | -0.001 |
sisters | -0.001 |
siblings | -0.001 |
Token | hide |
Token ID | 7808 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
Here | +0.031 |
chard | +0.030 |
ours | +0.030 |
redd | +0.029 |
right | +0.029 |
Neg logit contributions | |
friends | -0.014 |
marched | -0.013 |
, | -0.012 |
sisters | -0.012 |
came | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +7.58e-03 |
Pos logit contributions | |
friends | +0.007 |
marched | +0.006 |
sisters | +0.005 |
brothers | +0.005 |
came | +0.005 |
Neg logit contributions | |
Here | -0.025 |
chard | -0.025 |
ours | -0.025 |
right | -0.024 |
redd | -0.024 |
Token | seek |
Token ID | 5380 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
friends | +0.007 |
marched | +0.006 |
, | +0.006 |
sisters | +0.006 |
came | +0.006 |
Neg logit contributions | |
Here | -0.017 |
chard | -0.017 |
ours | -0.017 |
redd | -0.016 |
right | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -8.11e-03 |
Pos logit contributions | |
friends | +0.010 |
marched | +0.010 |
brothers | +0.008 |
sisters | +0.008 |
came | +0.008 |
Neg logit contributions | |
Here | -0.034 |
chard | -0.034 |
ours | -0.034 |
rily | -0.033 |
right | -0.033 |
Token | hop |
Token ID | 1725 |
Feature activation | -3.03e-03 |
Pos logit contributions | |
Here | +0.019 |
chard | +0.019 |
ours | +0.019 |
redd | +0.018 |
right | +0.018 |
Neg logit contributions | |
friends | -0.007 |
marched | -0.006 |
sisters | -0.005 |
, | -0.005 |
brothers | -0.005 |
Token | sc |
Token ID | 1416 |
Feature activation | -6.13e-02 |
Pos logit contributions | |
Here | +0.006 |
ours | +0.006 |
chard | +0.006 |
right | +0.006 |
rily | +0.006 |
Neg logit contributions | |
friends | -0.003 |
marched | -0.003 |
sisters | -0.003 |
brothers | -0.003 |
family | -0.003 |
Token | ot |
Token ID | 313 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
chard | +0.122 |
Here | +0.120 |
redd | +0.113 |
ours | +0.112 |
aman | +0.109 |
Neg logit contributions | |
friends | -0.082 |
marched | -0.075 |
, | -0.073 |
sisters | -0.068 |
came | -0.067 |
Token | ch |
Token ID | 354 |
Feature activation | +4.67e-03 |
Pos logit contributions | |
friends | +0.025 |
brothers | +0.023 |
family | +0.023 |
sisters | +0.023 |
marched | +0.023 |
Neg logit contributions | |
Here | -0.024 |
ours | -0.023 |
right | -0.023 |
fy | -0.022 |
rily | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +6.96e-03 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.004 |
family | +0.004 |
sisters | +0.003 |
brothers | +0.003 |
Neg logit contributions | |
right | -0.010 |
ours | -0.010 |
Here | -0.010 |
rily | -0.009 |
lowest | -0.009 |
Token | much |
Token ID | 881 |
Feature activation | -3.84e-03 |
Pos logit contributions | |
friends | +0.007 |
marched | +0.007 |
sisters | +0.006 |
brothers | +0.006 |
, | +0.006 |
Neg logit contributions | |
Here | -0.015 |
chard | -0.015 |
ours | -0.015 |
redd | -0.014 |
right | -0.014 |
Token | more |
Token ID | 517 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
Here | +0.007 |
ours | +0.007 |
chard | +0.007 |
right | +0.007 |
redd | +0.007 |
Neg logit contributions | |
friends | -0.005 |
marched | -0.004 |
sisters | -0.004 |
brothers | -0.004 |
came | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -1.89e-03 |
Pos logit contributions | |
friends | +0.016 |
marched | +0.016 |
sisters | +0.014 |
brothers | +0.014 |
mo | +0.013 |
Neg logit contributions | |
chard | -0.042 |
ours | -0.042 |
Here | -0.041 |
right | -0.039 |
rily | -0.038 |
Token | Barry |
Token ID | 14488 |
Feature activation | -3.30e-03 |
Pos logit contributions | |
Here | +0.004 |
chard | +0.003 |
ours | +0.003 |
right | +0.003 |
redd | +0.003 |
Neg logit contributions | |
friends | -0.003 |
marched | -0.002 |
sisters | -0.002 |
came | -0.002 |
marching | -0.002 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -5.06e-03 |
Pos logit contributions | |
Here | +0.007 |
chard | +0.007 |
ours | +0.007 |
right | +0.007 |
rily | +0.007 |
Neg logit contributions | |
friends | -0.003 |
marched | -0.003 |
sisters | -0.002 |
marching | -0.002 |
brothers | -0.002 |
Token | playing |
Token ID | 2712 |
Feature activation | -6.52e-03 |
Pos logit contributions | |
chard | +0.010 |
Here | +0.009 |
ours | +0.009 |
afar | +0.009 |
nam | +0.009 |
Neg logit contributions | |
marched | -0.005 |
friends | -0.005 |
sisters | -0.005 |
brothers | -0.005 |
came | -0.005 |
Token | hop |
Token ID | 1725 |
Feature activation | -5.28e-03 |
Pos logit contributions | |
Here | +0.012 |
chard | +0.012 |
ours | +0.012 |
rily | +0.011 |
right | +0.011 |
Neg logit contributions | |
marched | -0.007 |
sisters | -0.007 |
friends | -0.007 |
brothers | -0.006 |
family | -0.006 |
Token | sc |
Token ID | 1416 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
Here | +0.010 |
chard | +0.010 |
ours | +0.010 |
right | +0.010 |
redd | +0.010 |
Neg logit contributions | |
friends | -0.007 |
marched | -0.006 |
sisters | -0.006 |
brothers | -0.006 |
came | -0.006 |
Token | ot |
Token ID | 313 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
chard | +0.125 |
Here | +0.120 |
redd | +0.115 |
ours | +0.114 |
aman | +0.112 |
Neg logit contributions | |
friends | -0.078 |
, | -0.072 |
marched | -0.071 |
sisters | -0.064 |
. | -0.064 |
Token | ch |
Token ID | 354 |
Feature activation | +5.01e-03 |
Pos logit contributions | |
friends | +0.020 |
sisters | +0.019 |
marched | +0.019 |
brothers | +0.019 |
family | +0.018 |
Neg logit contributions | |
Here | -0.020 |
right | -0.019 |
ours | -0.018 |
chard | -0.018 |
redd | -0.017 |
Token | with |
Token ID | 351 |
Feature activation | +3.59e-04 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.005 |
sisters | +0.005 |
family | +0.005 |
came | +0.005 |
Neg logit contributions | |
Here | -0.010 |
right | -0.010 |
chard | -0.009 |
ours | -0.009 |
rily | -0.009 |
Token | them |
Token ID | 606 |
Feature activation | +2.04e-03 |
Pos logit contributions | |
friends | +0.000 |
marched | +0.000 |
, | +0.000 |
sisters | +0.000 |
came | +0.000 |
Neg logit contributions | |
Here | -0.001 |
chard | -0.001 |
ours | -0.001 |
redd | -0.001 |
right | -0.001 |
Token | so |
Token ID | 523 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
friends | +0.001 |
marched | +0.001 |
sisters | +0.001 |
brothers | +0.001 |
came | +0.001 |
Neg logit contributions | |
chard | -0.005 |
Here | -0.005 |
ours | -0.005 |
right | -0.005 |
rily | -0.005 |
Token | bunny |
Token ID | 44915 |
Feature activation | +4.52e-03 |
Pos logit contributions | |
ours | +0.033 |
rily | +0.032 |
Here | +0.032 |
redd | +0.032 |
chard | +0.031 |
Neg logit contributions | |
marched | -0.024 |
friends | -0.022 |
sisters | -0.020 |
marching | -0.020 |
came | -0.020 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
marched | +0.005 |
friends | +0.005 |
sisters | +0.005 |
brothers | +0.004 |
marching | +0.004 |
Neg logit contributions | |
chard | -0.009 |
Here | -0.009 |
ours | -0.009 |
right | -0.008 |
redd | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +4.07e-03 |
Pos logit contributions | |
friends | +0.016 |
marched | +0.014 |
, | +0.013 |
sisters | +0.013 |
came | +0.013 |
Neg logit contributions | |
Here | -0.030 |
chard | -0.029 |
ours | -0.029 |
redd | -0.028 |
right | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +7.21e-03 |
Pos logit contributions | |
friends | +0.004 |
sisters | +0.004 |
marched | +0.003 |
brothers | +0.003 |
came | +0.003 |
Neg logit contributions | |
Here | -0.009 |
chard | -0.009 |
right | -0.008 |
ours | -0.008 |
rily | -0.008 |
Token | Hop |
Token ID | 23483 |
Feature activation | +3.46e-03 |
Pos logit contributions | |
friends | +0.013 |
sisters | +0.012 |
marched | +0.012 |
brothers | +0.012 |
came | +0.012 |
Neg logit contributions | |
Here | -0.010 |
chard | -0.010 |
right | -0.009 |
ours | -0.009 |
redd | -0.009 |
Token | sc |
Token ID | 1416 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.003 |
sisters | +0.003 |
brothers | +0.003 |
, | +0.003 |
Neg logit contributions | |
Here | -0.008 |
chard | -0.008 |
ours | -0.007 |
right | -0.007 |
redd | -0.007 |
Token | ot |
Token ID | 313 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
chard | +0.126 |
redd | +0.118 |
Here | +0.114 |
aman | +0.114 |
ours | +0.113 |
Neg logit contributions | |
friends | -0.083 |
, | -0.076 |
marched | -0.073 |
came | -0.066 |
. | -0.065 |
Token | ch |
Token ID | 354 |
Feature activation | +9.91e-03 |
Pos logit contributions | |
friends | +0.018 |
marched | +0.016 |
sisters | +0.015 |
brothers | +0.015 |
marching | +0.015 |
Neg logit contributions | |
Here | -0.031 |
chard | -0.030 |
right | -0.029 |
ours | -0.029 |
rily | -0.028 |
Token | replied |
Token ID | 8712 |
Feature activation | -5.30e-03 |
Pos logit contributions | |
friends | +0.014 |
marched | +0.013 |
sisters | +0.013 |
brothers | +0.012 |
family | +0.012 |
Neg logit contributions | |
Here | -0.017 |
chard | -0.017 |
ours | -0.016 |
right | -0.016 |
