Token | to |
Token ID | 284 |
Feature activation | -8.76e-03 |
Pos logit contributions | |
above | +0.007 |
ary | +0.007 |
overed | +0.006 |
below | +0.006 |
: | +0.006 |
Neg logit contributions | |
handed | -0.010 |
cash | -0.009 |
cand | -0.009 |
moderation | -0.009 |
dishes | -0.008 |
Token | play |
Token ID | 711 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
handed | +0.015 |
cash | +0.014 |
cand | +0.014 |
moderation | +0.013 |
handful | +0.013 |
Neg logit contributions | |
above | -0.011 |
ary | -0.011 |
: | -0.010 |
behold | -0.010 |
below | -0.010 |
Token | outside |
Token ID | 2354 |
Feature activation | +6.80e-03 |
Pos logit contributions | |
above | +0.021 |
ary | +0.020 |
overed | +0.019 |
below | +0.019 |
: | +0.017 |
Neg logit contributions | |
handed | -0.036 |
cash | -0.034 |
cand | -0.034 |
moderation | -0.032 |
dishes | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -1.74e-03 |
Pos logit contributions | |
above | +0.007 |
ary | +0.007 |
overed | +0.006 |
below | +0.006 |
behold | +0.006 |
Neg logit contributions | |
handed | -0.013 |
cash | -0.013 |
cand | -0.013 |
moderation | -0.012 |
dishes | -0.012 |
Token | pick |
Token ID | 2298 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
handed | +0.003 |
cash | +0.003 |
cand | +0.002 |
moderation | +0.002 |
dishes | +0.002 |
Neg logit contributions | |
above | -0.003 |
ary | -0.003 |
below | -0.002 |
overed | -0.002 |
behold | -0.002 |
Token | l |
Token ID | 300 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
above | +0.015 |
below | +0.014 |
: | +0.013 |
over | +0.013 |
overed | +0.013 |
Neg logit contributions | |
handed | -0.018 |
cash | -0.017 |
moderation | -0.017 |
lest | -0.016 |
cand | -0.015 |
Token | imes |
Token ID | 999 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
brewing | +0.153 |
above | +0.148 |
behold | +0.146 |
lights | +0.137 |
ths | +0.133 |
Neg logit contributions | |
cand | -0.104 |
handed | -0.101 |
penn | -0.095 |
These | -0.094 |
moderation | -0.093 |
Token | from |
Token ID | 422 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
above | +0.055 |
ary | +0.052 |
overed | +0.049 |
below | +0.049 |
behold | +0.046 |
Neg logit contributions | |
handed | -0.087 |
cash | -0.084 |
cand | -0.083 |
moderation | -0.079 |
dishes | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
overed | +0.091 |
ary | +0.089 |
above | +0.087 |
brewing | +0.083 |
ols | +0.083 |
Neg logit contributions | |
cash | -0.058 |
handed | -0.055 |
cand | -0.055 |
toy | -0.051 |
moderation | -0.050 |
Token | tree |
Token ID | 5509 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
above | +0.030 |
ary | +0.029 |
overed | +0.029 |
below | +0.028 |
behold | +0.027 |
Neg logit contributions | |
handed | -0.021 |
cash | -0.020 |
cand | -0.020 |
moderation | -0.018 |
dishes | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | -3.31e-03 |
Pos logit contributions | |
above | +0.014 |
ary | +0.013 |
overed | +0.013 |
below | +0.012 |
behold | +0.012 |
Neg logit contributions | |
handed | -0.023 |
cash | -0.022 |
cand | -0.022 |
moderation | -0.021 |
dishes | -0.020 |
Token | permit |
Token ID | 8749 |
Feature activation | -4.15e-03 |
Pos logit contributions | |
above | +0.017 |
ary | +0.016 |
overed | +0.015 |
below | +0.015 |
behold | +0.014 |
Neg logit contributions | |
handed | -0.016 |
cash | -0.015 |
cand | -0.015 |
moderation | -0.014 |
dishes | -0.013 |
Token | you |
Token ID | 345 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
handed | +0.005 |
cash | +0.005 |
cand | +0.005 |
moderation | +0.005 |
handful | +0.005 |
Neg logit contributions | |
above | -0.007 |
ary | -0.007 |
below | -0.006 |
: | -0.006 |
overed | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +9.33e-03 |
Pos logit contributions | |
above | +0.020 |
overed | +0.019 |
ary | +0.019 |
below | +0.019 |
behold | +0.018 |
Neg logit contributions | |
handed | -0.025 |
cash | -0.024 |
cand | -0.023 |
moderation | -0.022 |
dishes | -0.022 |
Token | pick |
Token ID | 2298 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
overed | +0.015 |
above | +0.015 |
ary | +0.014 |
below | +0.014 |
ols | +0.013 |
Neg logit contributions | |
handed | -0.013 |
cash | -0.012 |
cand | -0.012 |
moderation | -0.011 |
dishes | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
above | +0.015 |
over | +0.014 |
below | +0.013 |
around | +0.013 |
: | +0.013 |
Neg logit contributions | |
handed | -0.017 |
cash | -0.016 |
lest | -0.015 |
moderation | -0.015 |
cand | -0.015 |
Token | l |
Token ID | 300 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
above | +0.050 |
ary | +0.048 |
below | +0.047 |
overed | +0.046 |
: | +0.045 |
Neg logit contributions | |
handed | -0.029 |
cash | -0.026 |
cand | -0.026 |
moderation | -0.024 |
dishes | -0.022 |
Token | ily |
Token ID | 813 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
above | +0.145 |
brewing | +0.138 |
lights | +0.134 |
behold | +0.133 |
ols | +0.131 |
Neg logit contributions | |
handed | -0.105 |
cash | -0.098 |
cand | -0.098 |
moderation | -0.091 |
handful | -0.091 |
Token | if |
Token ID | 611 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
above | +0.043 |
ary | +0.041 |
overed | +0.039 |
below | +0.039 |
behold | +0.037 |
Neg logit contributions | |
handed | -0.047 |
cash | -0.045 |
cand | -0.044 |
moderation | -0.042 |
dishes | -0.041 |
Token | you |
Token ID | 345 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
above | +0.023 |
ary | +0.022 |
overed | +0.021 |
below | +0.021 |
: | +0.021 |
Neg logit contributions | |
handed | -0.017 |
cash | -0.016 |
cand | -0.016 |
moderation | -0.014 |
handful | -0.014 |
Token | go |
Token ID | 467 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
overed | +0.027 |
lights | +0.027 |
above | +0.026 |
brewing | +0.025 |
ols | +0.025 |
Neg logit contributions | |
handed | -0.014 |
money | -0.013 |
cand | -0.013 |
cash | -0.013 |
moderation | -0.013 |
Token | outside |
Token ID | 2354 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
above | +0.015 |
ary | +0.014 |
overed | +0.014 |
behold | +0.013 |
below | +0.013 |
Neg logit contributions | |
handed | -0.019 |
cash | -0.018 |
cand | -0.017 |
moderation | -0.017 |
dishes | -0.016 |
Token | Jack |
Token ID | 3619 |
Feature activation | -6.61e-03 |
Pos logit contributions | |
handed | +0.024 |
cash | +0.023 |
cand | +0.023 |
moderation | +0.021 |
dishes | +0.021 |
Neg logit contributions | |
above | -0.023 |
ary | -0.022 |
overed | -0.021 |
below | -0.020 |
ols | -0.020 |
Token | if |
Token ID | 611 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
handed | +0.011 |
cash | +0.011 |
cand | +0.011 |
moderation | +0.010 |
dishes | +0.010 |
Neg logit contributions | |
above | -0.009 |
ary | -0.008 |
: | -0.008 |
below | -0.008 |
over | -0.008 |
Token | they |
Token ID | 484 |
Feature activation | +7.37e-03 |
Pos logit contributions | |
above | +0.023 |
ary | +0.022 |
below | +0.022 |
: | +0.021 |
overed | +0.021 |
Neg logit contributions | |
handed | -0.015 |
cash | -0.014 |
cand | -0.014 |
moderation | -0.013 |
handful | -0.012 |
Token | could |
Token ID | 714 |
Feature activation | +9.39e-03 |
Pos logit contributions | |
overed | +0.009 |
above | +0.009 |
brewing | +0.008 |
ols | +0.008 |
ores | +0.008 |
Neg logit contributions | |
cand | -0.013 |
handed | -0.012 |
cash | -0.012 |
candy | -0.012 |
toy | -0.012 |
Token | buy |
Token ID | 2822 |
Feature activation | -2.62e-03 |
Pos logit contributions | |
overed | +0.018 |
above | +0.018 |
ary | +0.017 |
below | +0.017 |
brewing | +0.017 |
Neg logit contributions | |
handed | -0.010 |
cash | -0.009 |
cand | -0.009 |
moderation | -0.008 |
candy | -0.008 |
Token | l |
Token ID | 300 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
handed | +0.004 |
cash | +0.004 |
lest | +0.004 |
moderation | +0.004 |
cand | +0.004 |
Neg logit contributions | |
above | -0.004 |
ary | -0.003 |
: | -0.003 |
below | -0.003 |
over | -0.003 |
Token | oll |
Token ID | 692 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
above | +0.141 |
brewing | +0.130 |
ary | +0.129 |
overed | +0.128 |
behold | +0.128 |
Neg logit contributions | |
handed | -0.108 |
cand | -0.105 |
cash | -0.103 |
moderation | -0.095 |
handful | -0.094 |
Token | ip |
Token ID | 541 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
: | +0.054 |
ary | +0.054 |
above | +0.054 |
overed | +0.050 |
ores | +0.048 |
Neg logit contributions | |
handed | -0.062 |
cash | -0.055 |
moderation | -0.052 |
redd | -0.049 |
Those | -0.049 |
Token | ops |
Token ID | 2840 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
above | +0.026 |
ary | +0.026 |
: | +0.024 |
overed | +0.024 |
below | +0.023 |
Neg logit contributions | |
handed | -0.025 |
cash | -0.022 |
moderation | -0.022 |
cand | -0.022 |
redd | -0.021 |
Token | for |
Token ID | 329 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
above | +0.024 |
ary | +0.023 |
below | +0.021 |
: | +0.021 |
overed | +0.020 |
Neg logit contributions | |
handed | -0.047 |
cash | -0.045 |
cand | -0.043 |
moderation | -0.043 |
dishes | -0.041 |
Token | them |
Token ID | 606 |
Feature activation | -2.32e-03 |
Pos logit contributions | |
above | +0.028 |
ary | +0.027 |
overed | +0.026 |
below | +0.025 |
: | +0.025 |
Neg logit contributions | |
handed | -0.031 |
cash | -0.029 |
cand | -0.029 |
moderation | -0.027 |
dishes | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +8.65e-03 |
Pos logit contributions | |
handed | +0.012 |
cash | +0.012 |
cand | +0.012 |
moderation | +0.011 |
toy | +0.011 |
Neg logit contributions | |
above | -0.008 |
ary | -0.008 |
overed | -0.008 |
below | -0.007 |
ols | -0.007 |
Token | She |
Token ID | 1375 |
Feature activation | +8.98e-03 |
Pos logit contributions | |
above | +0.015 |
ary | +0.014 |
overed | +0.014 |
below | +0.014 |
: | +0.013 |
Neg logit contributions | |
handed | -0.011 |
cash | -0.011 |
cand | -0.010 |
moderation | -0.010 |
dishes | -0.009 |
Token | carefully |
Token ID | 7773 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
above | +0.013 |
ols | +0.013 |
ary | +0.013 |
overed | +0.013 |
below | +0.012 |
Neg logit contributions | |
handed | -0.013 |
cash | -0.013 |
cand | -0.012 |
toy | -0.012 |
handful | -0.012 |
Token | placed |
Token ID | 4624 |
Feature activation | +5.39e-03 |
Pos logit contributions | |
above | +0.020 |
ary | +0.019 |
below | +0.018 |
overed | +0.017 |
: | +0.017 |
Neg logit contributions | |
handed | -0.029 |
cash | -0.027 |
cand | -0.027 |
moderation | -0.026 |
dishes | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
above | +0.008 |
ary | +0.007 |
below | +0.007 |
overed | +0.007 |
behold | +0.007 |
Neg logit contributions | |
handed | -0.009 |
cash | -0.008 |
cand | -0.008 |
moderation | -0.008 |
dishes | -0.007 |
Token | l |
Token ID | 300 |
Feature activation | +8.26e-02 |
Pos logit contributions | |
above | +0.053 |
ary | +0.050 |
below | +0.048 |
overed | +0.047 |
: | +0.046 |
Neg logit contributions | |
handed | -0.034 |
cash | -0.029 |
cand | -0.028 |
moderation | -0.027 |
lest | -0.025 |
Token | imes |
Token ID | 999 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
above | +0.130 |
behold | +0.116 |
ary | +0.114 |
below | +0.114 |
brewing | +0.113 |
Neg logit contributions | |
handed | -0.120 |
cash | -0.111 |
cand | -0.109 |
handful | -0.103 |
moderation | -0.102 |
Token | in |
Token ID | 287 |
Feature activation | -2.02e-04 |
Pos logit contributions | |
above | +0.044 |
ary | +0.039 |
below | +0.038 |
overed | +0.037 |
: | +0.034 |
Neg logit contributions | |
handed | -0.092 |
cash | -0.090 |
cand | -0.088 |
moderation | -0.085 |
dishes | -0.082 |
Token | an |
Token ID | 281 |
Feature activation | -1.48e-03 |
Pos logit contributions | |
handed | +0.000 |
cash | +0.000 |
cand | +0.000 |
lest | +0.000 |
dishes | +0.000 |
Neg logit contributions | |
above | -0.000 |
ary | -0.000 |
below | -0.000 |
: | -0.000 |
behold | -0.000 |
Token | open |
Token ID | 1280 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
handed | +0.002 |
cash | +0.002 |
cand | +0.002 |
moderation | +0.002 |
dishes | +0.002 |
Neg logit contributions | |
above | -0.002 |
ary | -0.002 |
overed | -0.002 |
below | -0.002 |
ols | -0.002 |
Token | space |
Token ID | 2272 |
Feature activation | +4.34e-03 |
Pos logit contributions | |
above | +0.031 |
ary | +0.029 |
below | +0.029 |
overed | +0.028 |
: | +0.027 |
Neg logit contributions | |
handed | -0.024 |
cash | -0.022 |
cand | -0.022 |
moderation | -0.020 |
dishes | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -8.35e-03 |
Pos logit contributions | |
handed | +0.008 |
cand | +0.008 |
cash | +0.008 |
lest | +0.007 |
redd | +0.007 |
Neg logit contributions | |
above | -0.006 |
ary | -0.006 |
below | -0.006 |
: | -0.005 |
behold | -0.005 |
Token | barn |
Token ID | 25203 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
lest | +0.013 |
handed | +0.013 |
cand | +0.012 |
cash | +0.011 |
Those | +0.011 |
Neg logit contributions | |
above | -0.012 |
below | -0.011 |
: | -0.010 |
over | -0.010 |
ary | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -9.17e-03 |
Pos logit contributions | |
handed | +0.037 |
cash | +0.036 |
cand | +0.036 |
moderation | +0.034 |
dishes | +0.033 |
Neg logit contributions | |
above | -0.023 |
ary | -0.022 |
overed | -0.021 |
below | -0.020 |
behold | -0.019 |
Token | how |
Token ID | 703 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
handed | +0.014 |
cash | +0.014 |
cand | +0.014 |
moderation | +0.013 |
dishes | +0.012 |
Neg logit contributions | |
above | -0.013 |
ary | -0.012 |
overed | -0.012 |
below | -0.012 |
behold | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
above | +0.037 |
ary | +0.036 |
overed | +0.035 |
below | +0.035 |
: | +0.034 |
Neg logit contributions | |
handed | -0.020 |
cash | -0.019 |
cand | -0.019 |
moderation | -0.017 |
dishes | -0.016 |
Token | l |
Token ID | 300 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
above | +0.028 |
overed | +0.028 |
ary | +0.027 |
ols | +0.026 |
below | +0.026 |
Neg logit contributions | |
handed | -0.026 |
cand | -0.025 |
cash | -0.025 |
candy | -0.023 |
toy | -0.023 |
Token | icked |
Token ID | 9484 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
above | +0.082 |
ary | +0.073 |
behold | +0.069 |
below | +0.069 |
overed | +0.067 |
Neg logit contributions | |
handed | -0.169 |
cand | -0.158 |
cash | -0.156 |
moderation | -0.150 |
handful | -0.146 |
Token | her |
Token ID | 607 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
above | +0.027 |
ary | +0.025 |
below | +0.024 |
: | +0.024 |
over | +0.023 |
Neg logit contributions | |
handed | -0.027 |
cash | -0.025 |
cand | -0.025 |
moderation | -0.023 |
redd | -0.022 |
Token | hand |
Token ID | 1021 |
Feature activation | +3.42e-04 |
Pos logit contributions | |
above | +0.018 |
ary | +0.017 |
below | +0.016 |
: | +0.016 |
overed | +0.016 |
Neg logit contributions | |
handed | -0.017 |
cash | -0.016 |
cand | -0.015 |
moderation | -0.015 |
These | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +5.12e-03 |
Pos logit contributions | |
above | +0.000 |
ary | +0.000 |
below | +0.000 |
: | +0.000 |
overed | +0.000 |
Neg logit contributions | |
handed | -0.001 |
cash | -0.001 |
cand | -0.001 |
moderation | -0.001 |
dishes | -0.001 |
Token | Max |
Token ID | 5436 |
Feature activation | +6.21e-04 |
Pos logit contributions | |
above | +0.009 |
ary | +0.008 |
overed | +0.008 |
below | +0.008 |
behold | +0.008 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.006 |
cand | -0.006 |
moderation | -0.006 |
dishes | -0.005 |
Token | as |
Token ID | 355 |
Feature activation | +6.15e-03 |
Pos logit contributions | |
handed | +0.019 |
cash | +0.018 |
cand | +0.018 |
moderation | +0.017 |
dishes | +0.016 |
Neg logit contributions | |
above | -0.013 |
ary | -0.012 |
below | -0.011 |
overed | -0.011 |
: | -0.011 |
Token | his |
Token ID | 465 |
Feature activation | +6.32e-03 |
Pos logit contributions | |
above | +0.012 |
ary | +0.012 |
overed | +0.011 |
below | +0.011 |
: | +0.011 |
Neg logit contributions | |
handed | -0.006 |
cash | -0.006 |
cand | -0.006 |
moderation | -0.005 |
dishes | -0.005 |
Token | mum |
Token ID | 25682 |
Feature activation | +3.49e-03 |
Pos logit contributions | |
above | +0.011 |
ary | +0.011 |
ols | +0.010 |
overed | +0.010 |
below | +0.010 |
Neg logit contributions | |
handed | -0.008 |
cash | -0.008 |
cand | -0.008 |
dishes | -0.007 |
toy | -0.007 |
Token | opened |
Token ID | 4721 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
above | +0.005 |
overed | +0.005 |
ary | +0.005 |
below | +0.005 |
ols | +0.005 |
Neg logit contributions | |
handed | -0.005 |
cash | -0.005 |
cand | -0.005 |
toy | -0.004 |
handful | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
above | +0.017 |
below | +0.015 |
ary | +0.015 |
overed | +0.015 |
: | +0.014 |
Neg logit contributions | |
handed | -0.018 |
cand | -0.017 |
cash | -0.016 |
moderation | -0.016 |
lest | -0.015 |
Token | l |
Token ID | 300 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
above | +0.045 |
ary | +0.044 |
overed | +0.042 |
below | +0.041 |
behold | +0.040 |
Neg logit contributions | |
handed | -0.048 |
cash | -0.046 |
cand | -0.045 |
moderation | -0.042 |
dishes | -0.042 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.00e-03 |
Pos logit contributions | |
above | +0.123 |
behold | +0.112 |
ary | +0.109 |
below | +0.109 |
brewing | +0.109 |
Neg logit contributions | |
handed | -0.124 |
cash | -0.110 |
cand | -0.110 |
moderation | -0.108 |
handful | -0.104 |
Token | Dave |
Token ID | 27984 |
Feature activation | -3.44e-03 |
Pos logit contributions | |
ary | +0.011 |
above | +0.011 |
overed | +0.011 |
behold | +0.010 |
ols | +0.010 |
Neg logit contributions | |
handed | -0.007 |
Those | -0.006 |
These | -0.006 |
moderation | -0.006 |
cand | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
handed | +0.006 |
cash | +0.006 |
cand | +0.006 |
moderation | +0.006 |
dishes | +0.005 |
Neg logit contributions | |
above | -0.004 |
ary | -0.004 |
below | -0.004 |
: | -0.004 |
overed | -0.004 |
Token | Amy |
Token ID | 14235 |
Feature activation | -3.38e-03 |
Pos logit contributions | |
handed | +0.027 |
cash | +0.026 |
cand | +0.026 |
moderation | +0.023 |
dishes | +0.023 |
Neg logit contributions | |
above | -0.038 |
ary | -0.036 |
below | -0.035 |
behold | -0.034 |
: | -0.034 |
Token | were |
Token ID | 547 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
handed | +0.005 |
cand | +0.005 |
cash | +0.005 |
toy | +0.004 |
moderation | +0.004 |
Neg logit contributions | |
overed | -0.005 |
above | -0.005 |
ary | -0.005 |
brewing | -0.004 |
ores | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +2.65e-03 |
Pos logit contributions | |
ary | +0.033 |
above | +0.032 |
behold | +0.032 |
overed | +0.031 |
ols | +0.030 |
Neg logit contributions | |
handed | -0.042 |
cash | -0.041 |
cand | -0.040 |
toy | -0.037 |
dishes | -0.037 |
Token | eat |
Token ID | 4483 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
above | +0.005 |
ary | +0.004 |
below | +0.004 |
behold | +0.004 |
: | +0.004 |
Neg logit contributions | |
handed | -0.003 |
cand | -0.003 |
cash | -0.003 |
moderation | -0.003 |
lest | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
above | +0.020 |
below | +0.018 |
: | +0.018 |
ary | +0.017 |
ores | +0.017 |
Neg logit contributions | |
handed | -0.018 |
cash | -0.016 |
cand | -0.015 |
lest | -0.015 |
moderation | -0.015 |
Token | Max |
Token ID | 5436 |
Feature activation | -4.50e-03 |
Pos logit contributions | |
above | +0.017 |
ary | +0.016 |
below | +0.015 |
overed | +0.015 |
behold | +0.015 |
Neg logit contributions | |
handed | -0.017 |
cash | -0.016 |
cand | -0.016 |
moderation | -0.015 |
dishes | -0.014 |
Token | sat |
Token ID | 3332 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
handed | +0.007 |
cash | +0.007 |
cand | +0.007 |
moderation | +0.006 |
dishes | +0.006 |
Neg logit contributions | |
above | -0.006 |
ary | -0.006 |
overed | -0.006 |
below | -0.006 |
: | -0.006 |
Token | l |
Token ID | 300 |
Feature activation | +8.11e-02 |
Pos logit contributions | |
ary | +0.031 |
above | +0.029 |
behold | +0.028 |
ols | +0.027 |
overed | +0.027 |
Neg logit contributions | |
handed | -0.032 |
cash | -0.030 |
cand | -0.029 |
moderation | -0.028 |
dishes | -0.028 |
Token | oy |
Token ID | 726 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
above | +0.130 |
ary | +0.120 |
behold | +0.120 |
below | +0.116 |
brewing | +0.115 |
Neg logit contributions | |
handed | -0.120 |
cash | -0.109 |
cand | -0.107 |
handful | -0.098 |
moderation | -0.097 |
Token | ally |
Token ID | 453 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
above | +0.028 |
ary | +0.027 |
overed | +0.027 |
behold | +0.026 |
below | +0.026 |
Neg logit contributions | |
handed | -0.035 |
cash | -0.033 |
cand | -0.033 |
dishes | -0.031 |
moderation | -0.030 |
Token | by |
Token ID | 416 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
above | +0.022 |
ary | +0.021 |
overed | +0.021 |
below | +0.020 |
behold | +0.019 |
Neg logit contributions | |
handed | -0.022 |
cash | -0.021 |
cand | -0.021 |
moderation | -0.020 |
dishes | -0.019 |
Token | their |
Token ID | 511 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
above | +0.032 |
below | +0.028 |
behold | +0.028 |
ary | +0.028 |
: | +0.028 |
Neg logit contributions | |
handed | -0.034 |
cand | -0.032 |
cash | -0.031 |
redd | -0.030 |
moderation | -0.030 |
Token | feet |
Token ID | 3625 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
handed | +0.020 |
cash | +0.019 |
cand | +0.019 |
moderation | +0.017 |
dishes | +0.017 |
Neg logit contributions | |
above | -0.026 |
ary | -0.024 |
overed | -0.024 |
below | -0.023 |
: | -0.023 |
Token | string |
Token ID | 4731 |
Feature activation | -4.96e-03 |
Pos logit contributions | |
above | +0.018 |
ary | +0.017 |
: | +0.017 |
below | +0.017 |
overed | +0.016 |
Neg logit contributions | |
handed | -0.011 |
cash | -0.009 |
moderation | -0.008 |
cand | -0.008 |
Those | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +6.24e-03 |
Pos logit contributions | |
handed | +0.009 |
cash | +0.009 |
cand | +0.009 |
moderation | +0.009 |
dishes | +0.008 |
Neg logit contributions | |
above | -0.006 |
ary | -0.005 |
below | -0.005 |
overed | -0.005 |
: | -0.005 |
Token | carefully |
Token ID | 7773 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
above | +0.009 |
ary | +0.009 |
overed | +0.008 |
below | +0.008 |
behold | +0.008 |
Neg logit contributions | |
handed | -0.010 |
cash | -0.009 |
cand | -0.009 |
moderation | -0.009 |
dishes | -0.008 |
Token | wrapped |
Token ID | 12908 |
Feature activation | +3.89e-03 |
Pos logit contributions | |
above | +0.027 |
ary | +0.026 |
overed | +0.025 |
below | +0.025 |
behold | +0.024 |
Neg logit contributions | |
handed | -0.029 |
cash | -0.028 |
cand | -0.027 |
moderation | -0.026 |
dishes | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
above | +0.005 |
ary | +0.004 |
overed | +0.004 |
below | +0.004 |
: | +0.004 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.007 |
cand | -0.007 |
moderation | -0.006 |
dishes | -0.006 |
Token | l |
Token ID | 300 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
above | +0.043 |
ary | +0.041 |
: | +0.040 |
below | +0.039 |
overed | +0.038 |
Neg logit contributions | |
handed | -0.030 |
cash | -0.022 |
moderation | -0.022 |
lest | -0.021 |
cand | -0.021 |
Token | imes |
Token ID | 999 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
above | +0.127 |
behold | +0.114 |
ary | +0.114 |
below | +0.113 |
brewing | +0.113 |
Neg logit contributions | |
handed | -0.116 |
cash | -0.110 |
cand | -0.109 |
handful | -0.103 |
moderation | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | +7.45e-03 |
Pos logit contributions | |
above | +0.040 |
ary | +0.035 |
below | +0.034 |
overed | +0.033 |
: | +0.031 |
Neg logit contributions | |
handed | -0.099 |
cash | -0.097 |
cand | -0.095 |