rily | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +7.90e-03 |
Pos logit contributions | |
chard | +0.013 |
Here | +0.013 |
rily | +0.013 |
curiously | +0.012 |
right | +0.012 |
Neg logit contributions | |
marched | -0.003 |
friends | -0.003 |
sisters | -0.003 |
brothers | -0.003 |
marching | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | -2.46e-03 |
Pos logit contributions | |
friends | +0.009 |
marched | +0.008 |
sisters | +0.008 |
brothers | +0.008 |
helpers | +0.007 |
Neg logit contributions | |
chard | -0.016 |
Here | -0.016 |
rily | -0.015 |
redd | -0.014 |
right | -0.014 |
Token | is |
Token ID | 318 |
Feature activation | +9.80e-03 |
Pos logit contributions | |
Here | +0.011 |
chard | +0.010 |
ours | +0.010 |
redd | +0.010 |
right | +0.010 |
Neg logit contributions | |
friends | -0.006 |
marched | -0.006 |
, | -0.005 |
came | -0.005 |
sisters | -0.005 |
Token | hiding |
Token ID | 11816 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
marched | +0.011 |
friends | +0.011 |
sisters | +0.009 |
brothers | +0.009 |
came | +0.009 |
Neg logit contributions | |
chard | -0.020 |
ours | -0.020 |
Here | -0.019 |
redd | -0.018 |
right | -0.018 |
Token | somewhere |
Token ID | 7382 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
friends | +0.010 |
marched | +0.009 |
, | +0.008 |
sisters | +0.008 |
brothers | +0.008 |
Neg logit contributions | |
Here | -0.030 |
chard | -0.030 |
ours | -0.029 |
redd | -0.028 |
right | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +8.31e-03 |
Pos logit contributions | |
friends | +0.013 |
marched | +0.012 |
, | +0.011 |
sisters | +0.011 |
came | +0.011 |
Neg logit contributions | |
Here | -0.022 |
chard | -0.021 |
ours | -0.020 |
redd | -0.020 |
right | -0.020 |
Token | Why |
Token ID | 4162 |
Feature activation | +8.81e-03 |
Pos logit contributions | |
friends | +0.012 |
marched | +0.011 |
brothers | +0.011 |
, | +0.011 |
sisters | +0.011 |
Neg logit contributions | |
chard | -0.015 |
ited | -0.014 |
ours | -0.014 |
aman | -0.014 |
right | -0.014 |
Token | don |
Token ID | 836 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
friends | +0.013 |
marched | +0.013 |
sisters | +0.012 |
brothers | +0.012 |
marching | +0.012 |
Neg logit contributions | |
Here | -0.014 |
chard | -0.014 |
ours | -0.014 |
redd | -0.013 |
right | -0.013 |
Token | 't |
Token ID | 470 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
friends | +0.073 |
marched | +0.068 |
sisters | +0.067 |
helpers | +0.067 |
mo | +0.065 |
Neg logit contributions | |
Here | -0.047 |
ours | -0.045 |
chard | -0.042 |
rily | -0.039 |
lowest | -0.039 |
Token | you |
Token ID | 345 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
friends | +0.021 |
marched | +0.020 |
brothers | +0.019 |
sisters | +0.019 |
came | +0.019 |
Neg logit contributions | |
Here | -0.018 |
chard | -0.018 |
ours | -0.018 |
rily | -0.016 |
redd | -0.016 |
Token | search |
Token ID | 2989 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
Here | +0.041 |
chard | +0.040 |
ours | +0.039 |
redd | +0.039 |
right | +0.038 |
Neg logit contributions | |
friends | -0.020 |
marched | -0.018 |
, | -0.018 |
came | -0.017 |
family | -0.016 |
Token | for |
Token ID | 329 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
, | +0.016 |
friends | +0.016 |
. | +0.014 |
on | +0.012 |
family | +0.010 |
Neg logit contributions | |
Here | -0.044 |
aman | -0.043 |
chard | -0.043 |
redd | -0.043 |
ited | -0.042 |
Token | him |
Token ID | 683 |
Feature activation | +6.19e-03 |
Pos logit contributions | |
friends | +0.017 |
marched | +0.016 |
, | +0.015 |
sisters | +0.015 |
came | +0.015 |
Neg logit contributions | |
Here | -0.026 |
chard | -0.025 |
ours | -0.025 |
right | -0.024 |
redd | -0.024 |
Token | everyone |
Token ID | 2506 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
Here | +0.004 |
ours | +0.004 |
chard | +0.004 |
redd | +0.004 |
right | +0.004 |
Neg logit contributions | |
friends | -0.002 |
, | -0.002 |
marched | -0.002 |
family | -0.002 |
came | -0.002 |
Token | still |
Token ID | 991 |
Feature activation | +3.68e-03 |
Pos logit contributions | |
friends | +0.016 |
sisters | +0.015 |
brothers | +0.014 |
marched | +0.014 |
helpers | +0.014 |
Neg logit contributions | |
chard | -0.033 |
Here | -0.031 |
right | -0.031 |
ours | -0.030 |
rily | -0.030 |
Token | remembered |
Token ID | 12086 |
Feature activation | +7.11e-03 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.003 |
sisters | +0.003 |
brothers | +0.003 |
, | +0.002 |
Neg logit contributions | |
Here | -0.009 |
chard | -0.008 |
ours | -0.008 |
right | -0.008 |
redd | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +4.15e-03 |
Pos logit contributions | |
friends | +0.007 |
marched | +0.007 |
sisters | +0.006 |
, | +0.006 |
brothers | +0.006 |
Neg logit contributions | |
Here | -0.015 |
chard | -0.015 |
ours | -0.015 |
right | -0.014 |
redd | -0.014 |
Token | big |
Token ID | 1263 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.005 |
sisters | +0.004 |
, | +0.004 |
came | +0.004 |
Neg logit contributions | |
Here | -0.008 |
chard | -0.008 |
ours | -0.008 |
redd | -0.008 |
right | -0.008 |
Token | aer |
Token ID | 9551 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
marched | +0.013 |
friends | +0.013 |
sisters | +0.012 |
brothers | +0.011 |
marching | +0.011 |
Neg logit contributions | |
ours | -0.018 |
redd | -0.018 |
Here | -0.017 |
chard | -0.017 |
aman | -0.017 |
Token | opl |
Token ID | 20106 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
friends | +0.074 |
marched | +0.071 |
sisters | +0.067 |
, | +0.066 |
came | +0.065 |
Neg logit contributions | |
Here | -0.063 |
chard | -0.060 |
ours | -0.059 |
right | -0.058 |
aman | -0.056 |
Token | ane |
Token ID | 1531 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
friends | +0.069 |
marched | +0.067 |
sisters | +0.064 |
, | +0.062 |
came | +0.062 |
Neg logit contributions | |
Here | -0.052 |
chard | -0.050 |
ours | -0.047 |
right | -0.046 |
aman | -0.044 |
Token | flying |
Token ID | 7348 |
Feature activation | +3.89e-03 |
Pos logit contributions | |
friends | +0.016 |
marched | +0.015 |
sisters | +0.015 |
brothers | +0.014 |
helpers | +0.013 |
Neg logit contributions | |
chard | -0.041 |
ours | -0.040 |
Here | -0.040 |
right | -0.039 |
rily | -0.037 |
Token | high |
Token ID | 1029 |
Feature activation | +5.40e-03 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.004 |
, | +0.004 |
came | +0.003 |
marching | +0.003 |
Neg logit contributions | |
Here | -0.009 |
chard | -0.008 |
ours | -0.008 |
redd | -0.008 |
right | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.003 |
, | +0.003 |
came | +0.003 |
sisters | +0.003 |
Neg logit contributions | |
Here | -0.014 |
chard | -0.013 |
ours | -0.013 |
redd | -0.013 |
right | -0.013 |
Token | down |
Token ID | 866 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.002 |
, | +0.002 |
came | +0.002 |
sisters | +0.002 |
Neg logit contributions | |
Here | -0.004 |
chard | -0.004 |
ours | -0.004 |
right | -0.003 |
redd | -0.003 |
Token | alongside |
Token ID | 7848 |
Feature activation | -8.82e-03 |
Pos logit contributions | |
Here | +0.032 |
chard | +0.031 |
ours | +0.031 |
right | +0.030 |
redd | +0.030 |
Neg logit contributions | |
friends | -0.008 |
marched | -0.007 |
sisters | -0.006 |
brothers | -0.006 |
came | -0.006 |
Token | one |
Token ID | 530 |
Feature activation | -6.84e-03 |
Pos logit contributions | |
Here | +0.020 |
chard | +0.020 |
ours | +0.020 |
redd | +0.019 |
right | +0.019 |
Neg logit contributions | |
friends | -0.009 |
marched | -0.008 |
, | -0.008 |
came | -0.007 |
sisters | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
Here | +0.017 |
chard | +0.017 |
ours | +0.017 |
redd | +0.016 |
rily | +0.016 |
Neg logit contributions | |
friends | -0.006 |
, | -0.006 |
. | -0.005 |
family | -0.005 |
marched | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +6.94e-03 |
Pos logit contributions | |
friends | +0.009 |
marched | +0.008 |
, | +0.008 |
sisters | +0.007 |
brothers | +0.007 |
Neg logit contributions | |
Here | -0.025 |
chard | -0.024 |
ours | -0.024 |
redd | -0.024 |
right | -0.023 |
Token | p |
Token ID | 279 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
friends | +0.009 |
sisters | +0.007 |
family | +0.007 |
, | +0.007 |
brothers | +0.007 |
Neg logit contributions | |
Here | -0.015 |
chard | -0.014 |
ours | -0.014 |
right | -0.014 |
redd | -0.013 |
Token | udd |
Token ID | 4185 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
friends | +0.062 |
marched | +0.057 |
, | +0.055 |
sisters | +0.053 |
came | +0.053 |
Neg logit contributions | |
Here | -0.066 |
chard | -0.065 |
ours | -0.063 |
redd | -0.060 |
right | -0.059 |
Token | les |
Token ID | 829 |
Feature activation | -1.66e-03 |
Pos logit contributions | |
friends | +0.048 |
marched | +0.046 |
, | +0.045 |
came | +0.044 |
sisters | +0.043 |
Neg logit contributions | |
Here | -0.043 |
chard | -0.042 |
ours | -0.040 |