moderation | -0.093 |
dishes | -0.089 |
Token |
|
Token ID | 198 |
Feature activation | +1.27e-03 |
Pos logit contributions | |
above | +0.011 |
ary | +0.011 |
overed | +0.010 |
below | +0.010 |
: | +0.010 |
Neg logit contributions | |
handed | -0.011 |
cash | -0.011 |
cand | -0.011 |
moderation | -0.010 |
dishes | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -9.06e-03 |
Pos logit contributions | |
above | +0.002 |
overed | +0.002 |
ary | +0.002 |
ols | +0.002 |
below | +0.002 |
Neg logit contributions | |
handed | -0.001 |
cash | -0.001 |
cand | -0.001 |
moderation | -0.001 |
handful | -0.001 |
Token | When |
Token ID | 2215 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
handed | +0.014 |
cash | +0.014 |
cand | +0.014 |
moderation | +0.013 |
dishes | +0.013 |
Neg logit contributions | |
above | -0.013 |
ary | -0.013 |
overed | -0.012 |
below | -0.012 |
: | -0.011 |
Token | together |
Token ID | 1978 |
Feature activation | +9.97e-03 |
Pos logit contributions | |
handed | +0.006 |
cand | +0.006 |
cash | +0.005 |
handful | +0.005 |
toy | +0.005 |
Neg logit contributions | |
ary | -0.006 |
above | -0.006 |
overed | -0.006 |
behold | -0.006 |
below | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +7.46e-03 |
Pos logit contributions | |
above | +0.013 |
ary | +0.013 |
overed | +0.012 |
behold | +0.012 |
ols | +0.012 |
Neg logit contributions | |
handed | -0.016 |
cand | -0.015 |
cash | -0.015 |
handful | -0.014 |
moderation | -0.014 |
Token | carefully |
Token ID | 7773 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
above | +0.012 |
ary | +0.011 |
below | +0.011 |
behold | +0.010 |
overed | +0.010 |
Neg logit contributions | |
handed | -0.011 |
cand | -0.010 |
cash | -0.010 |
moderation | -0.009 |
dishes | -0.009 |
Token | pick |
Token ID | 2298 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
above | +0.028 |
ary | +0.027 |
below | +0.025 |
overed | +0.025 |
: | +0.024 |
Neg logit contributions | |
handed | -0.038 |
cash | -0.036 |
cand | -0.036 |
moderation | -0.034 |
dishes | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
above | +0.018 |
below | +0.017 |
over | +0.016 |
: | +0.015 |
ary | +0.015 |
Neg logit contributions | |
handed | -0.024 |
cash | -0.023 |
cand | -0.022 |
moderation | -0.022 |
lest | -0.021 |
Token | l |
Token ID | 300 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
above | +0.064 |
ary | +0.060 |
below | +0.059 |
overed | +0.058 |
: | +0.057 |
Neg logit contributions | |
handed | -0.039 |
cash | -0.034 |
cand | -0.033 |
moderation | -0.032 |
dishes | -0.030 |
Token | ily |
Token ID | 813 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
above | +0.127 |
brewing | +0.118 |
behold | +0.114 |
lights | +0.111 |
below | +0.111 |
Neg logit contributions | |
handed | -0.116 |
cash | -0.109 |
cand | -0.109 |
moderation | -0.100 |
handful | -0.100 |
Token | from |
Token ID | 422 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
above | +0.038 |
ary | +0.036 |
overed | +0.035 |
below | +0.034 |
behold | +0.033 |
Neg logit contributions | |
handed | -0.040 |
cand | -0.038 |
cash | -0.038 |
moderation | -0.035 |
handful | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
ary | +0.068 |
above | +0.067 |
overed | +0.067 |
ols | +0.062 |
below | +0.062 |
Neg logit contributions | |
cash | -0.064 |
handed | -0.064 |
cand | -0.059 |
moderation | -0.058 |
dishes | -0.055 |
Token | bush |
Token ID | 24484 |
Feature activation | +3.46e-03 |
Pos logit contributions | |
above | +0.035 |
ary | +0.034 |
overed | +0.033 |
below | +0.033 |
behold | +0.031 |
Neg logit contributions | |
handed | -0.017 |
cash | -0.017 |
cand | -0.016 |
moderation | -0.015 |
dishes | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +6.55e-03 |
Pos logit contributions | |
above | +0.004 |
ary | +0.004 |
overed | +0.003 |
below | +0.003 |
behold | +0.003 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.006 |
cand | -0.006 |
moderation | -0.006 |
dishes | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
above | +0.005 |
ary | +0.005 |
overed | +0.004 |
below | +0.004 |
behold | +0.004 |
Neg logit contributions | |
handed | -0.003 |
cash | -0.003 |
cand | -0.003 |
moderation | -0.003 |
dishes | -0.003 |
Token | hoped |
Token ID | 10719 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
above | +0.023 |
ary | +0.022 |
overed | +0.022 |
ols | +0.021 |
below | +0.021 |
Neg logit contributions | |
cash | -0.023 |
handed | -0.023 |
cand | -0.022 |
moderation | -0.020 |
toy | -0.020 |
Token | they |
Token ID | 484 |
Feature activation | +8.77e-03 |
Pos logit contributions | |
above | +0.019 |
ary | +0.018 |
overed | +0.018 |
below | +0.017 |
behold | +0.016 |
Neg logit contributions | |
handed | -0.022 |
cash | -0.021 |
cand | -0.021 |
moderation | -0.020 |
dishes | -0.019 |
Token | would |
Token ID | 561 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
overed | +0.012 |
above | +0.011 |
ary | +0.011 |
ols | +0.011 |
brewing | +0.011 |
Neg logit contributions | |
cand | -0.014 |
cash | -0.013 |
candy | -0.013 |
handful | -0.013 |
handed | -0.013 |
Token | find |
Token ID | 1064 |
Feature activation | +4.66e-03 |
Pos logit contributions | |
overed | +0.038 |
above | +0.037 |
ary | +0.037 |
below | +0.035 |
ols | +0.034 |
Neg logit contributions | |
cash | -0.030 |
handed | -0.029 |
cand | -0.029 |
moderation | -0.029 |
candy | -0.027 |
Token | l |
Token ID | 300 |
Feature activation | +8.07e-02 |
Pos logit contributions | |
above | +0.008 |
ary | +0.007 |
below | +0.007 |
: | +0.007 |
ores | +0.007 |
Neg logit contributions | |
handed | -0.006 |
cash | -0.006 |
cand | -0.005 |
lest | -0.005 |
Those | -0.005 |
Token | imes |
Token ID | 999 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
above | +0.143 |
brewing | +0.134 |
behold | +0.132 |
ary | +0.129 |
below | +0.125 |
Neg logit contributions | |
handed | -0.103 |
cand | -0.098 |
moderation | -0.095 |
cash | -0.092 |
handful | -0.091 |
Token | next |
Token ID | 1306 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
above | +0.052 |
ary | +0.049 |
overed | +0.047 |
below | +0.046 |
behold | +0.044 |
Neg logit contributions | |
handed | -0.074 |
cash | -0.071 |
cand | -0.070 |
moderation | -0.066 |
dishes | -0.065 |
Token | week |
Token ID | 1285 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
overed | +0.060 |
ary | +0.058 |
above | +0.055 |
ols | +0.054 |
behold | +0.053 |
Neg logit contributions | |
cand | -0.051 |
toy | -0.051 |
handed | -0.050 |
cash | -0.050 |
dishes | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +6.10e-03 |
Pos logit contributions | |
handed | +0.048 |
cand | +0.048 |
cash | +0.048 |
dishes | +0.045 |
toy | +0.044 |
Neg logit contributions | |
above | -0.041 |
overed | -0.041 |
ary | -0.040 |
behold | -0.038 |
below | -0.037 |
Token | She |
Token ID | 1375 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
above | +0.010 |
ary | +0.010 |
overed | +0.009 |
below | +0.009 |
: | +0.009 |
Neg logit contributions | |
handed | -0.008 |
cash | -0.008 |
cand | -0.008 |
moderation | -0.007 |
dishes | -0.007 |
Token | forward |
Token ID | 2651 |
Feature activation | +3.58e-03 |
Pos logit contributions | |
handed | +0.034 |
cash | +0.033 |
cand | +0.032 |
handful | +0.030 |
moderation | +0.030 |
Neg logit contributions | |
above | -0.019 |
ary | -0.019 |
overed | -0.018 |
below | -0.017 |
ols | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +7.15e-03 |
Pos logit contributions | |
above | +0.005 |
ary | +0.005 |
ols | +0.005 |
overed | +0.005 |
behold | +0.004 |
Neg logit contributions | |
handed | -0.006 |
cash | -0.005 |
cand | -0.005 |
toy | -0.005 |
handful | -0.005 |
Token | swinging |
Token ID | 25635 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
above | +0.011 |
ary | +0.010 |
overed | +0.010 |
below | +0.010 |
behold | +0.009 |
Neg logit contributions | |
handed | -0.011 |
cash | -0.010 |
cand | -0.010 |
moderation | -0.010 |
dishes | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
ary | +0.042 |
above | +0.041 |
overed | +0.041 |
ols | +0.040 |
brewing | +0.039 |
Neg logit contributions | |
handed | -0.044 |
cand | -0.044 |
cash | -0.044 |
candy | -0.041 |
handful | -0.041 |
Token | eating |
Token ID | 6600 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
above | +0.016 |
ary | +0.016 |
overed | +0.016 |
ols | +0.015 |
below | +0.015 |
Neg logit contributions | |
handed | -0.019 |
cash | -0.019 |
cand | -0.018 |
moderation | -0.017 |
candy | -0.017 |
Token | l |
Token ID | 300 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
above | +0.017 |
below | +0.016 |
ary | +0.016 |
overed | +0.016 |
: | +0.015 |
Neg logit contributions | |
handed | -0.015 |
cash | -0.013 |
cand | -0.013 |
moderation | -0.012 |
lest | -0.012 |
Token | imes |
Token ID | 999 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
above | +0.141 |
brewing | +0.136 |
behold | +0.132 |
ols | +0.128 |
bell | +0.127 |
Neg logit contributions | |
handed | -0.100 |
cand | -0.086 |
moderation | -0.086 |
handful | -0.084 |
penn | -0.078 |
Token | with |
Token ID | 351 |
Feature activation | +6.14e-03 |
Pos logit contributions | |
above | +0.049 |
ary | +0.047 |
overed | +0.045 |
below | +0.044 |
behold | +0.042 |
Neg logit contributions | |
handed | -0.070 |
cash | -0.067 |
cand | -0.067 |
moderation | -0.063 |
dishes | -0.061 |
Token | Andy |
Token ID | 12382 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
above | +0.010 |
ary | +0.010 |
overed | +0.010 |
below | +0.010 |
ols | +0.009 |
Neg logit contributions | |
handed | -0.008 |
cash | -0.008 |
cand | -0.008 |
moderation | -0.007 |
handful | -0.007 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | -9.21e-03 |
Pos logit contributions | |
handed | +0.025 |
cash | +0.024 |
cand | +0.024 |
moderation | +0.023 |
dishes | +0.022 |
Neg logit contributions | |
above | -0.020 |
ary | -0.019 |
overed | -0.018 |
below | -0.018 |
behold | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +9.18e-03 |
Pos logit contributions | |
handed | +0.015 |
cand | +0.014 |
cash | +0.014 |
candy | +0.013 |
toy | +0.013 |
Neg logit contributions | |
above | -0.012 |
ary | -0.012 |
overed | -0.012 |
behold | -0.011 |
ols | -0.011 |
Token | mom |
Token ID | 1995 |
Feature activation | +6.46e-03 |
Pos logit contributions | |
above | +0.018 |
ary | +0.017 |
overed | +0.017 |
below | +0.017 |
ols | +0.016 |
Neg logit contributions | |
handed | -0.009 |
cash | -0.009 |
cand | -0.009 |
toy | -0.008 |
dishes | -0.008 |
Token | my |
Token ID | 1820 |
Feature activation | +4.12e-03 |
Pos logit contributions | |
above | +0.008 |
ary | +0.008 |
below | +0.007 |
overed | +0.007 |
: | +0.007 |
Neg logit contributions | |
handed | -0.011 |
cash | -0.011 |
cand | -0.011 |
moderation | -0.010 |
dishes | -0.010 |
Token | had |
Token ID | 550 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
above | +0.005 |
ary | +0.005 |
below | +0.005 |
: | +0.004 |
overed | +0.004 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.007 |
cand | -0.007 |
moderation | -0.007 |
handful | -0.006 |
Token | tied |
Token ID | 8165 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
above | +0.018 |
ary | +0.017 |
overed | +0.017 |
below | +0.017 |
: | +0.016 |
Neg logit contributions | |
handed | -0.024 |
cash | -0.023 |
cand | -0.023 |
moderation | -0.022 |
dishes | -0.021 |
Token | his |
Token ID | 465 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
above | +0.018 |
ary | +0.018 |
overed | +0.018 |
behold | +0.017 |
below | +0.017 |
Neg logit contributions | |
handed | -0.014 |
cand | -0.013 |
cash | -0.013 |
toy | -0.012 |
handful | -0.012 |
Token | l |
Token ID | 300 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
above | +0.034 |
ary | +0.033 |
overed | +0.032 |
below | +0.032 |
: | +0.031 |
Neg logit contributions | |
handed | -0.020 |
cash | -0.018 |
cand | -0.018 |
moderation | -0.017 |
dishes | -0.016 |
Token | aces |
Token ID | 2114 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
above | +0.134 |
brewing | +0.125 |
behold | +0.123 |
below | +0.122 |
ols | +0.120 |
Neg logit contributions | |
handed | -0.106 |
cand | -0.096 |
cash | -0.094 |
handful | -0.092 |
moderation | -0.090 |
Token | tight |
Token ID | 5381 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
above | +0.054 |
ary | +0.050 |
overed | +0.047 |
below | +0.047 |
: | +0.044 |
Neg logit contributions | |
handed | -0.089 |
cash | -0.087 |
cand | -0.085 |
moderation | -0.082 |
dishes | -0.079 |
Token | around |
Token ID | 1088 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
above | +0.018 |
ary | +0.017 |
overed | +0.016 |
below | +0.016 |
behold | +0.015 |
Neg logit contributions | |
handed | -0.030 |
cash | -0.029 |
cand | -0.029 |
moderation | -0.027 |
dishes | -0.027 |
Token | his |
Token ID | 465 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
handed | +0.020 |
cand | +0.019 |
cash | +0.019 |
moderation | +0.018 |
dishes | +0.018 |
Neg logit contributions | |
ary | -0.027 |
above | -0.027 |
overed | -0.027 |
below | -0.025 |
ols | -0.025 |
Token | heels |
Token ID | 18728 |
Feature activation | +8.81e-03 |
Pos logit contributions | |
handed | +0.018 |
cash | +0.017 |
cand | +0.017 |
moderation | +0.015 |
dishes | +0.015 |
Neg logit contributions | |
above | -0.029 |
ary | -0.028 |
overed | -0.028 |
below | -0.027 |
behold | -0.026 |
Token | investigate |
Token ID | 9161 |
Feature activation | +1.94e-03 |
Pos logit contributions | |
above | +0.009 |
ary | +0.009 |
below | +0.008 |
behold | +0.008 |
: | +0.008 |
Neg logit contributions | |
cand | -0.016 |
handed | -0.016 |
cash | -0.016 |
moderation | -0.015 |
redd | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +4.89e-03 |
Pos logit contributions | |
ary | +0.003 |
overed | +0.003 |
above | +0.003 |
ols | +0.003 |
ores | +0.002 |
Neg logit contributions | |
handed | -0.003 |
cand | -0.003 |
cash | -0.003 |
toy | -0.003 |
candy | -0.003 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
above | +0.006 |
ary | +0.006 |
below | +0.006 |
overed | +0.005 |
behold | +0.005 |
Neg logit contributions | |
handed | -0.009 |
cand | -0.008 |
cash | -0.008 |
moderation | -0.008 |
dishes | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
above | +0.027 |
below | +0.025 |
ary | +0.025 |
: | +0.024 |
overed | +0.024 |
Neg logit contributions | |
handed | -0.025 |
cash | -0.024 |
cand | -0.024 |
moderation | -0.023 |
redd | -0.021 |
Token | shiny |
Token ID | 22441 |
Feature activation | +5.30e-03 |
Pos logit contributions | |
above | +0.039 |
ary | +0.038 |
overed | +0.037 |
below | +0.036 |
: | +0.035 |
Neg logit contributions | |
handed | -0.025 |
cash | -0.024 |
cand | -0.023 |
moderation | -0.022 |
dishes | -0.021 |
Token | l |
Token ID | 300 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
above | +0.010 |
ary | +0.010 |
overed | +0.009 |
below | +0.009 |
: | +0.009 |
Neg logit contributions | |
handed | -0.006 |
cash | -0.005 |
cand | -0.005 |
moderation | -0.005 |
dishes | -0.005 |
Token | oll |
Token ID | 692 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
above | +0.133 |
behold | +0.125 |
brewing | +0.120 |
ols | +0.119 |
ary | +0.118 |
Neg logit contributions | |
handed | -0.110 |
cash | -0.092 |
cand | -0.090 |
toy | -0.087 |
moderation | -0.086 |
Token | ipop |
Token ID | 42800 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
above | +0.089 |
ary | +0.086 |
overed | +0.083 |
: | +0.082 |
below | +0.081 |
Neg logit contributions | |
handed | -0.067 |
cash | -0.062 |
cand | -0.059 |
moderation | -0.057 |
dishes | -0.053 |
Token | in |
Token ID | 287 |
Feature activation | +7.34e-03 |
Pos logit contributions | |
ary | +0.042 |
above | +0.041 |
behold | +0.040 |
overed | +0.038 |
ores | +0.038 |
Neg logit contributions | |
handed | -0.054 |
cash | -0.053 |
cand | -0.052 |
toy | -0.050 |
candy | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | -1.84e-03 |
Pos logit contributions | |
above | +0.011 |
below | +0.010 |
behold | +0.010 |
over | +0.009 |
: | +0.009 |
Neg logit contributions | |
cand | -0.011 |
handed | -0.011 |
cash | -0.011 |
lest | -0.011 |
redd | -0.010 |
Token | garden |
Token ID | 11376 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
lest | +0.003 |
handed | +0.003 |
cand | +0.003 |
moderation | +0.002 |
handful | +0.002 |
Neg logit contributions | |
above | -0.003 |
below | -0.002 |
over | -0.002 |
: | -0.002 |
ary | -0.002 |
Token | restless |
Token ID | 42537 |
Feature activation | +7.88e-04 |
Pos logit contributions | |
above | +0.027 |
ary | +0.026 |
overed | +0.025 |
below | +0.025 |
: | +0.024 |
Neg logit contributions | |
handed | -0.023 |
cash | -0.021 |
cand | -0.021 |
moderation | -0.020 |
dishes | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
above | +0.001 |
ary | +0.001 |
overed | +0.001 |
below | +0.001 |
behold | +0.001 |
Neg logit contributions | |
handed | -0.001 |
cash | -0.001 |
cand | -0.001 |
moderation | -0.001 |
dishes | -0.001 |
Token | I |
Token ID | 314 |
Feature activation | +7.12e-03 |
Pos logit contributions | |
above | +0.002 |
ary | +0.002 |
below | +0.002 |
overed | +0.002 |
: | +0.002 |
Neg logit contributions | |
handed | -0.002 |
cash | -0.002 |
cand | -0.002 |
moderation | -0.002 |
handful | -0.002 |
Token | wondered |
Token ID | 14028 |
Feature activation | +2.09e-03 |
Pos logit contributions | |
above | +0.011 |
ary | +0.011 |
overed | +0.011 |
below | +0.010 |
ols | +0.010 |
Neg logit contributions | |
handed | -0.010 |
cash | -0.009 |
cand | -0.009 |
moderation | -0.009 |
dishes | -0.008 |
Token | how |
Token ID | 703 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
above | +0.003 |
ary | +0.003 |
overed | +0.003 |
below | +0.003 |
ols | +0.003 |
Neg logit contributions | |
handed | -0.003 |
cand | -0.003 |
cash | -0.003 |
moderation | -0.002 |
dishes | -0.002 |
Token | pe |
Token ID | 613 |
Feature activation | +8.01e-02 |
Pos logit contributions | |
above | +0.049 |
overed | +0.049 |
ary | +0.048 |
ols | +0.047 |
behold | +0.045 |
Neg logit contributions | |
handed | -0.036 |
cand | -0.033 |
toy | -0.032 |
candy | -0.032 |
cash | -0.032 |
Token | aches |
Token ID | 3694 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
above | +0.140 |
ary | +0.134 |
overed | +0.130 |
below | +0.129 |
: | +0.124 |
Neg logit contributions | |
handed | -0.100 |
cash | -0.094 |
cand | -0.093 |
moderation | -0.086 |
dishes | -0.082 |
Token | tasted |
Token ID | 29187 |
Feature activation | +7.43e-03 |
Pos logit contributions | |
above | +0.071 |
ary | +0.067 |
overed | +0.064 |
below | +0.063 |
behold | +0.060 |
Neg logit contributions | |
handed | -0.099 |
cand | -0.095 |
cash | -0.094 |
moderation | -0.089 |
dishes | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | +4.53e-03 |
Pos logit contributions | |
above | +0.010 |
ary | +0.010 |
overed | +0.009 |
below | +0.009 |
behold | +0.009 |
Neg logit contributions | |
handed | -0.012 |
cash | -0.012 |
cand | -0.012 |
moderation | -0.011 |
dishes | -0.011 |
Token | I |
Token ID | 314 |
Feature activation | +5.51e-03 |
Pos logit contributions | |
above | +0.007 |
ary | +0.006 |
: | +0.006 |
below | +0.006 |
overed | +0.006 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.007 |
cand | -0.007 |
dishes | -0.006 |
moderation | -0.006 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
above | +0.008 |
ary | +0.008 |
overed | +0.007 |
below | +0.007 |
: | +0.007 |
Neg logit contributions | |
handed | -0.009 |
cash | -0.008 |
cand | -0.008 |
moderation | -0.008 |
dishes | -0.007 |
Token | Molly |
Token ID | 30236 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
above | +0.014 |
ary | +0.013 |
overed | +0.013 |
below | +0.013 |
ols | +0.013 |
Neg logit contributions | |
handed | -0.011 |
cand | -0.010 |
cash | -0.010 |
moderation | -0.010 |
dishes | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +2.01e-03 |
Pos logit contributions | |
handed | +0.033 |
cand | +0.031 |
cash | +0.031 |
moderation | +0.029 |
dishes | +0.029 |
Neg logit contributions | |
above | -0.024 |
overed | -0.023 |
ary | -0.022 |
below | -0.021 |
behold | -0.021 |
Token | He |
Token ID | 679 |
Feature activation | -1.62e-03 |
Pos logit contributions | |
above | +0.003 |
ary | +0.003 |
overed | +0.003 |
below | +0.003 |
: | +0.003 |
Neg logit contributions | |
handed | -0.003 |
cash | -0.003 |
cand | -0.003 |
moderation | -0.003 |
dishes | -0.003 |
Token | put |
Token ID | 1234 |
Feature activation | -4.01e-03 |
Pos logit contributions | |
cash | +0.002 |
cand | +0.002 |
handed | +0.002 |
toy | +0.002 |
handful | +0.002 |
Neg logit contributions | |
above | -0.003 |
ary | -0.002 |
overed | -0.002 |
below | -0.002 |
ols | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
handed | +0.007 |
cash | +0.006 |
cand | +0.006 |
moderation | +0.006 |
dishes | +0.006 |
Neg logit contributions | |
above | -0.006 |
ary | -0.005 |
below | -0.005 |
overed | -0.005 |
over | -0.005 |
Token | l |
Token ID | 300 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
above | +0.039 |
ary | +0.038 |
below | +0.036 |
overed | +0.035 |
behold | +0.034 |
Neg logit contributions | |
handed | -0.031 |
cash | -0.026 |
cand | -0.025 |
moderation | -0.025 |
lest | -0.024 |
Token | ily |
Token ID | 813 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
above | +0.103 |
ary | +0.091 |
below | +0.090 |
behold | +0.087 |
overed | +0.087 |
Neg logit contributions | |
handed | -0.140 |
cash | -0.131 |
cand | -0.131 |
moderation | -0.123 |
handful | -0.123 |
Token | pad |
Token ID | 14841 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
above | +0.018 |
ary | +0.016 |
below | +0.015 |
overed | +0.015 |
: | +0.014 |
Neg logit contributions | |
handed | -0.046 |
cash | -0.045 |
cand | -0.044 |
moderation | -0.042 |
dishes | -0.041 |
Token | on |
Token ID | 319 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
above | +0.013 |
ary | +0.013 |
overed | +0.012 |
below | +0.011 |
: | +0.011 |
Neg logit contributions | |
handed | -0.026 |
cash | -0.025 |
cand | -0.025 |
moderation | -0.024 |
dishes | -0.023 |
Token | his |
Token ID | 465 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
handed | +0.022 |
cand | +0.020 |
cash | +0.020 |
moderation | +0.019 |
dishes | +0.019 |
Neg logit contributions | |
above | -0.018 |
ary | -0.017 |
below | -0.016 |
overed | -0.016 |
: | -0.016 |
Token | back |
Token ID | 736 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
handed | +0.017 |
cash | +0.016 |
cand | +0.016 |
moderation | +0.015 |
handful | +0.014 |
Neg logit contributions | |
above | -0.022 |
ary | -0.022 |
below | -0.020 |
overed | -0.020 |
: | -0.020 |
Token | he |
Token ID | 339 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
above | +0.037 |
below | +0.035 |
over | +0.032 |
behold | +0.032 |
: | +0.032 |
Neg logit contributions | |
handed | -0.028 |
cand | -0.026 |
cash | -0.025 |
These | -0.023 |
moderation | -0.023 |
Token | found |
Token ID | 1043 |
Feature activation | +4.44e-03 |
Pos logit contributions | |
ols | +0.020 |
above | +0.019 |
overed | +0.018 |
lights | +0.018 |
ores | +0.017 |
Neg logit contributions | |
cash | -0.016 |
toy | -0.015 |
cand | -0.015 |
handed | -0.015 |
handful | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
above | +0.007 |
below | +0.006 |
over | +0.006 |
: | +0.006 |
overed | +0.006 |
Neg logit contributions | |
handed | -0.006 |
lest | -0.006 |
cand | -0.006 |
cash | -0.006 |
These | -0.006 |
Token | blo |
Token ID | 24924 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
above | +0.032 |
ary | +0.031 |
below | +0.029 |
overed | +0.029 |
: | +0.029 |
Neg logit contributions | |
handed | -0.020 |
cash | -0.018 |
cand | -0.018 |
moderation | -0.017 |
dishes | -0.016 |
Token | oming |
Token ID | 3383 |
Feature activation | +1.97e-03 |
Pos logit contributions | |
above | +0.062 |
ary | +0.062 |
brewing | +0.060 |
behold | +0.059 |
overed | +0.057 |
Neg logit contributions | |
handful | -0.072 |
cand | -0.070 |
redd | -0.069 |
handed | -0.068 |