redd | -0.038 |
right | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | +5.38e-03 |
Pos logit contributions | |
chard | +0.004 |
Here | +0.004 |
ours | +0.004 |
rily | +0.004 |
right | +0.004 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
sisters | -0.001 |
brothers | -0.001 |
family | -0.001 |
Token | watched |
Token ID | 7342 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
friends | +0.006 |
marched | +0.005 |
, | +0.005 |
came | +0.005 |
sisters | +0.005 |
Neg logit contributions | |
Here | -0.012 |
chard | -0.012 |
ours | -0.011 |
right | -0.011 |
redd | -0.011 |
Token | as |
Token ID | 355 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
friends | +0.036 |
marched | +0.033 |
, | +0.031 |
sisters | +0.030 |
came | +0.029 |
Neg logit contributions | |
Here | -0.081 |
chard | -0.080 |
ours | -0.079 |
redd | -0.076 |
right | -0.076 |
Token | been |
Token ID | 587 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
sisters | +0.002 |
mo | +0.002 |
helpers | +0.002 |
brothers | +0.002 |
marching | +0.002 |
Neg logit contributions | |
ours | -0.003 |
chard | -0.003 |
Here | -0.003 |
right | -0.003 |
yours | -0.003 |
Token | able |
Token ID | 1498 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
sisters | +0.010 |
marched | +0.010 |
brothers | +0.009 |
friends | +0.009 |
mo | +0.008 |
Neg logit contributions | |
chard | -0.014 |
ours | -0.013 |
right | -0.012 |
redd | -0.012 |
ited | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +2.12e-03 |
Pos logit contributions | |
ours | +0.032 |
chard | +0.030 |
Here | +0.029 |
right | +0.029 |
redd | +0.028 |
Neg logit contributions | |
marched | -0.021 |
sisters | -0.019 |
brothers | -0.018 |
mo | -0.017 |
Kids | -0.017 |
Token | see |
Token ID | 766 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
friends | +0.003 |
sisters | +0.003 |
marched | +0.002 |
brothers | +0.002 |
helpers | +0.002 |
Neg logit contributions | |
Here | -0.004 |
chard | -0.004 |
ours | -0.004 |
right | -0.004 |
lowest | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +2.50e-03 |
Pos logit contributions | |
friends | +0.011 |
marched | +0.009 |
, | +0.009 |
brothers | +0.009 |
family | +0.008 |
Neg logit contributions | |
Here | -0.029 |
chard | -0.028 |
ours | -0.027 |
redd | -0.027 |
right | -0.027 |
Token | lightning |
Token ID | 14357 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.002 |
sisters | +0.002 |
, | +0.002 |
came | +0.002 |
Neg logit contributions | |
Here | -0.005 |
chard | -0.005 |
ours | -0.005 |
redd | -0.005 |
right | -0.005 |
Token | ! |
Token ID | 0 |
Feature activation | -4.94e-03 |
Pos logit contributions | |
friends | +0.033 |
marched | +0.029 |
sisters | +0.027 |
brothers | +0.026 |
family | +0.024 |
Neg logit contributions | |
Here | -0.085 |
chard | -0.084 |
ours | -0.082 |
right | -0.081 |
redd | -0.080 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.50e-03 |
Pos logit contributions | |
Here | +0.011 |
chard | +0.010 |
ours | +0.010 |
right | +0.010 |
redd | +0.010 |
Neg logit contributions | |
friends | -0.005 |
marched | -0.005 |
sisters | -0.004 |
came | -0.004 |
marching | -0.004 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.17e-03 |
Pos logit contributions | |
friends | +0.003 |
sisters | +0.003 |
marched | +0.003 |
helpers | +0.003 |
mo | +0.003 |
Neg logit contributions | |
Here | -0.005 |
chard | -0.004 |
right | -0.004 |
rily | -0.004 |
Here | -0.004 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.004 |
, | +0.004 |
came | +0.004 |
sisters | +0.004 |
Neg logit contributions | |
Here | -0.003 |
chard | -0.002 |
ours | -0.002 |
redd | -0.002 |
right | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
Here | +0.054 |
chard | +0.053 |
aman | +0.053 |
ours | +0.052 |
redd | +0.052 |
Neg logit contributions | |
friends | -0.013 |
. | -0.011 |
, | -0.010 |
marched | -0.009 |
came | -0.009 |
Token | only |
Token ID | 691 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
friends | +0.001 |
marched | +0.001 |
sisters | +0.001 |
marching | +0.001 |
brothers | +0.001 |
Neg logit contributions | |
Here | -0.003 |
chard | -0.003 |
ours | -0.003 |
redd | -0.003 |
right | -0.003 |
Token | works |
Token ID | 2499 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
chard | +0.034 |
Here | +0.034 |
rily | +0.032 |
ours | +0.032 |
redd | +0.031 |
Neg logit contributions | |
friends | -0.018 |
, | -0.017 |
marched | -0.016 |
came | -0.015 |
sisters | -0.015 |
Token | for |
Token ID | 329 |
Feature activation | -1.94e-03 |
Pos logit contributions | |
friends | +0.014 |
marched | +0.014 |
sisters | +0.013 |
family | +0.012 |
mo | +0.012 |
Neg logit contributions | |
ours | -0.037 |
Here | -0.037 |
right | -0.036 |
chard | -0.036 |
rily | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +2.06e-03 |
Pos logit contributions | |
Here | +0.004 |
chard | +0.004 |
ours | +0.004 |
redd | +0.004 |
right | +0.004 |
Neg logit contributions | |
friends | -0.003 |
marched | -0.002 |
, | -0.002 |
sisters | -0.002 |
brothers | -0.002 |
Token | few |
Token ID | 1178 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.002 |
, | +0.002 |
sisters | +0.002 |
came | +0.002 |
Neg logit contributions | |
Here | -0.004 |
chard | -0.004 |
ours | -0.004 |
redd | -0.004 |
right | -0.004 |
Token | seconds |
Token ID | 4201 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
marched | +0.012 |
marching | +0.011 |
friends | +0.011 |
sisters | +0.010 |
came | +0.010 |
Neg logit contributions | |
Here | -0.021 |
right | -0.021 |
ours | -0.020 |
chard | -0.020 |
redd | -0.020 |
Token | ! |
Token ID | 0 |
Feature activation | +9.11e-03 |
Pos logit contributions | |
friends | +0.028 |
marched | +0.025 |
sisters | +0.022 |
brothers | +0.021 |
came | +0.020 |
Neg logit contributions | |
Here | -0.088 |
chard | -0.086 |
ours | -0.086 |
right | -0.083 |
redd | -0.081 |
Token | You |
Token ID | 921 |
Feature activation | +3.18e-03 |
Pos logit contributions | |
friends | +0.014 |
marched | +0.013 |
brothers | +0.013 |
, | +0.012 |
sisters | +0.012 |
Neg logit contributions | |
chard | -0.016 |
ours | -0.015 |
redd | -0.015 |
Here | -0.014 |
rily | -0.014 |
Token | need |
Token ID | 761 |
Feature activation | -3.04e-03 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.004 |
sisters | +0.004 |
brothers | +0.004 |
marching | +0.004 |
Neg logit contributions | |
Here | -0.006 |
ours | -0.006 |
chard | -0.006 |
right | -0.006 |
redd | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -1.27e-03 |
Pos logit contributions | |
Here | +0.008 |
chard | +0.008 |
ours | +0.008 |
redd | +0.007 |
rily | +0.007 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.002 |
, | -0.002 |
came | -0.002 |
sisters | -0.002 |
Token | read |
Token ID | 1100 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
Here | +0.002 |
chard | +0.002 |
ours | +0.002 |
right | +0.002 |
redd | +0.002 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.001 |
sisters | -0.001 |
came | -0.001 |
brothers | -0.001 |
Token | then |
Token ID | 788 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
, | +0.005 |
. | +0.004 |
friends | +0.004 |
came | +0.004 |
and | +0.003 |
Neg logit contributions | |
Here | -0.012 |
ours | -0.011 |
redd | -0.011 |
rily | -0.011 |
chard | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
Here | +0.037 |
chard | +0.037 |
ours | +0.036 |
right | +0.035 |
curiously | +0.035 |
Neg logit contributions | |
friends | -0.006 |
marched | -0.006 |
sisters | -0.005 |
marching | -0.004 |
brothers | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +4.70e-03 |
Pos logit contributions | |
friends | +0.025 |
, | +0.024 |
came | +0.021 |
marched | +0.020 |
. | +0.019 |
Neg logit contributions | |
Here | -0.069 |
ours | -0.066 |
rily | -0.065 |
redd | -0.065 |
aman | -0.065 |
Token | cob |
Token ID | 22843 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
friends | +0.007 |
marched | +0.006 |
, | +0.006 |
sisters | +0.006 |
brothers | +0.006 |
Neg logit contributions | |
Here | -0.009 |
chard | -0.009 |
ours | -0.009 |
redd | -0.008 |
right | -0.008 |
Token | web |
Token ID | 12384 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
friends | +0.037 |
marched | +0.036 |
marching | +0.034 |
sisters | +0.034 |
brothers | +0.034 |
Neg logit contributions | |
Here | -0.027 |
chard | -0.026 |
right | -0.026 |
redd | -0.024 |
rily | -0.024 |
Token | went |
Token ID | 1816 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
friends | +0.020 |
sisters | +0.018 |
marched | +0.017 |
brothers | +0.017 |
marching | +0.017 |
Neg logit contributions | |
chard | -0.040 |
Here | -0.039 |
right | -0.038 |
redd | -0.037 |
ours | -0.037 |
Token | " |
Token ID | 366 |
Feature activation | -3.42e-03 |
Pos logit contributions | |
friends | +0.013 |
marched | +0.012 |
, | +0.011 |
came | +0.011 |
marching | +0.010 |
Neg logit contributions | |
Here | -0.026 |
chard | -0.025 |
ours | -0.024 |
redd | -0.024 |
right | -0.024 |
Token | snap |
Token ID | 45380 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
ours | +0.006 |
Here | +0.006 |
chard | +0.006 |
rily | +0.006 |
aman | +0.006 |
Neg logit contributions | |
marched | -0.005 |
came | -0.005 |
friends | -0.005 |
cl | -0.004 |
j | -0.004 |
Token | !" |
Token ID | 2474 |
Feature activation | +8.77e-03 |
Pos logit contributions | |
friends | +0.029 |
marched | +0.028 |
sisters | +0.026 |
family | +0.025 |
brothers | +0.025 |
Neg logit contributions | |
Here | -0.041 |
right | -0.039 |
ours | -0.039 |
chard | -0.039 |
redd | -0.037 |
Token | Tim |
Token ID | 5045 |
Feature activation | -3.67e-04 |
Pos logit contributions | |
, | +0.010 |
friends | +0.010 |
came | +0.009 |
. | +0.009 |
marched | +0.009 |
Neg logit contributions | |
ours | -0.019 |
chard | -0.019 |
Here | -0.018 |
redd | -0.018 |
aman | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | -9.70e-03 |
Pos logit contributions | |
Here | +0.001 |
chard | +0.001 |
right | +0.001 |
ours | +0.001 |
redd | +0.001 |
Neg logit contributions | |
friends | -0.000 |
marched | -0.000 |
sisters | -0.000 |
marching | -0.000 |
brothers | -0.000 |
Token | ily |
Token ID | 813 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
chard | +0.054 |
Here | +0.054 |
ours | +0.051 |
redd | +0.051 |
right | +0.049 |
Neg logit contributions | |
friends | -0.035 |
marched | -0.031 |
, | -0.031 |
came | -0.030 |
sisters | -0.030 |
Token | liked |
Token ID | 8288 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
friends | +0.025 |
sisters | +0.023 |
marching | +0.022 |
marched | +0.022 |
brothers | +0.022 |
Neg logit contributions | |
Here | -0.033 |
ours | -0.030 |
chard | -0.029 |
aman | -0.028 |
right | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -6.98e-03 |
Pos logit contributions | |
Here | +0.008 |
chard | +0.007 |
ours | +0.007 |
right | +0.007 |
redd | +0.007 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.002 |
, | -0.002 |
sisters | -0.002 |
brothers | -0.002 |
Token | imagine |
Token ID | 5967 |
Feature activation | -3.71e-03 |
Pos logit contributions | |
Here | +0.015 |
chard | +0.014 |
ours | +0.014 |
right | +0.013 |
redd | +0.013 |
Neg logit contributions | |
friends | -0.008 |
marched | -0.007 |
sisters | -0.007 |
brothers | -0.007 |
came | -0.007 |
Token | things |
Token ID | 1243 |
Feature activation | -5.43e-03 |
Pos logit contributions | |
Here | +0.010 |
chard | +0.009 |
ours | +0.009 |
right | +0.009 |
redd | +0.009 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.002 |
sisters | -0.002 |
came | -0.002 |
brothers | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e-03 |
Pos logit contributions | |
Here | +0.013 |
ours | +0.013 |
chard | +0.012 |
right | +0.012 |
finder | +0.012 |
Neg logit contributions | |
marched | -0.004 |
friends | -0.004 |
sisters | -0.003 |
mo | -0.003 |
brothers | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
chard | +0.002 |
ours | +0.002 |
rily | +0.002 |
aman | +0.002 |
ited | +0.002 |
Neg logit contributions | |
, | -0.002 |
friends | -0.001 |
. | -0.001 |
sisters | -0.001 |
marched | -0.001 |
Token | imagined |
Token ID | 15758 |
Feature activation | +3.88e-03 |
Pos logit contributions | |
friends | +0.015 |
sisters | +0.013 |
marching | +0.013 |
brothers | +0.013 |
helpers | +0.012 |
Neg logit contributions | |
chard | -0.028 |
Here | -0.028 |
right | -0.026 |
redd | -0.026 |
ours | -0.025 |
Token | she |
Token ID | 673 |
Feature activation | -9.77e-03 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.004 |
, | +0.004 |
came | +0.004 |
sisters | +0.004 |
Neg logit contributions | |
Here | -0.008 |
chard | -0.008 |
ours | -0.008 |
redd | -0.008 |
right | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +7.18e-03 |
Pos logit contributions | |
Here | +0.021 |
chard | +0.021 |
ours | +0.020 |
right | +0.020 |
redd | +0.019 |
Neg logit contributions | |
friends | -0.009 |
marched | -0.008 |
sisters | -0.008 |
marching | -0.008 |
brothers | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +4.05e-03 |
Pos logit contributions | |
marched | +0.008 |
friends | +0.008 |
sisters | +0.007 |
' | +0.007 |
marching | +0.007 |
Neg logit contributions | |
chard | -0.014 |
Here | -0.014 |
ours | -0.014 |
right | -0.013 |
redd | -0.013 |
Token | " |
Token ID | 366 |
Feature activation | +2.57e-03 |
Pos logit contributions | |
Here | +0.003 |
chard | +0.002 |
ours | +0.002 |
redd | +0.002 |
rily | +0.002 |
Neg logit contributions | |
marched | -0.003 |
brothers | -0.003 |
sisters | -0.003 |
friends | -0.003 |
rac | -0.003 |
Token | c |
Token ID | 66 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.003 |
came | +0.003 |
family | +0.003 |
cl | +0.002 |
Neg logit contributions | |
chard | -0.005 |
Here | -0.005 |
ours | -0.005 |
right | -0.005 |
rily | -0.005 |
Token | aw |
Token ID | 707 |
Feature activation | -1.38e-05 |
Pos logit contributions | |
friends | +0.013 |
marched | +0.012 |
marching | +0.012 |
sisters | +0.011 |
brothers | +0.011 |
Neg logit contributions | |
Here | -0.021 |
ours | -0.020 |
chard | -0.019 |
right | -0.019 |
redd | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -6.66e-03 |
Pos logit contributions | |
Here | +0.000 |
chard | +0.000 |
ours | +0.000 |
right | +0.000 |
redd | +0.000 |
Neg logit contributions | |
friends | -0.000 |
marched | -0.000 |
sisters | -0.000 |
brothers | -0.000 |
marching | -0.000 |
Token | c |
Token ID | 269 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
Here | +0.013 |
ours | +0.013 |
chard | +0.012 |
redd | +0.012 |
right | +0.011 |
Neg logit contributions | |
friends | -0.008 |
marched | -0.008 |
sisters | -0.007 |
came | -0.007 |
brothers | -0.007 |
Token | aw |
Token ID | 707 |
Feature activation | +2.16e-04 |
Pos logit contributions | |
friends | +0.039 |
marched | +0.036 |
, | +0.035 |
came | +0.034 |
brothers | +0.033 |
Neg logit contributions | |
Here | -0.044 |
chard | -0.044 |
ours | -0.042 |
right | -0.041 |
redd | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
friends | +0.000 |
marched | +0.000 |
sisters | +0.000 |
brothers | +0.000 |
family | +0.000 |
Neg logit contributions | |
Here | -0.001 |
chard | -0.001 |
ours | -0.001 |
aman | -0.001 |
right | -0.001 |
Token | c |
Token ID | 269 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
Here | +0.024 |
chard | +0.024 |
ours | +0.023 |
right | +0.023 |
redd | +0.023 |
Neg logit contributions | |
friends | -0.014 |
marched | -0.013 |
, | -0.012 |
sisters | -0.012 |
came | -0.012 |
Token | aw |
Token ID | 707 |
Feature activation | -3.97e-04 |
Pos logit contributions | |
friends | +0.037 |
marched | +0.034 |
, | +0.033 |
came | +0.033 |
brothers | +0.032 |
Neg logit contributions | |
Here | -0.039 |
chard | -0.039 |
ours | -0.037 |
right | -0.036 |
redd | -0.036 |
Token | ". |
Token ID | 1911 |
Feature activation | +6.79e-05 |
Pos logit contributions | |
Here | +0.001 |
chard | +0.001 |
ours | +0.001 |
aman | +0.001 |
rily | +0.001 |
Neg logit contributions | |
friends | -0.000 |
marched | -0.000 |
sisters | -0.000 |
brothers | -0.000 |
family | -0.000 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
friends | +0.000 |
marched | +0.000 |
, | +0.000 |
sisters | +0.000 |
came | +0.000 |
Neg logit contributions | |
Here | -0.000 |
chard | -0.000 |
ours | -0.000 |
redd | -0.000 |
right | -0.000 |
Token | simply |
Token ID | 2391 |
Feature activation | -7.48e-03 |
Pos logit contributions | |
chard | +0.006 |
Here | +0.006 |
right | +0.005 |
ours | +0.005 |
aman | +0.005 |
Neg logit contributions | |
friends | -0.003 |
sisters | -0.003 |
marching | -0.003 |
marched | -0.003 |
brothers | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | -8.88e-04 |
Pos logit contributions | |
Here | +0.015 |
chard | +0.015 |
right | +0.015 |
ours | +0.014 |
redd | +0.014 |
Neg logit contributions | |
friends | -0.008 |
marched | -0.007 |
sisters | -0.007 |
brothers | -0.007 |
marching | -0.007 |
Token | " |
Token ID | 366 |
Feature activation | -4.34e-03 |
Pos logit contributions | |
Here | +0.002 |
chard | +0.002 |
right | +0.002 |
rily | +0.002 |
ours | +0.002 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
sisters | -0.001 |
marching | -0.001 |
brothers | -0.001 |
Token | Oh |
Token ID | 5812 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
ours | +0.008 |
Here | +0.008 |
chard | +0.008 |
rily | +0.007 |
aly | +0.007 |
Neg logit contributions | |
friends | -0.006 |
marched | -0.006 |
came | -0.006 |
family | -0.005 |
cl | -0.005 |
Token | OK |
Token ID | 7477 |
Feature activation | +7.09e-03 |
Pos logit contributions | |
friends | +0.007 |
marched | +0.007 |
sisters | +0.006 |
marching | +0.005 |
brothers | +0.005 |
Neg logit contributions | |
Here | -0.027 |
ours | -0.026 |
chard | -0.026 |
right | -0.025 |
aman | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
marched | +0.005 |
friends | +0.004 |
mo | +0.004 |
marching | +0.004 |
spl | +0.004 |
Neg logit contributions | |
Here | -0.017 |