cash | -0.067 |
Token | l |
Token ID | 300 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
ary | +0.004 |
overed | +0.003 |
ores | +0.003 |
above | +0.003 |
ols | +0.003 |
Neg logit contributions | |
cand | -0.002 |
cash | -0.002 |
toy | -0.002 |
handed | -0.002 |
candy | -0.002 |
Token | ily |
Token ID | 813 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
above | +0.126 |
brewing | +0.125 |
lights | +0.123 |
ols | +0.122 |
behold | +0.121 |
Neg logit contributions | |
handed | -0.103 |
cand | -0.091 |
handful | -0.089 |
redd | -0.088 |
moderation | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | +4.28e-03 |
Pos logit contributions | |
ary | +0.049 |
above | +0.049 |
overed | +0.048 |
ores | +0.048 |
ols | +0.047 |
Neg logit contributions | |
handed | -0.034 |
cand | -0.034 |
cash | -0.031 |
toy | -0.030 |
candy | -0.029 |
Token | He |
Token ID | 679 |
Feature activation | -5.44e-04 |
Pos logit contributions | |
above | +0.007 |
below | +0.006 |
ary | +0.006 |
: | +0.006 |
overed | +0.006 |
Neg logit contributions | |
cand | -0.006 |
handed | -0.006 |
moderation | -0.006 |
cash | -0.006 |
handful | -0.006 |
Token | could |
Token ID | 714 |
Feature activation | +1.26e-03 |
Pos logit contributions | |
cash | +0.001 |
cand | +0.001 |
handed | +0.001 |
toy | +0.001 |
handful | +0.001 |
Neg logit contributions | |
ols | -0.001 |
above | -0.001 |
ary | -0.001 |
overed | -0.001 |
below | -0.001 |
Token | not |
Token ID | 407 |
Feature activation | +5.79e-03 |
Pos logit contributions | |
overed | +0.002 |
brewing | +0.002 |
ols | +0.002 |
lights | +0.002 |
above | +0.002 |
Neg logit contributions | |
handed | -0.001 |
cash | -0.001 |
cand | -0.001 |
moderation | -0.001 |
handful | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +6.61e-03 |
Pos logit contributions | |
handed | +0.056 |
cand | +0.055 |
cash | +0.054 |
moderation | +0.053 |
dishes | +0.051 |
Neg logit contributions | |
above | -0.037 |
ary | -0.033 |
below | -0.033 |
overed | -0.032 |
: | -0.031 |
Token | they |
Token ID | 484 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
above | +0.009 |
ary | +0.008 |
below | +0.008 |
overed | +0.008 |
: | +0.007 |
Neg logit contributions | |
handed | -0.011 |
cand | -0.011 |
cash | -0.010 |
moderation | -0.010 |
dishes | -0.010 |
Token | bought |
Token ID | 5839 |
Feature activation | -5.21e-03 |
Pos logit contributions | |
cash | +0.016 |
cand | +0.015 |
handed | +0.015 |
handful | +0.014 |
toy | +0.014 |
Neg logit contributions | |
overed | -0.014 |
above | -0.014 |
ary | -0.013 |
ols | -0.013 |
brewing | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
handed | +0.008 |
cash | +0.008 |
cand | +0.008 |
moderation | +0.008 |
lest | +0.007 |
Neg logit contributions | |
above | -0.007 |
ary | -0.007 |
below | -0.007 |
overed | -0.007 |
: | -0.006 |
Token | delicious |
Token ID | 12625 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
above | +0.032 |
ary | +0.031 |
: | +0.030 |
below | +0.030 |
over | +0.029 |
Neg logit contributions | |
handed | -0.027 |
moderation | -0.024 |
cash | -0.023 |
cand | -0.023 |
Those | -0.022 |
Token | l |
Token ID | 300 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
above | +0.046 |
ary | +0.044 |
: | +0.043 |
overed | +0.043 |
below | +0.042 |
Neg logit contributions | |
handed | -0.027 |
cash | -0.023 |
moderation | -0.022 |
cand | -0.022 |
lest | -0.021 |
Token | olly |
Token ID | 5098 |
Feature activation | +8.98e-03 |
Pos logit contributions | |
above | +0.130 |
below | +0.117 |
ary | +0.117 |
behold | +0.116 |
brewing | +0.114 |
Neg logit contributions | |
handed | -0.114 |
cand | -0.103 |
cash | -0.102 |
moderation | -0.096 |
handful | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | +8.57e-03 |
Pos logit contributions | |
above | +0.017 |
ary | +0.016 |
: | +0.015 |
below | +0.015 |
behold | +0.015 |
Neg logit contributions | |
handed | -0.010 |
cash | -0.009 |
cand | -0.008 |
moderation | -0.008 |
dishes | -0.008 |
Token | The |
Token ID | 383 |
Feature activation | -3.37e-03 |
Pos logit contributions | |
above | +0.013 |
ary | +0.012 |
overed | +0.012 |
below | +0.012 |
: | +0.012 |
Neg logit contributions | |
handed | -0.013 |
cash | -0.012 |
cand | -0.012 |
moderation | -0.012 |
dishes | -0.011 |
Token | pup |
Token ID | 15552 |
Feature activation | -9.84e-03 |
Pos logit contributions | |
handed | +0.004 |
cand | +0.004 |
cash | +0.004 |
moderation | +0.003 |
handful | +0.003 |
Neg logit contributions | |
above | -0.006 |
ary | -0.006 |
below | -0.006 |
overed | -0.006 |
: | -0.005 |
Token | stopped |
Token ID | 5025 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
handed | +0.016 |
cash | +0.015 |
cand | +0.015 |
toy | +0.014 |
handful | +0.014 |
Neg logit contributions | |
above | -0.014 |
ary | -0.013 |
overed | -0.012 |
below | -0.012 |
ols | -0.012 |
Token | ! |
Token ID | 0 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
above | +0.018 |
overed | +0.017 |
ary | +0.017 |
below | +0.016 |
behold | +0.016 |
Neg logit contributions | |
handed | -0.019 |
cash | -0.017 |
cand | -0.017 |
moderation | -0.016 |
handful | -0.016 |
Token | I |
Token ID | 314 |
Feature activation | +1.80e-03 |
Pos logit contributions | |
above | +0.023 |
ary | +0.021 |
overed | +0.021 |
below | +0.021 |
behold | +0.020 |
Neg logit contributions | |
handed | -0.017 |
cash | -0.016 |
cand | -0.016 |
moderation | -0.015 |
dishes | -0.014 |
Token | know |
Token ID | 760 |
Feature activation | +8.92e-03 |
Pos logit contributions | |
above | +0.003 |
overed | +0.003 |
ary | +0.003 |
below | +0.003 |
ols | +0.003 |
Neg logit contributions | |
handed | -0.002 |
cash | -0.002 |
cand | -0.002 |
moderation | -0.002 |
handful | -0.002 |
Token | where |
Token ID | 810 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
above | +0.013 |
ary | +0.012 |
below | +0.012 |
overed | +0.012 |
: | +0.012 |
Neg logit contributions | |
handed | -0.014 |
cash | -0.013 |
cand | -0.013 |
moderation | -0.012 |
dishes | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
above | +0.033 |
ary | +0.032 |
overed | +0.031 |
below | +0.030 |
behold | +0.029 |
Neg logit contributions | |
handed | -0.032 |
cash | -0.030 |
cand | -0.030 |
moderation | -0.028 |
dishes | -0.027 |
Token | l |
Token ID | 300 |
Feature activation | +7.96e-02 |
Pos logit contributions | |
above | +0.050 |
ary | +0.049 |
overed | +0.048 |
below | +0.046 |
ols | +0.045 |
Neg logit contributions | |
handed | -0.032 |
cash | -0.031 |
cand | -0.031 |
moderation | -0.028 |
dishes | -0.028 |
Token | ily |
Token ID | 813 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
above | +0.117 |
lights | +0.113 |
brewing | +0.113 |
ols | +0.104 |
Jas | +0.103 |
Neg logit contributions | |
handed | -0.115 |
cand | -0.107 |
These | -0.101 |
handful | -0.100 |
cash | -0.099 |
Token | is |
Token ID | 318 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
above | +0.054 |
ary | +0.053 |
overed | +0.052 |
below | +0.050 |
ols | +0.049 |
Neg logit contributions | |
handed | -0.049 |
cand | -0.047 |
cash | -0.045 |
moderation | -0.042 |
toy | -0.042 |
Token | ." |
Token ID | 526 |
Feature activation | +8.87e-03 |
Pos logit contributions | |
overed | +0.030 |
ary | +0.030 |
above | +0.030 |
behold | +0.028 |
ols | +0.028 |
Neg logit contributions | |
handed | -0.029 |
cand | -0.028 |
cash | -0.027 |
toy | -0.026 |
moderation | -0.026 |
Token | Maxwell |
Token ID | 28276 |
Feature activation | +9.59e-03 |
Pos logit contributions | |
above | +0.014 |
ary | +0.014 |
overed | +0.013 |
below | +0.013 |
behold | +0.013 |
Neg logit contributions | |
handed | -0.012 |
cash | -0.012 |
cand | -0.011 |
moderation | -0.011 |
dishes | -0.010 |
Token | followed |
Token ID | 3940 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
above | +0.014 |
ary | +0.014 |
overed | +0.013 |
below | +0.013 |
ores | +0.013 |
Neg logit contributions | |
handed | -0.014 |
cash | -0.014 |
cand | -0.014 |
dishes | -0.012 |
toy | -0.012 |
Token | better |
Token ID | 1365 |
Feature activation | +4.61e-03 |
Pos logit contributions | |
above | +0.015 |
ary | +0.014 |
below | +0.014 |
overed | +0.013 |
: | +0.013 |
Neg logit contributions | |
handed | -0.012 |
cash | -0.011 |
cand | -0.011 |
moderation | -0.010 |
dishes | -0.010 |
Token | ! |
Token ID | 0 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
above | +0.005 |
ary | +0.005 |
below | +0.004 |
overed | +0.004 |
: | +0.004 |
Neg logit contributions | |
handed | -0.009 |
cash | -0.009 |
cand | -0.009 |
moderation | -0.008 |
redd | -0.008 |
Token | He |
Token ID | 679 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
above | +0.017 |
ary | +0.016 |
: | +0.016 |
below | +0.016 |
overed | +0.016 |
Neg logit contributions | |
handed | -0.013 |
cand | -0.013 |
cash | -0.013 |
handful | -0.011 |
lest | -0.011 |
Token | put |
Token ID | 1234 |
Feature activation | -4.33e-03 |
Pos logit contributions | |
above | +0.002 |
ols | +0.002 |
ores | +0.002 |
ary | +0.002 |
overed | +0.002 |
Neg logit contributions | |
cash | -0.002 |
cand | -0.002 |
handed | -0.002 |
toy | -0.002 |
candy | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
handed | +0.007 |
cash | +0.006 |
cand | +0.006 |
lest | +0.006 |
These | +0.006 |
Neg logit contributions | |
above | -0.006 |
below | -0.006 |
over | -0.005 |
ary | -0.005 |
overed | -0.005 |
Token | l |
Token ID | 300 |
Feature activation | +7.95e-02 |
Pos logit contributions | |
above | +0.025 |
ary | +0.023 |
: | +0.022 |
behold | +0.021 |
below | +0.021 |
Neg logit contributions | |
handed | -0.026 |
lest | -0.021 |
Those | -0.021 |
These | -0.020 |
moderation | -0.020 |
Token | oll |
Token ID | 692 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
above | +0.120 |
ary | +0.113 |
overed | +0.109 |
below | +0.108 |
behold | +0.103 |
Neg logit contributions | |
handed | -0.120 |
cash | -0.114 |
cand | -0.113 |
moderation | -0.105 |
dishes | -0.102 |
Token | ipop |
Token ID | 42800 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
ary | +0.054 |
above | +0.054 |
: | +0.052 |
overed | +0.050 |
below | +0.049 |
Neg logit contributions | |
handed | -0.060 |
cash | -0.053 |
moderation | -0.051 |
Those | -0.050 |
These | -0.049 |
Token | on |
Token ID | 319 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
above | +0.032 |
ary | +0.029 |
overed | +0.028 |
below | +0.027 |
behold | +0.025 |
Neg logit contributions | |
handed | -0.065 |
cash | -0.063 |
cand | -0.062 |
moderation | -0.059 |
dishes | -0.058 |
Token | his |
Token ID | 465 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
handed | +0.014 |
cand | +0.013 |
cash | +0.013 |
moderation | +0.011 |
dishes | +0.011 |
Neg logit contributions | |
above | -0.024 |
ary | -0.023 |
below | -0.022 |
overed | -0.022 |
: | -0.022 |
Token | head |
Token ID | 1182 |
Feature activation | +4.46e-03 |
Pos logit contributions | |
handed | +0.018 |
cash | +0.016 |
cand | +0.016 |
moderation | +0.015 |
Those | +0.015 |
Neg logit contributions | |
above | -0.021 |
ary | -0.020 |
: | -0.019 |
below | -0.019 |
overed | -0.019 |
Token | now |
Token ID | 783 |
Feature activation | +1.59e-03 |
Pos logit contributions | |
above | +0.008 |
ary | +0.008 |
overed | +0.008 |
below | +0.008 |
ols | +0.007 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.007 |
cand | -0.007 |
moderation | -0.006 |
dishes | -0.006 |
Token | I |
Token ID | 314 |
Feature activation | +4.21e-03 |
Pos logit contributions | |
above | +0.003 |
ary | +0.003 |
overed | +0.003 |
below | +0.003 |
brewing | +0.003 |
Neg logit contributions | |
handed | -0.002 |
cand | -0.002 |
cash | -0.002 |
moderation | -0.002 |
candy | -0.002 |
Token | can |
Token ID | 460 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
overed | +0.007 |
above | +0.007 |
lights | +0.006 |
ols | +0.006 |
below | +0.006 |
Neg logit contributions | |
handed | -0.005 |
cand | -0.005 |
cash | -0.005 |
toy | -0.005 |
moderation | -0.005 |
Token | count |
Token ID | 954 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