right | -0.016 |
chard | -0.016 |
ours | -0.016 |
aman | -0.016 |
Token | We |
Token ID | 775 |
Feature activation | -5.99e-03 |
Pos logit contributions | |
friends | +0.018 |
marched | +0.017 |
, | +0.017 |
brothers | +0.016 |
came | +0.016 |
Neg logit contributions | |
chard | -0.022 |
ours | -0.022 |
redd | -0.021 |
Here | -0.021 |
rily | -0.020 |
Token | can |
Token ID | 460 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
Here | +0.010 |
ours | +0.009 |
chard | +0.009 |
right | +0.009 |
redd | +0.009 |
Neg logit contributions | |
friends | -0.008 |
marched | -0.008 |
sisters | -0.008 |
marching | -0.008 |
brothers | -0.008 |
Token | remain |
Token ID | 3520 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
Here | +0.026 |
ours | +0.024 |
chard | +0.024 |
aman | +0.023 |
right | +0.023 |
Neg logit contributions | |
friends | -0.017 |
marched | -0.016 |
sisters | -0.016 |
came | -0.015 |
marching | -0.015 |
Token | here |
Token ID | 994 |
Feature activation | +5.29e-03 |
Pos logit contributions | |
marched | +0.017 |
came | +0.017 |
sisters | +0.015 |
se | +0.015 |
rac | +0.015 |
Neg logit contributions | |
ours | -0.025 |
chard | -0.023 |
Here | -0.023 |
afar | -0.022 |
rily | -0.022 |
Token | ." |
Token ID | 526 |
Feature activation | +5.35e-03 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.005 |
sisters | +0.005 |
came | +0.004 |
brothers | +0.004 |
Neg logit contributions | |
Here | -0.012 |
chard | -0.011 |
ours | -0.011 |
right | -0.011 |
redd | -0.011 |
Token | The |
Token ID | 383 |
Feature activation | -1.47e-03 |
Pos logit contributions | |
ours | +0.003 |
chard | +0.003 |
redd | +0.003 |
ited | +0.003 |
rily | +0.003 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.002 |
, | -0.002 |
came | -0.002 |
brothers | -0.002 |
Token | frog |
Token ID | 21264 |
Feature activation | -2.82e-03 |
Pos logit contributions | |
Here | +0.003 |
chard | +0.003 |
ours | +0.003 |
right | +0.003 |
redd | +0.003 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.001 |
sisters | -0.001 |
, | -0.001 |
brothers | -0.001 |
Token | started |
Token ID | 2067 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
chard | +0.005 |
ited | +0.005 |
curiously | +0.005 |
Here | +0.005 |
right | +0.005 |
Neg logit contributions | |
helpers | -0.003 |
sisters | -0.003 |
friends | -0.003 |
brothers | -0.002 |
marching | -0.002 |
Token | feeling |
Token ID | 4203 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
brothers | +0.012 |
friends | +0.012 |
sisters | +0.012 |
helpers | +0.011 |
marched | +0.011 |
Neg logit contributions | |
chard | -0.022 |
right | -0.021 |
curiously | -0.021 |
Here | -0.021 |
like | -0.020 |
Token | happy |
Token ID | 3772 |
Feature activation | -4.03e-03 |
Pos logit contributions | |
friends | +0.018 |
marched | +0.017 |
sisters | +0.017 |
helpers | +0.017 |
brothers | +0.016 |
Neg logit contributions | |
chard | -0.023 |
redd | -0.021 |
ours | -0.021 |
Here | -0.021 |
right | -0.020 |
Token | again |
Token ID | 757 |
Feature activation | +4.08e-03 |
Pos logit contributions | |
curiously | +0.007 |
chard | +0.007 |
Here | +0.007 |
rily | +0.007 |
ours | +0.007 |
Neg logit contributions | |
marched | -0.004 |
sisters | -0.004 |
brothers | -0.004 |
friends | -0.004 |
blast | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e-05 |
Pos logit contributions | |
marched | +0.003 |
friends | +0.003 |
sisters | +0.003 |
brothers | +0.003 |
helpers | +0.003 |
Neg logit contributions | |
chard | -0.009 |
right | -0.008 |
ours | -0.008 |
aman | -0.008 |
Here | -0.008 |
Token | He |
Token ID | 679 |
Feature activation | -4.11e-03 |
Pos logit contributions | |
friends | +0.000 |
marched | +0.000 |
, | +0.000 |
brothers | +0.000 |
came | +0.000 |
Neg logit contributions | |
ours | -0.000 |
chard | -0.000 |
Here | -0.000 |
redd | -0.000 |
right | -0.000 |
Token | hopped |
Token ID | 45230 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
chard | +0.008 |
Here | +0.007 |
ited | +0.007 |
redd | +0.007 |
ours | +0.007 |
Neg logit contributions | |
friends | -0.004 |
helpers | -0.004 |
sisters | -0.004 |
brothers | -0.004 |
siblings | -0.004 |
Token | into |
Token ID | 656 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
Here | +0.030 |
chard | +0.029 |
ours | +0.029 |
right | +0.028 |
redd | +0.028 |
Neg logit contributions | |
friends | -0.015 |
marched | -0.014 |
sisters | -0.013 |
brothers | -0.013 |
family | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +1.81e-03 |
Pos logit contributions | |
Here | +0.029 |
chard | +0.029 |
ours | +0.028 |
redd | +0.027 |
right | +0.027 |
Neg logit contributions | |
friends | -0.009 |
marched | -0.008 |
, | -0.007 |
sisters | -0.007 |
brothers | -0.007 |
Token | my |
Token ID | 1820 |
Feature activation | +2.02e-03 |
Pos logit contributions | |
Here | +0.019 |
chard | +0.018 |
ours | +0.018 |
redd | +0.017 |
right | +0.017 |
Neg logit contributions | |
friends | -0.020 |
marched | -0.019 |
, | -0.018 |
sisters | -0.018 |
came | -0.018 |
Token | couldn |
Token ID | 3521 |
Feature activation | -8.23e-03 |
Pos logit contributions | |
friends | +0.002 |
sisters | +0.002 |
marched | +0.002 |
marching | +0.002 |
helpers | +0.002 |
Neg logit contributions | |
Here | -0.004 |
chard | -0.004 |
ours | -0.004 |
aman | -0.004 |
rily | -0.004 |
Token | 't |
Token ID | 470 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
Here | +0.011 |
ours | +0.010 |
right | +0.010 |
chard | +0.010 |
lowest | +0.009 |
Neg logit contributions | |
friends | -0.015 |
sisters | -0.014 |
marched | -0.014 |
helpers | -0.014 |
explorers | -0.014 |
Token | wait |
Token ID | 4043 |
Feature activation | +2.82e-03 |
Pos logit contributions | |
chard | +0.020 |
Here | +0.019 |
ours | +0.018 |
right | +0.018 |
ited | +0.017 |
Neg logit contributions | |
friends | -0.032 |
sisters | -0.031 |
brothers | -0.031 |
marched | -0.030 |
helpers | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -5.39e-03 |
Pos logit contributions | |
brothers | +0.003 |
friends | +0.003 |
sisters | +0.003 |
marched | +0.003 |
siblings | +0.003 |
Neg logit contributions | |
ours | -0.005 |
Here | -0.005 |
right | -0.005 |
chard | -0.005 |
rily | -0.005 |
Token | show |
Token ID | 905 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
ours | +0.009 |
Here | +0.009 |
chard | +0.008 |
yours | +0.008 |
cris | +0.008 |
Neg logit contributions | |
sisters | -0.007 |
marched | -0.007 |
friends | -0.007 |
es | -0.006 |
helpers | -0.006 |
Token | his |
Token ID | 465 |
Feature activation | -2.43e-03 |
Pos logit contributions | |
Here | +0.034 |
ours | +0.034 |
chard | +0.034 |
rily | +0.032 |
redd | +0.032 |
Neg logit contributions | |
friends | -0.020 |
marched | -0.020 |
sisters | -0.018 |
came | -0.018 |
marching | -0.018 |
Token | mom |
Token ID | 1995 |
Feature activation | +9.45e-03 |
Pos logit contributions | |
ours | +0.005 |
chard | +0.004 |
redd | +0.004 |
Here | +0.004 |
rily | +0.004 |
Neg logit contributions | |
marched | -0.003 |
came | -0.003 |
Nic | -0.002 |
marching | -0.002 |
comes | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +9.87e-03 |
Pos logit contributions | |
friends | +0.008 |
, | +0.007 |
marched | +0.007 |
sisters | +0.006 |
brothers | +0.006 |
Neg logit contributions | |
Here | -0.023 |
chard | -0.023 |
ours | -0.022 |
redd | -0.022 |
right | -0.022 |
Token | fish |
Token ID | 5916 |
Feature activation | -8.32e-04 |
Pos logit contributions | |
marched | +0.013 |
friends | +0.012 |
sisters | +0.012 |
, | +0.011 |
came | +0.011 |
Neg logit contributions | |
ours | -0.018 |
redd | -0.018 |
Here | -0.017 |
chard | -0.017 |
right | -0.016 |
Token | they |
Token ID | 484 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
ours | +0.002 |
chard | +0.002 |
Here | +0.002 |
rily | +0.002 |
right | +0.002 |
Neg logit contributions | |
marched | -0.001 |
friends | -0.001 |
sisters | -0.001 |
brothers | -0.001 |
came | -0.001 |
Token | things |
Token ID | 1243 |
Feature activation | +3.78e-03 |
Pos logit contributions | |
marched | +0.002 |
friends | +0.002 |
sisters | +0.002 |
brothers | +0.002 |
came | +0.002 |
Neg logit contributions | |
Here | -0.003 |
ours | -0.003 |
right | -0.003 |
chard | -0.003 |
redd | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +2.76e-03 |
Pos logit contributions | |
friends | +0.003 |
sisters | +0.003 |
brothers | +0.003 |
siblings | +0.003 |
marched | +0.003 |
Neg logit contributions | |
ours | -0.008 |
chard | -0.008 |
Here | -0.008 |
right | -0.008 |
rily | -0.008 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.23e-03 |
Pos logit contributions | |
friends | +0.003 |
, | +0.003 |
marched | +0.003 |
brothers | +0.002 |
came | +0.002 |
Neg logit contributions | |
chard | -0.006 |
redd | -0.006 |
ours | -0.006 |
rily | -0.006 |
ited | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -2.46e-03 |
Pos logit contributions | |
chard | +0.003 |
Here | +0.003 |
right | +0.002 |
aman | +0.002 |
ours | +0.002 |