overed | +0.022 |
above | +0.022 |
ores | +0.020 |
lights | +0.020 |
brewing | +0.020 |
Neg logit contributions | |
handed | -0.016 |
cash | -0.016 |
cand | -0.014 |
toy | -0.014 |
moderation | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
overed | +0.052 |
ary | +0.052 |
behold | +0.049 |
above | +0.049 |
rounded | +0.047 |
Neg logit contributions | |
cand | -0.047 |
candy | -0.044 |
handful | -0.044 |
toy | -0.043 |
dishes | -0.043 |
Token | l |
Token ID | 300 |
Feature activation | +7.93e-02 |
Pos logit contributions | |
above | +0.057 |
ary | +0.056 |
overed | +0.056 |
below | +0.054 |
ores | +0.053 |
Neg logit contributions | |
cand | -0.020 |
cash | -0.020 |
handed | -0.020 |
moderation | -0.018 |
candy | -0.017 |
Token | imes |
Token ID | 999 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
above | +0.138 |
lights | +0.135 |
brewing | +0.135 |
behold | +0.133 |
rounded | +0.124 |
Neg logit contributions | |
handed | -0.087 |
handful | -0.079 |
These | -0.078 |
Those | -0.077 |
redd | -0.077 |
Token | too |
Token ID | 1165 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
above | +0.051 |
ary | +0.050 |
overed | +0.048 |
behold | +0.046 |
below | +0.046 |
Neg logit contributions | |
handed | -0.067 |
cash | -0.063 |
cand | -0.063 |
moderation | -0.059 |
handful | -0.058 |
Token | !" |
Token ID | 2474 |
Feature activation | +7.82e-03 |
Pos logit contributions | |
above | +0.030 |
ary | +0.029 |
overed | +0.029 |
behold | +0.028 |
ols | +0.027 |
Neg logit contributions | |
handed | -0.029 |
cash | -0.027 |
cand | -0.027 |
handful | -0.026 |
moderation | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +7.33e-05 |
Pos logit contributions | |
above | +0.015 |
ary | +0.014 |
overed | +0.014 |
brewing | +0.014 |
ores | +0.014 |
Neg logit contributions | |
handed | -0.008 |
cash | -0.008 |
cand | -0.007 |
moderation | -0.007 |
Those | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -7.58e-03 |
Pos logit contributions | |
above | +0.000 |
lights | +0.000 |
ores | +0.000 |
brewing | +0.000 |
overed | +0.000 |
Neg logit contributions | |
handed | -0.000 |
cash | -0.000 |
toy | -0.000 |
His | -0.000 |
These | -0.000 |
Token | want |
Token ID | 765 |
Feature activation | -5.18e-03 |
Pos logit contributions | |
handed | +0.016 |
cash | +0.015 |
cand | +0.015 |
moderation | +0.014 |
dishes | +0.013 |
Neg logit contributions | |
above | -0.015 |
ary | -0.015 |
below | -0.014 |
: | -0.013 |
behold | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
handed | +0.009 |
cash | +0.009 |
cand | +0.008 |
moderation | +0.008 |
dishes | +0.008 |
Neg logit contributions | |
above | -0.007 |
ary | -0.006 |
overed | -0.006 |
below | -0.006 |
behold | -0.006 |
Token | go |
Token ID | 467 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
handed | +0.015 |
cash | +0.014 |
cand | +0.014 |
moderation | +0.013 |
dishes | +0.012 |
Neg logit contributions | |
above | -0.019 |
ary | -0.018 |
overed | -0.018 |
below | -0.018 |
: | -0.017 |
Token | empty |
Token ID | 6565 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
handed | +0.011 |
cash | +0.011 |
cand | +0.011 |
moderation | +0.010 |
dishes | +0.010 |
Neg logit contributions | |
above | -0.008 |
ary | -0.007 |
overed | -0.007 |
below | -0.007 |
behold | -0.007 |
Token | - |
Token ID | 12 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
handed | +0.028 |
cand | +0.026 |
cash | +0.026 |
moderation | +0.024 |
dishes | +0.024 |
Neg logit contributions | |
ary | -0.023 |
above | -0.023 |
overed | -0.022 |
below | -0.021 |
behold | -0.021 |
Token | handed |
Token ID | 13638 |
Feature activation | -8.17e-02 |
Pos logit contributions | |
above | +0.028 |
ary | +0.027 |
below | +0.027 |
overed | +0.025 |
brewing | +0.025 |
Neg logit contributions | |
cand | -0.006 |
cash | -0.005 |
handful | -0.004 |
dishes | -0.004 |
moderation | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -9.01e-03 |
Pos logit contributions | |
handed | +0.147 |
cash | +0.142 |
cand | +0.139 |
moderation | +0.135 |
handful | +0.129 |
Neg logit contributions | |
above | -0.099 |
ary | -0.090 |
below | -0.088 |
overed | -0.085 |
: | -0.083 |
Token | so |
Token ID | 523 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
handed | +0.013 |
cash | +0.012 |
cand | +0.012 |
moderation | +0.011 |
dishes | +0.011 |
Neg logit contributions | |
above | -0.015 |
ary | -0.014 |
below | -0.013 |
: | -0.013 |
overed | -0.013 |
Token | she |
Token ID | 673 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
handed | +0.032 |
cash | +0.030 |
cand | +0.029 |
moderation | +0.027 |
dishes | +0.026 |
Neg logit contributions | |
above | -0.053 |
ary | -0.051 |
overed | -0.049 |
below | -0.049 |
behold | -0.048 |
Token | sque |
Token ID | 35776 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
above | +0.015 |
ary | +0.014 |
overed | +0.014 |
below | +0.014 |
ols | +0.013 |
Neg logit contributions | |
cash | -0.015 |
handed | -0.015 |
cand | -0.015 |
toy | -0.013 |
handful | -0.013 |
Token | aked |
Token ID | 4335 |
Feature activation | -8.45e-03 |
Pos logit contributions | |
above | +0.059 |
ary | +0.056 |
below | +0.054 |
overed | +0.054 |
brewing | +0.052 |
Neg logit contributions | |
handed | -0.054 |
cand | -0.048 |
moderation | -0.047 |
cash | -0.046 |
handful | -0.046 |
Token | came |
Token ID | 1625 |
Feature activation | +1.66e-04 |
Pos logit contributions | |
above | +0.016 |
ary | +0.016 |
overed | +0.015 |
brewing | +0.015 |
ols | +0.015 |
Neg logit contributions | |
cash | -0.013 |
cand | -0.013 |
handed | -0.013 |
toy | -0.012 |
dishes | -0.011 |
Token | back |
Token ID | 736 |
Feature activation | +6.90e-03 |
Pos logit contributions | |
overed | +0.000 |
ols | +0.000 |
behold | +0.000 |
ary | +0.000 |
above | +0.000 |
Neg logit contributions | |
toy | -0.000 |
handed | -0.000 |
cash | -0.000 |
handful | -0.000 |
dishes | -0.000 |
Token | home |
Token ID | 1363 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
ary | +0.010 |
overed | +0.010 |
above | +0.010 |
ols | +0.009 |
behold | +0.009 |
Neg logit contributions | |
handed | -0.010 |
cash | -0.010 |
cand | -0.009 |
toy | -0.009 |
candy | -0.009 |
Token | empty |
Token ID | 6565 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
handed | +0.037 |
cash | +0.036 |
cand | +0.036 |
moderation | +0.035 |
redd | +0.034 |
Neg logit contributions | |
above | -0.023 |
below | -0.020 |
ary | -0.020 |
: | -0.020 |
overed | -0.020 |
Token | - |
Token ID | 12 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
handed | +0.018 |
cand | +0.017 |
cash | +0.017 |
dishes | +0.016 |
moderation | +0.016 |
Neg logit contributions | |
ary | -0.014 |
above | -0.013 |
overed | -0.013 |
ols | -0.012 |
behold | -0.012 |
Token | handed |
Token ID | 13638 |
Feature activation | -7.88e-02 |
Pos logit contributions | |
above | +0.047 |
below | +0.046 |
ary | +0.046 |
overed | +0.045 |
brewing | +0.044 |
Neg logit contributions | |
handful | -0.007 |
cand | -0.007 |
moderation | -0.006 |
cash | -0.006 |
redd | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -6.15e-03 |
Pos logit contributions | |
handed | +0.149 |
cash | +0.146 |
moderation | +0.143 |
cand | +0.142 |
redd | +0.136 |
Neg logit contributions | |
above | -0.086 |
below | -0.076 |
ary | -0.073 |
: | -0.073 |
overed | -0.071 |
Token | told |
Token ID | 1297 |
Feature activation | -4.38e-03 |
Pos logit contributions | |
handed | +0.009 |
cash | +0.009 |
cand | +0.008 |
moderation | +0.008 |
dishes | +0.008 |
Neg logit contributions | |
above | -0.009 |
ary | -0.009 |
below | -0.009 |
overed | -0.009 |
behold | -0.008 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.88e-03 |
Pos logit contributions | |
handed | +0.005 |
cash | +0.005 |
cand | +0.005 |
moderation | +0.005 |
dishes | +0.005 |
Neg logit contributions | |
above | -0.008 |
ary | -0.007 |
overed | -0.007 |
below | -0.007 |
ols | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
above | +0.005 |
ary | +0.004 |
: | +0.004 |
below | +0.004 |
overed | +0.004 |
Neg logit contributions | |
handed | -0.010 |
cash | -0.010 |
cand | -0.009 |
moderation | -0.009 |
redd | -0.009 |
Token | news |
Token ID | 1705 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
above | +0.028 |
ary | +0.027 |
overed | +0.026 |
below | +0.026 |
behold | +0.025 |
Neg logit contributions | |
handed | -0.018 |
cash | -0.017 |
cand | -0.016 |
moderation | -0.015 |
dishes | -0.014 |
Token | he |
Token ID | 339 |
Feature activation | -4.91e-03 |
Pos logit contributions | |
above | +0.022 |
ary | +0.022 |
overed | +0.021 |
below | +0.021 |
ols | +0.020 |
Neg logit contributions | |
handed | -0.014 |
cash | -0.013 |
cand | -0.013 |
moderation | -0.012 |
dishes | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | +5.83e-03 |
Pos logit contributions | |
handed | +0.006 |
toy | +0.006 |
cand | +0.006 |
candy | +0.006 |
cash | +0.005 |
Neg logit contributions | |
overed | -0.008 |
ols | -0.008 |
above | -0.008 |
lights | -0.008 |
ores | -0.008 |
Token | caught |
Token ID | 4978 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
above | +0.009 |
ary | +0.009 |
overed | +0.009 |
ols | +0.009 |
behold | +0.009 |
Neg logit contributions | |
handed | -0.008 |
cash | -0.007 |
cand | -0.007 |
toy | -0.007 |
moderation | -0.007 |
Token | red |
Token ID | 2266 |
Feature activation | -4.34e-03 |
Pos logit contributions | |
ary | +0.018 |
above | +0.017 |
overed | +0.017 |
ols | +0.016 |
behold | +0.016 |
Neg logit contributions | |
handed | -0.024 |
cash | -0.022 |
cand | -0.022 |
toy | -0.021 |
dishes | -0.021 |
Token | - |
Token ID | 12 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
handed | +0.008 |
cash | +0.007 |
cand | +0.007 |
moderation | +0.007 |
handful | +0.007 |
Neg logit contributions | |
above | -0.005 |
ary | -0.005 |
below | -0.005 |
overed | -0.004 |
: | -0.004 |
Token | handed |
Token ID | 13638 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
ary | +0.030 |
above | +0.028 |
below | +0.027 |
te | +0.025 |
over | +0.025 |
Neg logit contributions | |
cand | -0.033 |
dishes | -0.032 |
cash | -0.032 |
moderation | -0.031 |
handed | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -2.96e-04 |
Pos logit contributions | |
handed | +0.140 |
cash | +0.134 |
cand | +0.132 |
moderation | +0.129 |
dishes | +0.123 |
Neg logit contributions | |
above | -0.073 |
ary | -0.064 |
below | -0.063 |
overed | -0.061 |
: | -0.059 |
Token | But |
Token ID | 887 |
Feature activation | +6.32e-03 |
Pos logit contributions | |
handed | +0.000 |
cash | +0.000 |
cand | +0.000 |
moderation | +0.000 |
dishes | +0.000 |
Neg logit contributions | |
above | -0.001 |
ary | -0.001 |
overed | -0.000 |
below | -0.000 |
: | -0.000 |
Token | he |
Token ID | 339 |
Feature activation | -5.21e-03 |
Pos logit contributions | |
above | +0.010 |
ary | +0.010 |
overed | +0.009 |
below | +0.009 |
ols | +0.009 |
Neg logit contributions | |
handed | -0.009 |
cash | -0.008 |
cand | -0.008 |
moderation | -0.008 |
dishes | -0.008 |
Token | didn |
Token ID | 1422 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
toy | +0.006 |
cash | +0.006 |
handed | +0.005 |
cand | +0.005 |
poor | +0.005 |
Neg logit contributions | |
ols | -0.009 |
lights | -0.009 |
above | -0.009 |
overed | -0.009 |
below | -0.008 |
Token | 't |
Token ID | 470 |
Feature activation | +8.13e-04 |
Pos logit contributions | |
above | +0.067 |
overed | +0.061 |
below | +0.061 |
behold | +0.060 |
ary | +0.059 |
Neg logit contributions | |
handed | -0.057 |
cash | -0.053 |
cand | -0.050 |
These | -0.049 |
dishes | -0.048 |
Token | rounded |
Token ID | 19273 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
above | +0.010 |
ary | +0.010 |
ols | +0.010 |
overed | +0.010 |
ores | +0.009 |
Neg logit contributions | |
handed | -0.010 |
toy | -0.009 |
cash | -0.009 |
cand | -0.009 |
handful | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
ary | +0.022 |
above | +0.022 |
overed | +0.021 |
ols | +0.020 |
below | +0.020 |