Neg logit contributions | |
friends | -0.001 |
sisters | -0.001 |
marched | -0.001 |
brothers | -0.001 |
marching | -0.001 |
Token | very |
Token ID | 845 |
Feature activation | -5.47e-03 |
Pos logit contributions | |
chard | +0.005 |
ours | +0.005 |
Here | +0.005 |
right | +0.004 |
redd | +0.004 |
Neg logit contributions | |
friends | -0.003 |
marched | -0.003 |
sisters | -0.003 |
brothers | -0.003 |
came | -0.003 |
Token | happy |
Token ID | 3772 |
Feature activation | -4.96e-03 |
Pos logit contributions | |
Here | +0.011 |
chard | +0.011 |
ours | +0.011 |
redd | +0.010 |
right | +0.010 |
Neg logit contributions | |
friends | -0.006 |
marched | -0.006 |
sisters | -0.006 |
came | -0.005 |
brothers | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
Here | +0.009 |
chard | +0.009 |
ours | +0.009 |
curiously | +0.009 |
rily | +0.009 |
Neg logit contributions | |
marched | -0.005 |
sisters | -0.005 |
friends | -0.004 |
brothers | -0.004 |
blast | -0.004 |
Token | be |
Token ID | 307 |
Feature activation | +8.17e-03 |
Pos logit contributions | |
Here | +0.024 |
chard | +0.022 |
curiously | +0.021 |
yours | +0.021 |
perfection | +0.021 |
Neg logit contributions | |
helpers | -0.026 |
brothers | -0.026 |
sisters | -0.026 |
twins | -0.024 |
siblings | -0.024 |
Token | at |
Token ID | 379 |
Feature activation | +2.90e-03 |
Pos logit contributions | |
comes | +0.009 |
marched | +0.009 |
imag | +0.009 |
Kids | +0.008 |
mo | +0.008 |
Neg logit contributions | |
chard | -0.014 |
ours | -0.014 |
rily | -0.012 |
yours | -0.012 |
pole | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.003 |
sisters | +0.002 |
brothers | +0.002 |
came | +0.002 |
Neg logit contributions | |
Here | -0.006 |
chard | -0.006 |
ours | -0.006 |
right | -0.006 |
redd | -0.006 |
Token | park |
Token ID | 3952 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
Here | +0.024 |
rily | +0.023 |
chard | +0.023 |
ours | +0.023 |
right | +0.022 |
Neg logit contributions | |
friends | -0.010 |
family | -0.008 |
, | -0.008 |
marching | -0.008 |
marched | -0.008 |
Token | then |
Token ID | 788 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
Here | +0.013 |
ours | +0.012 |
rily | +0.012 |
redd | +0.012 |
right | +0.012 |
Neg logit contributions | |
friends | -0.006 |
, | -0.005 |
marched | -0.005 |
came | -0.005 |
family | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
chard | +0.032 |
Here | +0.032 |
ours | +0.030 |
redd | +0.030 |
right | +0.030 |
Neg logit contributions | |
friends | -0.005 |
marched | -0.005 |
sisters | -0.004 |
marching | -0.004 |
brothers | -0.003 |
Token | he |
Token ID | 339 |
Feature activation | -3.23e-03 |
Pos logit contributions | |
friends | +0.023 |
, | +0.021 |
marched | +0.020 |
came | +0.019 |
family | +0.018 |
Neg logit contributions | |
Here | -0.054 |
ours | -0.052 |
right | -0.050 |
rily | -0.050 |
redd | -0.050 |
Token | noticed |
Token ID | 6810 |
Feature activation | +1.72e-04 |
Pos logit contributions | |
chard | +0.006 |
ited | +0.005 |
ours | +0.005 |
curiously | +0.005 |
redd | +0.005 |
Neg logit contributions | |
sisters | -0.004 |
friends | -0.004 |
helpers | -0.004 |
marching | -0.003 |
siblings | -0.003 |
Token | something |
Token ID | 1223 |
Feature activation | +1.82e-03 |
Pos logit contributions | |
friends | +0.000 |
marched | +0.000 |
, | +0.000 |
came | +0.000 |
brothers | +0.000 |
Neg logit contributions | |
Here | -0.000 |
ours | -0.000 |
chard | -0.000 |
redd | -0.000 |
right | -0.000 |
Token | in |
Token ID | 287 |
Feature activation | -2.07e-03 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.002 |
sisters | +0.002 |
brothers | +0.002 |
family | +0.002 |
Neg logit contributions | |
chard | -0.003 |
Here | -0.003 |
ours | -0.003 |
right | -0.003 |
redd | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +1.72e-05 |
Pos logit contributions | |
Here | +0.006 |
chard | +0.005 |
ours | +0.005 |
right | +0.005 |
rily | +0.005 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
, | -0.001 |
family | -0.001 |
brothers | -0.001 |
Token | distance |
Token ID | 5253 |
Feature activation | -5.65e-03 |
Pos logit contributions | |
friends | +0.000 |
marched | +0.000 |
sisters | +0.000 |
came | +0.000 |
, | +0.000 |
Neg logit contributions | |
chard | -0.000 |
Here | -0.000 |
ours | -0.000 |
redd | -0.000 |
right | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +7.11e-03 |
Pos logit contributions | |
Here | +0.017 |
chard | +0.017 |
ours | +0.017 |
redd | +0.016 |
right | +0.016 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
, | -0.001 |
came | -0.000 |
brothers | -0.000 |
Token | It |
Token ID | 632 |
Feature activation | -4.38e-03 |
Pos logit contributions | |
friends | +0.010 |
marched | +0.009 |
, | +0.009 |
came | +0.009 |
brothers | +0.009 |
Neg logit contributions | |
ours | -0.013 |
chard | -0.013 |
Here | -0.013 |
aman | -0.012 |
ited | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
chard | +0.008 |
redd | +0.008 |
curiously | +0.008 |
right | +0.008 |
Here | +0.007 |
Neg logit contributions | |
sisters | -0.005 |
friends | -0.005 |
helpers | -0.005 |
brothers | -0.005 |
siblings | -0.005 |
Token | liked |
Token ID | 8288 |
Feature activation | -2.97e-03 |
Pos logit contributions | |
Here | +0.004 |
chard | +0.004 |
ours | +0.004 |
right | +0.003 |
redd | +0.003 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.002 |
sisters | -0.002 |
brothers | -0.002 |
marching | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -1.40e-03 |
Pos logit contributions | |
Here | +0.007 |
chard | +0.007 |
ours | +0.007 |
redd | +0.006 |
right | +0.006 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.002 |
sisters | -0.002 |
came | -0.002 |
, | -0.002 |
Token | do |
Token ID | 466 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
Here | +0.003 |
chard | +0.003 |
ours | +0.002 |
right | +0.002 |
redd | +0.002 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.002 |
sisters | -0.002 |
brothers | -0.001 |
marching | -0.001 |
Token | fancy |
Token ID | 14996 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
marched | +0.015 |
friends | +0.015 |
sisters | +0.015 |
came | +0.014 |
brothers | +0.014 |
Neg logit contributions | |
Here | -0.018 |
ours | -0.018 |
chard | -0.018 |
right | -0.017 |
redd | -0.017 |
Token | things |
Token ID | 1243 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
Here | +0.022 |
ours | +0.022 |
ires | +0.020 |
redd | +0.020 |
curiously | +0.020 |
Neg logit contributions | |
marched | -0.022 |
came | -0.021 |
' | -0.020 |
sisters | -0.020 |
dis | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -3.12e-03 |
Pos logit contributions | |
ours | +0.028 |
chard | +0.028 |
Here | +0.027 |
right | +0.026 |
redd | +0.026 |
Neg logit contributions | |
marched | -0.012 |
sisters | -0.011 |
friends | -0.010 |
family | -0.009 |
brothers | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | -3.40e-04 |
Pos logit contributions | |
Here | +0.005 |
chard | +0.005 |
ours | +0.005 |
right | +0.005 |
redd | +0.005 |
Neg logit contributions | |
friends | -0.005 |
marched | -0.005 |
sisters | -0.004 |
, | -0.004 |
came | -0.004 |
Token | liked |
Token ID | 8288 |
Feature activation | -2.08e-04 |
Pos logit contributions | |
Here | +0.001 |
chard | +0.001 |
redd | +0.001 |
right | +0.001 |
ours | +0.001 |
Neg logit contributions | |
friends | -0.000 |
sisters | -0.000 |
helpers | -0.000 |
brothers | -0.000 |
marching | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | -1.65e-03 |
Pos logit contributions | |
Here | +0.000 |
chard | +0.000 |
ours | +0.000 |
redd | +0.000 |
right | +0.000 |
Neg logit contributions | |
friends | -0.000 |
marched | -0.000 |
sisters | -0.000 |
brothers | -0.000 |
came | -0.000 |
Token | dress |
Token ID | 6576 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
Here | +0.003 |
chard | +0.003 |
ours | +0.003 |
redd | +0.003 |
right | +0.003 |
Neg logit contributions | |
friends | -0.002 |
marched | -0.002 |
sisters | -0.002 |
brothers | -0.002 |
came | -0.002 |
Token | up |
Token ID | 510 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
Here | +0.021 |
chard | +0.021 |
right | +0.020 |
ours | +0.020 |
redd | +0.019 |
Neg logit contributions | |
friends | -0.017 |
, | -0.016 |
marched | -0.015 |
came | -0.014 |
. | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -6.15e-03 |
Pos logit contributions | |
friends | +0.012 |
marched | +0.011 |
sisters | +0.010 |
brothers | +0.010 |
family | +0.009 |
Neg logit contributions | |
chard | -0.033 |
Here | -0.032 |
ours | -0.031 |
right | -0.030 |
redd | -0.030 |
Token | listened |
Token ID | 16399 |
Feature activation | -1.14e-04 |
Pos logit contributions | |
Here | +0.014 |
ours | +0.014 |
chard | +0.014 |
right | +0.013 |
redd | +0.013 |
Neg logit contributions | |
friends | -0.006 |
marched | -0.005 |
, | -0.005 |
came | -0.005 |
sisters | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
Here | +0.000 |
chard | +0.000 |