Neg logit contributions | |
handed | -0.021 |
cash | -0.019 |
cand | -0.019 |
moderation | -0.018 |
toy | -0.018 |
Token | corner |
Token ID | 5228 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
handed | +0.034 |
cand | +0.033 |
cash | +0.032 |
moderation | +0.031 |
handful | +0.030 |
Neg logit contributions | |
above | -0.028 |
below | -0.026 |
ary | -0.025 |
: | -0.024 |
overed | -0.023 |
Token | of |
Token ID | 286 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
handed | +0.033 |
cash | +0.031 |
cand | +0.031 |
moderation | +0.028 |
dishes | +0.027 |
Neg logit contributions | |
above | -0.039 |
ary | -0.037 |
overed | -0.036 |
below | -0.036 |
ols | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
handed | +0.021 |
cash | +0.020 |
cand | +0.020 |
moderation | +0.019 |
dishes | +0.018 |
Neg logit contributions | |
above | -0.020 |
ary | -0.019 |
overed | -0.018 |
below | -0.018 |
ols | -0.017 |
Token | harbour |
Token ID | 39720 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
handed | +0.020 |
cand | +0.020 |
cash | +0.019 |
moderation | +0.018 |
handful | +0.017 |
Neg logit contributions | |
above | -0.020 |
below | -0.018 |
ary | -0.018 |
: | -0.017 |
overed | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -1.74e-03 |
Pos logit contributions | |
handed | +0.108 |
cash | +0.103 |
cand | +0.102 |
moderation | +0.099 |
handful | +0.092 |
Neg logit contributions | |
above | -0.104 |
ary | -0.097 |
below | -0.096 |
overed | -0.094 |
: | -0.094 |
Token | it |
Token ID | 340 |
Feature activation | -6.05e-03 |
Pos logit contributions | |
handed | +0.003 |
cash | +0.003 |
cand | +0.002 |
moderation | +0.002 |
dishes | +0.002 |
Neg logit contributions | |
above | -0.003 |
ary | -0.002 |
overed | -0.002 |
below | -0.002 |
ols | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -3.37e-03 |
Pos logit contributions | |
handed | +0.008 |
toy | +0.008 |
cash | +0.008 |
cand | +0.007 |
poor | +0.007 |
Neg logit contributions | |
ols | -0.008 |
ary | -0.008 |
above | -0.008 |
overed | -0.008 |
Jas | -0.008 |
Token | surprised |
Token ID | 6655 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
toy | +0.004 |
cheap | +0.004 |
plastic | +0.004 |
fake | +0.004 |
poor | +0.004 |
Neg logit contributions | |
ols | -0.006 |
behold | -0.005 |
ary | -0.005 |
overed | -0.005 |
oline | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
handed | +0.045 |
toy | +0.044 |
cand | +0.043 |
cash | +0.041 |
candy | +0.040 |
Neg logit contributions | |
ary | -0.056 |
behold | -0.055 |
overed | -0.054 |
ols | -0.053 |
halftime | -0.053 |
Token | skipped |
Token ID | 26684 |
Feature activation | +1.16e-04 |
Pos logit contributions | |
overed | +0.030 |
above | +0.030 |
ary | +0.029 |
ols | +0.029 |
behold | +0.028 |
Neg logit contributions | |
handed | -0.031 |
cand | -0.029 |
toy | -0.029 |
cash | -0.029 |
dishes | -0.027 |
Token | happily |
Token ID | 18177 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
above | +0.000 |
ary | +0.000 |
overed | +0.000 |
behold | +0.000 |
below | +0.000 |
Neg logit contributions | |
handed | -0.000 |
cash | -0.000 |
cand | -0.000 |
toy | -0.000 |
handful | -0.000 |
Token | down |
Token ID | 866 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
above | +0.019 |
ary | +0.019 |
overed | +0.018 |
behold | +0.017 |
below | +0.017 |
Neg logit contributions | |
handed | -0.030 |
cash | -0.029 |
cand | -0.029 |
moderation | -0.027 |
dishes | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -9.96e-04 |
Pos logit contributions | |
ary | +0.023 |
ols | +0.022 |
behold | +0.022 |
overed | +0.022 |
above | +0.021 |
Neg logit contributions | |
handed | -0.016 |
cash | -0.014 |
toy | -0.014 |
cand | -0.014 |
candy | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -2.22e-03 |
Pos logit contributions | |
handed | +0.002 |
cash | +0.002 |
cand | +0.002 |
moderation | +0.002 |
dishes | +0.001 |
Neg logit contributions | |
above | -0.001 |
ary | -0.001 |
below | -0.001 |
overed | -0.001 |
behold | -0.001 |
Token | harbour |
Token ID | 39720 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
handed | +0.003 |
cand | +0.003 |
moderation | +0.003 |
cash | +0.003 |
lest | +0.003 |
Neg logit contributions | |
above | -0.004 |
below | -0.003 |
ary | -0.003 |
: | -0.003 |
over | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-03 |
Pos logit contributions | |
handed | +0.136 |
cash | +0.132 |
cand | +0.132 |
moderation | +0.126 |
handful | +0.122 |
Neg logit contributions | |
above | -0.068 |
ary | -0.061 |
below | -0.060 |
overed | -0.056 |
: | -0.055 |
Token | She |
Token ID | 1375 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
handed | +0.002 |
cash | +0.002 |
cand | +0.002 |
moderation | +0.002 |
dishes | +0.001 |
Neg logit contributions | |
above | -0.002 |
ary | -0.002 |
overed | -0.002 |
below | -0.002 |
: | -0.002 |
Token | saw |
Token ID | 2497 |
Feature activation | +7.13e-03 |
Pos logit contributions | |
above | +0.015 |
ary | +0.015 |
overed | +0.014 |
ols | +0.014 |
below | +0.014 |
Neg logit contributions | |
handed | -0.015 |
cash | -0.014 |
cand | -0.014 |
toy | -0.013 |
handful | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +5.46e-03 |
Pos logit contributions | |
above | +0.011 |
below | +0.010 |
ary | +0.010 |
: | +0.010 |
overed | +0.009 |
Neg logit contributions | |
handed | -0.011 |
cash | -0.010 |
moderation | -0.010 |
cand | -0.010 |
lest | -0.009 |
Token | yacht |
Token ID | 43207 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
above | +0.010 |
below | +0.009 |
ary | +0.009 |
overed | +0.008 |
: | +0.008 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.007 |
cand | -0.007 |
moderation | -0.006 |
Those | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -3.19e-03 |
Pos logit contributions | |
handed | +0.019 |
cash | +0.018 |
cand | +0.018 |
toy | +0.018 |
handful | +0.017 |
Neg logit contributions | |
above | -0.017 |
overed | -0.017 |
ary | -0.017 |
ores | -0.016 |
ols | -0.016 |
Token | floating |
Token ID | 12462 |
Feature activation | -4.80e-03 |
Pos logit contributions | |
handed | +0.004 |
toy | +0.003 |
handful | +0.003 |
cash | +0.003 |
cand | +0.003 |
Neg logit contributions | |
ols | -0.005 |
ary | -0.005 |
above | -0.005 |
overed | -0.005 |
behold | -0.005 |
Token | away |
Token ID | 1497 |
Feature activation | +3.94e-03 |
Pos logit contributions | |
handed | +0.008 |
toy | +0.007 |
handful | +0.007 |
cash | +0.007 |
dishes | +0.007 |
Neg logit contributions | |
ary | -0.006 |
overed | -0.006 |
ols | -0.006 |
behold | -0.005 |
above | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
above | +0.004 |
ary | +0.004 |
overed | +0.004 |
below | +0.004 |
behold | +0.004 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.007 |
cand | -0.007 |
moderation | -0.006 |
dishes | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
handed | +0.022 |
cash | +0.021 |
cand | +0.021 |
moderation | +0.019 |
lest | +0.019 |
Neg logit contributions | |
above | -0.021 |
ary | -0.019 |
below | -0.019 |
overed | -0.018 |
behold | -0.017 |
Token | navy |
Token ID | 23956 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
handed | +0.014 |
cash | +0.013 |
cand | +0.013 |
moderation | +0.012 |
dishes | +0.012 |
Neg logit contributions | |
above | -0.018 |
ary | -0.018 |
overed | -0.017 |
below | -0.016 |
: | -0.016 |
Token | sea |
Token ID | 5417 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
handed | +0.110 |
cash | +0.106 |
cand | +0.104 |
moderation | +0.100 |
dishes | +0.094 |
Neg logit contributions | |
above | -0.089 |
ary | -0.083 |
below | -0.080 |
overed | -0.078 |
: | -0.076 |
Token | ! |
Token ID | 0 |
Feature activation | -2.35e-03 |
Pos logit contributions | |
handed | +0.102 |
cash | +0.098 |
cand | +0.097 |
moderation | +0.092 |
dishes | +0.090 |
Neg logit contributions | |
above | -0.058 |
ary | -0.054 |
overed | -0.051 |
below | -0.051 |
: | -0.047 |
Token | He |
Token ID | 679 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
handed | +0.003 |
cash | +0.003 |
cand | +0.003 |
moderation | +0.003 |
dishes | +0.003 |
Neg logit contributions | |
above | -0.004 |
ary | -0.004 |
overed | -0.004 |
below | -0.004 |
behold | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -3.92e-03 |
Pos logit contributions | |
toy | +0.015 |
cand | +0.014 |
handed | +0.014 |
cash | +0.014 |
handful | +0.013 |
Neg logit contributions | |
ores | -0.018 |
overed | -0.018 |
above | -0.018 |
ary | -0.018 |
ols | -0.018 |
Token | so |
Token ID | 523 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
handed | +0.005 |
cash | +0.004 |
cand | +0.004 |
toy | +0.004 |
handful | +0.004 |
Neg logit contributions | |
above | -0.007 |
ary | -0.006 |
overed | -0.006 |
ols | -0.006 |
behold | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
cash | +0.008 |
handed | +0.008 |
cand | +0.008 |
toy | +0.008 |
handful | +0.007 |
Neg logit contributions | |
ary | -0.013 |
overed | -0.013 |
ols | -0.012 |
above | -0.012 |
below | -0.012 |
Token | place |
Token ID | 1295 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
handed | +0.013 |
cash | +0.013 |
cand | +0.012 |
moderation | +0.011 |
toy | +0.011 |
Neg logit contributions | |
above | -0.022 |
ary | -0.021 |
overed | -0.021 |
below | -0.020 |
ols | -0.019 |
Token | deep |
Token ID | 2769 |
Feature activation | +1.99e-03 |
Pos logit contributions | |
handed | +0.033 |
cand | +0.032 |
cash | +0.031 |
moderation | +0.029 |
dishes | +0.029 |
Neg logit contributions | |
above | -0.029 |
ary | -0.028 |
overed | -0.027 |
below | -0.026 |
ols | -0.026 |
Token | in |
Token ID | 287 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
ary | +0.002 |
overed | +0.002 |
ols | +0.002 |
behold | +0.002 |
ores | +0.002 |
Neg logit contributions | |
handed | -0.004 |
cand | -0.004 |
cash | -0.004 |
handful | -0.004 |
toy | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
handed | +0.030 |
cash | +0.029 |
cand | +0.028 |
moderation | +0.026 |
dishes | +0.026 |
Neg logit contributions | |
above | -0.023 |
ary | -0.021 |
below | -0.021 |
overed | -0.020 |
behold | -0.020 |
Token | sea |
Token ID | 5417 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
handed | +0.027 |
cash | +0.026 |
cand | +0.026 |
moderation | +0.024 |
dishes | +0.023 |
Neg logit contributions | |
above | -0.026 |
ary | -0.024 |
below | -0.023 |
overed | -0.023 |
behold | -0.022 |
Token | that |
Token ID | 326 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
handed | +0.124 |
cash | +0.123 |
cand | +0.121 |
moderation | +0.114 |
dishes | +0.110 |
Neg logit contributions | |
above | -0.076 |
ary | -0.068 |
below | -0.068 |
: | -0.063 |
overed | -0.063 |
Token | the |
Token ID | 262 |
Feature activation | -7.87e-03 |
Pos logit contributions | |
handed | +0.046 |
cash | +0.043 |
cand | +0.043 |
moderation | +0.041 |
dishes | +0.040 |
Neg logit contributions | |
above | -0.034 |
ary | -0.033 |
overed | -0.031 |
below | -0.030 |
ols | -0.029 |
Token | mer |
Token ID | 4017 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
handed | +0.010 |
cash | +0.010 |
cand | +0.010 |
dishes | +0.009 |
moderation | +0.009 |
Neg logit contributions | |
above | -0.013 |
ary | -0.013 |
overed | -0.013 |
ols | -0.012 |
below | -0.012 |
Token | maid |
Token ID | 23151 |
Feature activation | -9.17e-04 |
Pos logit contributions | |
handed | +0.028 |
cand | +0.026 |
cash | +0.025 |
handful | +0.024 |
toy | +0.024 |
Neg logit contributions | |
ary | -0.025 |
above | -0.024 |
brewing | -0.022 |
ores | -0.022 |
below | -0.021 |
Token | carefully |
Token ID | 7773 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
handed | +0.002 |
cand | +0.001 |
cash | +0.001 |
toy | +0.001 |
lest | +0.001 |
Neg logit contributions | |
above | -0.001 |
ary | -0.001 |
overed | -0.001 |
ols | -0.001 |
ores | -0.001 |
Token | back |
Token ID | 736 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
handed | +0.003 |
cash | +0.003 |
toy | +0.003 |
cand | +0.003 |
handful | +0.003 |
Neg logit contributions | |