ours | +0.000 |
redd | +0.000 |
right | +0.000 |
Neg logit contributions | |
friends | -0.000 |
marched | -0.000 |
, | -0.000 |
came | -0.000 |
sisters | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -9.05e-04 |
Pos logit contributions | |
Here | +0.037 |
chard | +0.037 |
ours | +0.036 |
redd | +0.036 |
right | +0.036 |
Neg logit contributions | |
friends | -0.010 |
, | -0.008 |
marched | -0.007 |
family | -0.007 |
came | -0.007 |
Token | bird |
Token ID | 6512 |
Feature activation | +9.41e-03 |
Pos logit contributions | |
Here | +0.002 |
chard | +0.002 |
ours | +0.002 |
right | +0.002 |
rily | +0.002 |
Neg logit contributions | |
friends | -0.001 |
family | -0.001 |
, | -0.001 |
marched | -0.001 |
brothers | -0.001 |
Token | 's |
Token ID | 338 |
Feature activation | -9.21e-03 |
Pos logit contributions | |
friends | +0.004 |
, | +0.002 |
marched | +0.002 |
. | +0.002 |
came | +0.001 |
Neg logit contributions | |
Here | -0.028 |
chard | -0.028 |
ours | -0.027 |
redd | -0.027 |
right | -0.026 |
Token | song |
Token ID | 3496 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
Here | +0.018 |
chard | +0.018 |
ours | +0.018 |
right | +0.017 |
redd | +0.017 |
Neg logit contributions | |
friends | -0.011 |
marched | -0.011 |
came | -0.010 |
sisters | -0.010 |
, | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -9.05e-04 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.004 |
sisters | +0.003 |
brothers | +0.003 |
marching | +0.003 |
Neg logit contributions | |
Here | -0.029 |
chard | -0.029 |
ours | -0.028 |
right | -0.028 |
rily | -0.028 |
Token | He |
Token ID | 679 |
Feature activation | -6.20e-03 |
Pos logit contributions | |
ours | +0.002 |
chard | +0.002 |
ited | +0.002 |
aman | +0.002 |
redd | +0.002 |
Neg logit contributions | |
friends | -0.001 |
, | -0.001 |
marched | -0.001 |
came | -0.001 |
. | -0.001 |
Token | thought |
Token ID | 1807 |
Feature activation | +5.26e-03 |
Pos logit contributions | |
chard | +0.014 |
Here | +0.013 |
ours | +0.013 |
redd | +0.013 |
right | +0.013 |
Neg logit contributions | |
friends | -0.006 |
marched | -0.005 |
sisters | -0.005 |
brothers | -0.005 |
marching | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
friends | +0.006 |
, | +0.005 |
marched | +0.005 |
came | +0.005 |
brothers | +0.005 |
Neg logit contributions | |
Here | -0.012 |
chard | -0.011 |
ours | -0.011 |
redd | -0.011 |
right | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +5.29e-03 |
Pos logit contributions | |
friends | +0.003 |
, | +0.003 |
came | +0.002 |
family | +0.002 |
marched | +0.002 |
Neg logit contributions | |
Here | -0.010 |
rily | -0.010 |
ours | -0.010 |
right | -0.010 |
chard | -0.009 |
Token | big |
Token ID | 1263 |
Feature activation | +1.77e-03 |
Pos logit contributions | |
friends | +0.006 |
, | +0.005 |
family | +0.005 |
came | +0.005 |
marched | +0.005 |
Neg logit contributions | |
Here | -0.012 |
ours | -0.012 |
right | -0.011 |
rily | -0.011 |
chard | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
friends | +0.002 |
marched | +0.002 |
sisters | +0.002 |
brothers | +0.002 |
marching | +0.002 |
Neg logit contributions | |
chard | -0.003 |
Here | -0.003 |
ours | -0.003 |
redd | -0.003 |
right | -0.003 |
Token | juicy |
Token ID | 35075 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
friends | +0.013 |
, | +0.013 |
j | +0.012 |
came | +0.012 |
marched | +0.012 |
Neg logit contributions | |
Here | -0.021 |
aman | -0.019 |
rily | -0.019 |
right | -0.019 |
ours | -0.018 |
Token | water |
Token ID | 1660 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
Here | +0.021 |
chard | +0.019 |
right | +0.018 |
ours | +0.018 |
rily | +0.017 |
Neg logit contributions | |
friends | -0.034 |
, | -0.032 |
came | -0.030 |
family | -0.030 |
marched | -0.029 |
Token | melon |
Token ID | 45690 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
chard | +0.027 |
Here | +0.027 |
ours | +0.026 |
redd | +0.025 |
right | +0.025 |
Neg logit contributions | |
friends | -0.018 |
marched | -0.017 |
sisters | -0.017 |
brothers | -0.016 |
family | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
chard | +0.138 |
Here | +0.136 |
ours | +0.135 |
redd | +0.131 |
rily | +0.130 |
Neg logit contributions | |
friends | -0.027 |
marched | -0.025 |
sisters | -0.021 |
brothers | -0.018 |
came | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
Here | +0.054 |
fy | +0.052 |
ours | +0.050 |
ited | +0.050 |
aly | +0.050 |
Neg logit contributions | |
, | -0.009 |
. | -0.008 |
friends | -0.007 |
p | -0.005 |
family | -0.004 |
Token | ground |
Token ID | 2323 |
Feature activation | -5.32e-03 |
Pos logit contributions | |
Here | +0.037 |
right | +0.035 |
ited | +0.034 |
ours | +0.033 |
chard | +0.033 |
Neg logit contributions | |
friends | -0.027 |
, | -0.025 |
family | -0.024 |
marched | -0.023 |
. | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e-03 |
Pos logit contributions | |
Here | +0.016 |
chard | +0.016 |
ours | +0.016 |
redd | +0.015 |
right | +0.015 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
, | -0.001 |
came | -0.000 |
sisters | -0.000 |
Token | She |
Token ID | 1375 |
Feature activation | +8.02e-03 |
Pos logit contributions | |
, | +0.002 |
friends | +0.002 |
came | +0.002 |
marched | +0.002 |
. | +0.002 |
Neg logit contributions | |
ours | -0.004 |
chard | -0.004 |
right | -0.004 |
ited | -0.004 |
rily | -0.004 |
Token | It |
Token ID | 632 |
Feature activation | -8.15e-03 |
Pos logit contributions | |
, | +0.007 |
friends | +0.007 |
marched | +0.006 |
came | +0.006 |
. | +0.006 |
Neg logit contributions | |
chard | -0.014 |
ited | -0.013 |
ours | -0.013 |
aman | -0.013 |
rily | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
chard | +0.018 |
Here | +0.018 |
redd | +0.018 |
ours | +0.018 |
right | +0.017 |
Neg logit contributions | |
friends | -0.007 |
sisters | -0.007 |
marched | -0.006 |
brothers | -0.006 |
marching | -0.006 |
Token | fixed |
Token ID | 5969 |
Feature activation | -6.85e-03 |
Pos logit contributions | |
Here | +0.049 |
chard | +0.047 |
ours | +0.045 |
right | +0.045 |
rily | +0.045 |
Neg logit contributions | |
friends | -0.023 |
marched | -0.021 |
, | -0.021 |
came | -0.019 |
brothers | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -7.67e-03 |
Pos logit contributions | |
Here | +0.018 |
chard | +0.018 |
ours | +0.018 |
redd | +0.017 |
right | +0.017 |
Neg logit contributions | |
friends | -0.004 |
marched | -0.003 |
, | -0.003 |
came | -0.003 |
brothers | -0.003 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
Here | +0.017 |
chard | +0.016 |
ours | +0.016 |
rily | +0.016 |
right | +0.016 |
Neg logit contributions | |
friends | -0.008 |
marched | -0.008 |
came | -0.007 |
, | -0.007 |
brothers | -0.007 |
Token | brand |
Token ID | 4508 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
Here | +0.027 |
chard | +0.026 |
aman | +0.025 |
right | +0.025 |
ours | +0.024 |
Neg logit contributions | |
friends | -0.014 |
, | -0.014 |
marched | -0.013 |
came | -0.012 |
. | -0.012 |
Token | new |
Token ID | 649 |
Feature activation | +9.02e-03 |
Pos logit contributions | |
chard | +0.093 |
Here | +0.091 |
ours | +0.089 |
right | +0.085 |
redd | +0.085 |
Neg logit contributions | |
friends | -0.061 |
, | -0.054 |
marched | -0.052 |
came | -0.050 |
brothers | -0.050 |
Token | ! |
Token ID | 0 |
Feature activation | +4.08e-03 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.004 |
sisters | +0.003 |
came | +0.003 |
brothers | +0.003 |
Neg logit contributions | |
Here | -0.024 |
chard | -0.024 |
ours | -0.024 |
right | -0.023 |
rily | -0.023 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
friends | +0.004 |
, | +0.004 |
came | +0.004 |
marched | +0.004 |
brothers | +0.004 |
Neg logit contributions | |
chard | -0.009 |
rily | -0.009 |
ited | -0.009 |
ours | -0.009 |
aman | -0.008 |
Token | my |
Token ID | 1820 |
Feature activation | +2.94e-03 |
Pos logit contributions | |
Here | +0.021 |
chard | +0.020 |
ours | +0.020 |
redd | +0.019 |
right | +0.019 |
Neg logit contributions | |
friends | -0.021 |
marched | -0.020 |
, | -0.019 |
sisters | -0.019 |
brothers | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -5.63e-03 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.002 |
sisters | +0.002 |
marching | +0.002 |
brothers | +0.002 |
Neg logit contributions | |
Here | -0.006 |
chard | -0.006 |
redd | -0.006 |
ours | -0.006 |
right | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -3.88e-03 |
Pos logit contributions | |
Here | +0.022 |
chard | +0.022 |
right | +0.021 |
rated | +0.021 |
mediately | +0.021 |
Neg logit contributions | |
friends | -0.004 |
, | -0.004 |
family | -0.003 |
. | -0.003 |
sisters | -0.002 |
Token | steak |
Token ID | 26320 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
Here | +0.006 |
chard | +0.005 |
right | +0.005 |
aman | +0.005 |
mediately | +0.005 |
Neg logit contributions | |
friends | -0.008 |
family | -0.007 |
, | -0.007 |
brothers | -0.007 |
. | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +4.54e-03 |
Pos logit contributions | |
chard | +0.017 |
Here | +0.017 |
ours | +0.017 |
right | +0.016 |
redd | +0.016 |
Neg logit contributions | |
friends | -0.003 |
marched | -0.003 |
sisters | -0.002 |
brothers | -0.002 |
marching | -0.002 |
Token | Jane |
Token ID | 12091 |
Feature activation | -1.14e-03 |
Pos logit contributions | |
friends | +0.007 |
, | +0.007 |
marched | +0.007 |
came | +0.006 |
sisters | +0.006 |
Neg logit contributions | |
chard | -0.008 |
ours | -0.007 |
Here | -0.007 |
redd | -0.007 |
right | -0.007 |
Token | said |
Token ID | 531 |
Feature activation | -5.72e-03 |
Pos logit contributions | |
Here | +0.003 |
ours | +0.003 |
chard | +0.003 |
redd | +0.003 |
right | +0.003 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
, | -0.001 |
came | -0.001 |
sisters | -0.001 |
Token | yes |
Token ID | 3763 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
Here | +0.010 |
chard | +0.010 |
ours | +0.010 |
redd | +0.009 |
right | +0.009 |
Neg logit contributions | |
friends | -0.008 |
marched | -0.008 |
sisters | -0.007 |
brothers | -0.007 |
, | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -6.49e-03 |
Pos logit contributions | |
Here | +0.120 |
chard | +0.117 |
ours | +0.117 |
right | +0.114 |
redd | +0.113 |
Neg logit contributions | |
friends | -0.016 |
marched | -0.013 |
sisters | -0.010 |
brothers | -0.009 |
marching | -0.008 |
Token | please |
Token ID | 3387 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
Here | +0.017 |
chard | +0.017 |
ours | +0.016 |
redd | +0.016 |
right | +0.016 |
Neg logit contributions | |
friends | -0.004 |
marched | -0.004 |
, | -0.004 |
came | -0.003 |
sisters | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | -4.84e-03 |
Pos logit contributions | |
Here | +0.037 |
chard | +0.036 |
ours | +0.035 |
right | +0.035 |
redd | +0.033 |
Neg logit contributions | |
friends | -0.010 |
marched | -0.009 |
sisters | -0.008 |
brothers | -0.008 |
marching | -0.008 |
Token | Grand |
Token ID | 5675 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
chard | +0.010 |
ours | +0.009 |
redd | +0.009 |
rily | +0.009 |
ited | +0.009 |
Neg logit contributions | |
friends | -0.006 |
, | -0.006 |
marched | -0.006 |
. | -0.006 |
came | -0.005 |
Token | ma |
Token ID | 2611 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
Here | +0.052 |
chard | +0.051 |
ours | +0.050 |
right | +0.049 |
redd | +0.048 |
Neg logit contributions | |
friends | -0.031 |
marched | -0.029 |
sisters | -0.027 |
, | -0.026 |
brothers | -0.026 |
Token | decided |
Token ID | 3066 |
Feature activation | -7.28e-03 |
Pos logit contributions | |
friends | +0.009 |
sisters | +0.008 |
brothers | +0.008 |
marching | +0.007 |
helpers | +0.007 |
Neg logit contributions | |
chard | -0.016 |
Here | -0.016 |
redd | -0.016 |
aman | -0.016 |
right | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -4.03e-05 |
Pos logit contributions | |
chard | +0.017 |
Here | +0.017 |
ours | +0.017 |
redd | +0.016 |
right | +0.016 |
Neg logit contributions | |
friends | -0.006 |
marched | -0.005 |
brothers | -0.005 |
sisters | -0.005 |
family | -0.005 |
Token | have |
Token ID | 423 |
Feature activation | +9.09e-03 |
Pos logit contributions | |
Here | +0.000 |
ours | +0.000 |
chard | +0.000 |
right | +0.000 |
redd | +0.000 |
Neg logit contributions | |
friends | -0.000 |
sisters | -0.000 |
brothers | -0.000 |
marched | -0.000 |
helpers | -0.000 |
Token | an |
Token ID | 281 |
Feature activation | +7.62e-03 |
Pos logit contributions | |
brothers | +0.013 |
marched | +0.013 |
sisters | +0.013 |
friends | +0.013 |
mo | +0.012 |
Neg logit contributions | |
ours | -0.014 |
chard | -0.014 |
Here | -0.014 |
redd | -0.013 |
right | -0.013 |
Token | adventure |
Token ID | 8855 |
Feature activation | +6.51e-03 |
Pos logit contributions | |
friends | +0.007 |
marched | +0.006 |
, | +0.006 |
family | +0.005 |
brothers | +0.005 |
Neg logit contributions | |
Here | -0.018 |
chard | -0.018 |
ours | -0.017 |
rily | -0.017 |
redd | -0.017 |
Token | outdoors |
Token ID | 24349 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
friends | +0.005 |
marched | +0.004 |
sisters | +0.004 |
brothers | +0.004 |
family | +0.003 |
Neg logit contributions | |
chard | -0.016 |
Here | -0.016 |
ours | -0.016 |
right | -0.015 |
redd | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -9.79e-04 |
Pos logit contributions | |
chard | +0.100 |
Here | +0.099 |
right | +0.096 |
ours | +0.096 |
aman | +0.093 |
Neg logit contributions | |
friends | -0.022 |
marched | -0.019 |
brothers | -0.017 |
sisters | -0.017 |
helpers | -0.014 |
Token | She |
Token ID | 1375 |
Feature activation | +9.22e-03 |
Pos logit contributions | |
chard | +0.002 |
ours | +0.002 |
Here | +0.002 |
rily | +0.002 |
right | +0.002 |
Neg logit contributions | |
friends | -0.001 |
marched | -0.001 |
, | -0.001 |
came | -0.001 |
family | -0.001 |
Token | walked |
Token ID | 6807 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
friends | +0.009 |
sisters | +0.009 |
brothers | +0.008 |
helpers | +0.008 |
siblings | +0.008 |
Neg logit contributions | |
chard | -0.018 |
Here | -0.017 |
redd | -0.017 |
right | -0.017 |
curiously | -0.017 |
Token | along |
Token ID | 1863 |
Feature activation | +1.11e-03 |
Pos logit contributions | |
friends | +0.012 |
marched | +0.011 |
, | +0.010 |
came | +0.010 |
sisters | +0.010 |
Neg logit contributions | |
Here | -0.030 |
chard | -0.029 |
ours | -0.029 |
redd | -0.028 |
right | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
friends | +0.001 |
marched | +0.001 |
sisters | +0.001 |
brothers | +0.001 |
came | +0.001 |
Neg logit contributions | |
Here | -0.003 |
chard | -0.003 |
ours | -0.003 |
right | -0.002 |
redd | -0.002 |
Token | there |
Token ID | 612 |
Feature activation | +5.99e-03 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.004 |
sisters | +0.003 |
brothers | +0.003 |
helpers | +0.002 |
Neg logit contributions | |
Here | -0.027 |
chard | -0.026 |
ours | -0.026 |
right | -0.026 |
aman | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | -7.65e-03 |
Pos logit contributions | |
friends | +0.004 |
marched | +0.004 |
sisters | +0.003 |
, | +0.003 |
brothers | +0.003 |
Neg logit contributions | |
Here | -0.015 |
chard | -0.015 |
ours | -0.014 |
right | -0.014 |
redd | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +8.86e-03 |
Pos logit contributions | |
Here | +0.021 |
chard | +0.021 |
rily | +0.020 |
aman | +0.020 |
ours | +0.020 |
Neg logit contributions | |
friends | -0.005 |
, | -0.004 |
. | -0.004 |
family | -0.003 |
j | -0.003 |
Token | clever |
Token ID | 14169 |
Feature activation | +6.35e-03 |
Pos logit contributions | |
friends | +0.011 |
marched | +0.011 |
, | +0.010 |
sisters | +0.010 |
came | +0.010 |
Neg logit contributions | |
Here | -0.017 |
chard | -0.017 |
ours | -0.016 |
right | -0.016 |
redd | -0.016 |
Token | boy |
Token ID | 2933 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
friends | +0.008 |
marched | +0.007 |
sisters | +0.007 |
came | +0.007 |
, | +0.007 |
Neg logit contributions | |
Here | -0.012 |
chard | -0.012 |
ours | -0.012 |
redd | -0.011 |
right | -0.011 |
Token | named |
Token ID | 3706 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
Here | +0.031 |
chard | +0.031 |
right | +0.030 |
ours | +0.028 |
redd | +0.027 |
Neg logit contributions | |
friends | -0.015 |
marched | -0.014 |
sisters | -0.014 |
helpers | -0.012 |
brothers | -0.012 |
Token | Tom |
Token ID | 4186 |
Feature activation | +5.95e-03 |
Pos logit contributions | |
rily | +0.084 |
chard | +0.083 |
Here | +0.082 |
aman | +0.081 |
ited | +0.081 |
Neg logit contributions | |
friends | -0.041 |
, | -0.040 |
marched | -0.036 |
. | -0.036 |
came | -0.035 |
Token | who |
Token ID | 508 |
Feature activation | +7.08e-03 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.003 |
sisters | +0.002 |
marching | +0.002 |
brothers | +0.002 |
Neg logit contributions | |
Here | -0.016 |
chard | -0.015 |
ours | -0.015 |
right | -0.015 |
redd | -0.014 |
Token | wanted |
Token ID | 2227 |
Feature activation | +4.22e-03 |
Pos logit contributions | |
friends | +0.010 |
sisters | +0.010 |
marched | +0.010 |
marching | +0.009 |
helpers | +0.009 |
Neg logit contributions | |
Here | -0.012 |
chard | -0.011 |
redd | -0.011 |
right | -0.011 |
ours | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +1.18e-03 |
Pos logit contributions | |
friends | +0.003 |
marched | +0.003 |
sisters | +0.003 |
brothers | +0.003 |
came | +0.003 |
Neg logit contributions | |
Here | -0.010 |
chard | -0.010 |
ours | -0.010 |
right | -0.010 |
redd | -0.010 |
Token | explore |
Token ID | 7301 |
Feature activation | +3.42e-03 |
Pos logit contributions | |
friends | +0.001 |
marched | +0.001 |
sisters | +0.001 |
came | +0.001 |
marching | +0.001 |
Neg logit contributions | |
Here | -0.002 |
chard | -0.002 |
ours | -0.002 |
right | -0.002 |
redd | -0.002 |