ary | -0.005 |
overed | -0.005 |
behold | -0.005 |
above | -0.005 |
ols | -0.005 |
Token | home |
Token ID | 1363 |
Feature activation | -4.23e-03 |
Pos logit contributions | |
above | +0.035 |
ary | +0.035 |
overed | +0.034 |
behold | +0.032 |
ols | +0.032 |
Neg logit contributions | |
handed | -0.048 |
cash | -0.044 |
cand | -0.044 |
toy | -0.041 |
handful | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | +3.04e-03 |
Pos logit contributions | |
handed | +0.008 |
cash | +0.008 |
cand | +0.008 |
moderation | +0.008 |
redd | +0.008 |
Neg logit contributions | |
above | -0.004 |
below | -0.004 |
ary | -0.004 |
overed | -0.004 |
: | -0.004 |
Token | empty |
Token ID | 6565 |
Feature activation | -9.61e-03 |
Pos logit contributions | |
above | +0.004 |
below | +0.004 |
ary | +0.004 |
overed | +0.004 |
: | +0.004 |
Neg logit contributions | |
handed | -0.005 |
cand | -0.005 |
cash | -0.005 |
moderation | -0.004 |
dishes | -0.004 |
Token | - |
Token ID | 12 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
handed | +0.015 |
cand | +0.015 |
cash | +0.014 |
toy | +0.014 |
dishes | +0.014 |
Neg logit contributions | |
ary | -0.014 |
behold | -0.012 |
above | -0.012 |
overed | -0.012 |
ols | -0.012 |
Token | handed |
Token ID | 13638 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
above | +0.041 |
ary | +0.041 |
below | +0.040 |
overed | +0.039 |
brewing | +0.037 |
Neg logit contributions | |
cand | -0.022 |
cash | -0.020 |
moderation | -0.020 |
dishes | -0.019 |
handful | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +5.40e-03 |
Pos logit contributions | |
handed | +0.128 |
cash | +0.124 |
cand | +0.122 |
moderation | +0.121 |
redd | +0.114 |
Neg logit contributions | |
above | -0.068 |
below | -0.060 |
ary | -0.059 |
overed | -0.057 |
: | -0.056 |
Token |
|
Token ID | 198 |
Feature activation | -3.26e-03 |
Pos logit contributions | |
above | +0.007 |
: | +0.007 |
ary | +0.007 |
below | +0.007 |
overed | +0.007 |
Neg logit contributions | |
cand | -0.009 |
handed | -0.008 |
cash | -0.008 |
lest | -0.008 |
dishes | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
handed | +0.006 |
cash | +0.005 |
cand | +0.005 |
moderation | +0.005 |
handful | +0.005 |
Neg logit contributions | |
above | -0.004 |
overed | -0.004 |
ary | -0.004 |
ols | -0.004 |
below | -0.004 |
Token | Nature |
Token ID | 46934 |
Feature activation | -4.25e-03 |
Pos logit contributions | |
handed | +0.015 |
cand | +0.015 |
cash | +0.015 |
moderation | +0.014 |
dishes | +0.014 |
Neg logit contributions | |
above | -0.016 |
ary | -0.016 |
overed | -0.015 |
below | -0.015 |
behold | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | -4.90e-03 |
Pos logit contributions | |
handed | +0.006 |
toy | +0.005 |
cand | +0.005 |
cash | +0.005 |
lest | +0.005 |
Neg logit contributions | |
ores | -0.006 |
ols | -0.006 |
ary | -0.006 |
Jas | -0.006 |
above | -0.006 |
Token | I |
Token ID | 40 |
Feature activation | +4.29e-03 |
Pos logit contributions | |
handed | +0.023 |
cash | +0.022 |
cand | +0.022 |
moderation | +0.021 |
dishes | +0.021 |
Neg logit contributions | |
above | -0.016 |
ary | -0.015 |
overed | -0.014 |
below | -0.014 |
behold | -0.014 |
Token | fell |
Token ID | 3214 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
above | +0.007 |
ary | +0.006 |
overed | +0.006 |
below | +0.006 |
: | +0.006 |
Neg logit contributions | |
handed | -0.006 |
cash | -0.006 |
cand | -0.006 |
moderation | -0.006 |
dishes | -0.005 |
Token | off |
Token ID | 572 |
Feature activation | +6.33e-03 |
Pos logit contributions | |
handed | +0.028 |
cash | +0.027 |
cand | +0.027 |
moderation | +0.025 |
dishes | +0.025 |
Neg logit contributions | |
above | -0.019 |
ary | -0.018 |
overed | -0.017 |
below | -0.017 |
behold | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
above | +0.010 |
ary | +0.010 |
overed | +0.009 |
below | +0.009 |
ols | +0.009 |
Neg logit contributions | |
handed | -0.009 |
cash | -0.008 |
cand | -0.008 |
moderation | -0.008 |
dishes | -0.008 |
Token | clothes |
Token ID | 8242 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
above | +0.026 |
ary | +0.025 |
overed | +0.025 |
below | +0.024 |
behold | +0.024 |
Neg logit contributions | |
handed | -0.014 |
cash | -0.013 |
cand | -0.013 |
moderation | -0.011 |
dishes | -0.011 |
Token | line |
Token ID | 1370 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
handed | +0.039 |
cash | +0.038 |
cand | +0.037 |
moderation | +0.036 |
dishes | +0.034 |
Neg logit contributions | |
above | -0.027 |
ary | -0.025 |
below | -0.024 |
overed | -0.023 |
: | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +7.38e-03 |
Pos logit contributions | |
handed | +0.111 |
cash | +0.106 |
cand | +0.105 |
moderation | +0.099 |
dishes | +0.097 |
Neg logit contributions | |
above | -0.083 |
ary | -0.078 |
overed | -0.075 |
below | -0.074 |
behold | -0.070 |
Token | I |
Token ID | 314 |
Feature activation | -1.38e-03 |
Pos logit contributions | |
above | +0.012 |
ary | +0.012 |
overed | +0.011 |
below | +0.011 |
ols | +0.011 |
Neg logit contributions | |
handed | -0.010 |
cash | -0.010 |
cand | -0.009 |
moderation | -0.009 |
dishes | -0.009 |
Token | can |
Token ID | 460 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
handed | +0.002 |
cash | +0.002 |
cand | +0.002 |
moderation | +0.002 |
toy | +0.002 |
Neg logit contributions | |
above | -0.002 |
ary | -0.002 |
overed | -0.002 |
below | -0.002 |
ols | -0.002 |
Token | 't |
Token ID | 470 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
above | +0.025 |
overed | +0.025 |
below | +0.024 |
ary | +0.023 |
ols | +0.023 |
Neg logit contributions | |
handed | -0.024 |
cash | -0.023 |
cand | -0.021 |
toy | -0.021 |
dishes | -0.020 |
Token | get |
Token ID | 651 |
Feature activation | -3.96e-05 |
Pos logit contributions | |
overed | +0.026 |
above | +0.023 |
ols | +0.023 |
lights | +0.023 |
arted | +0.023 |
Neg logit contributions | |
handed | -0.015 |
toy | -0.012 |
moderation | -0.012 |
rest | -0.012 |
cash | -0.012 |
Token | bad |
Token ID | 2089 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
handed | +0.018 |
cand | +0.017 |
cash | +0.017 |
moderation | +0.015 |
dishes | +0.015 |
Neg logit contributions | |
above | -0.020 |
ary | -0.020 |
overed | -0.019 |
below | -0.019 |
ols | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | +1.76e-03 |
Pos logit contributions | |
ary | +0.047 |
above | +0.047 |
overed | +0.045 |
below | +0.044 |
behold | +0.043 |
Neg logit contributions | |
cand | -0.053 |
handed | -0.053 |
toy | -0.052 |
cash | -0.051 |
candy | -0.050 |
Token | lurking |
Token ID | 36105 |
Feature activation | +5.43e-04 |
Pos logit contributions | |
ary | +0.002 |
above | +0.002 |
overed | +0.002 |
ols | +0.002 |
behold | +0.002 |
Neg logit contributions | |
handed | -0.003 |
cash | -0.003 |
cand | -0.003 |
toy | -0.003 |
dishes | -0.003 |
Token | in |
Token ID | 287 |
Feature activation | -7.71e-03 |
Pos logit contributions | |
ary | +0.001 |
overed | +0.001 |
ols | +0.001 |
behold | +0.000 |
above | +0.000 |
Neg logit contributions | |
handed | -0.001 |
toy | -0.001 |
cand | -0.001 |
cash | -0.001 |
handful | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -3.30e-03 |
Pos logit contributions | |
handed | +0.012 |
cash | +0.011 |
cand | +0.011 |
moderation | +0.011 |
dishes | +0.010 |
Neg logit contributions | |
above | -0.011 |
ary | -0.011 |
overed | -0.010 |
below | -0.010 |
: | -0.010 |
Token | harbor |
Token ID | 25451 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
handed | +0.005 |
cash | +0.005 |
cand | +0.005 |
moderation | +0.004 |
dishes | +0.004 |
Neg logit contributions | |
ary | -0.005 |
above | -0.005 |
overed | -0.005 |
ols | -0.004 |
below | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -1.44e-03 |
Pos logit contributions | |
handed | +0.118 |
cash | +0.113 |
cand | +0.112 |
moderation | +0.106 |
dishes | +0.103 |
Neg logit contributions | |
above | -0.074 |
ary | -0.070 |
overed | -0.066 |
below | -0.065 |
behold | -0.061 |
Token | so |
Token ID | 523 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
handed | +0.002 |
cash | +0.002 |
cand | +0.002 |
moderation | +0.002 |
dishes | +0.002 |
Neg logit contributions | |
above | -0.002 |
ary | -0.002 |
overed | -0.002 |
below | -0.002 |
: | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
handed | +0.029 |
cash | +0.027 |
cand | +0.027 |
moderation | +0.025 |
dishes | +0.024 |
Neg logit contributions | |
above | -0.045 |
ary | -0.043 |
overed | -0.042 |
below | -0.041 |
ols | -0.040 |
Token | called |
Token ID | 1444 |
Feature activation | +5.45e-04 |
Pos logit contributions | |
ols | +0.022 |
above | +0.022 |
overed | +0.022 |
ores | +0.021 |
ary | +0.021 |
Neg logit contributions | |
handed | -0.020 |
cash | -0.020 |
cand | -0.020 |
toy | -0.020 |
pig | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
above | +0.001 |
ary | +0.001 |
overed | +0.001 |
below | +0.001 |
ols | +0.001 |
Neg logit contributions | |
handed | -0.001 |
cash | -0.001 |
cand | -0.001 |
moderation | -0.001 |
dishes | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | +3.47e-03 |
Pos logit contributions | |
above | +0.010 |
ary | +0.010 |
overed | +0.009 |
behold | +0.009 |
ols | +0.009 |
Neg logit contributions | |
handed | -0.014 |
cash | -0.014 |
cand | -0.013 |
handful | -0.013 |
toy | -0.013 |
Token | laundry |
Token ID | 25724 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
above | +0.007 |
below | +0.006 |
ary | +0.006 |
: | +0.006 |
behold | +0.006 |
Neg logit contributions | |
handed | -0.004 |
cash | -0.003 |
cand | -0.003 |
moderation | -0.003 |
lest | -0.003 |
Token | on |
Token ID | 319 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
handed | +0.038 |
cash | +0.037 |
cand | +0.036 |
moderation | +0.034 |
dishes | +0.033 |
Neg logit contributions | |
above | -0.031 |
ary | -0.030 |
overed | -0.029 |
below | -0.028 |
behold | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
handed | +0.024 |
cash | +0.023 |
cand | +0.022 |
moderation | +0.021 |
dishes | +0.020 |
Neg logit contributions | |
above | -0.023 |
ary | -0.022 |
overed | -0.021 |
below | -0.021 |
: | -0.020 |
Token | clothes |
Token ID | 8242 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
handed | +0.015 |
cand | +0.014 |
cash | +0.014 |
moderation | +0.013 |
handful | +0.012 |
Neg logit contributions | |
above | -0.026 |
ary | -0.025 |
below | -0.025 |
: | -0.024 |
overed | -0.024 |
Token | line |
Token ID | 1370 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
handed | +0.067 |
cash | +0.065 |
cand | +0.065 |
moderation | +0.064 |
redd | +0.061 |
Neg logit contributions | |
above | -0.032 |
below | -0.028 |
ary | -0.027 |
: | -0.026 |
overed | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -7.36e-03 |
Pos logit contributions | |
handed | +0.121 |
cash | +0.117 |
cand | +0.116 |
moderation | +0.111 |
dishes | +0.107 |
Neg logit contributions | |
above | -0.070 |
ary | -0.065 |
overed | -0.062 |
below | -0.062 |
: | -0.058 |
Token | " |
Token ID | 366 |
Feature activation | -8.75e-03 |
Pos logit contributions | |
handed | +0.009 |
cash | +0.009 |
cand | +0.008 |
moderation | +0.008 |
handful | +0.007 |
Neg logit contributions | |
above | -0.013 |
ary | -0.012 |
overed | -0.012 |
below | -0.012 |
behold | -0.012 |
Token | He |
Token ID | 1544 |
Feature activation | +9.63e-03 |
Pos logit contributions | |
cand | +0.016 |
handed | +0.015 |
cash | +0.015 |
dishes | +0.014 |
handful | +0.014 |
Neg logit contributions | |
above | -0.011 |
ary | -0.010 |
below | -0.010 |
behold | -0.010 |
overed | -0.009 |
Token | wants |
Token ID | 3382 |
Feature activation | +5.91e-03 |
Pos logit contributions | |
above | +0.012 |
: | +0.012 |
ary | +0.012 |
below | +0.011 |
ols | +0.011 |
Neg logit contributions | |
handed | -0.016 |
cash | -0.016 |
moderation | -0.015 |
cand | -0.015 |
redd | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
above | +0.008 |
ary | +0.007 |
below | +0.007 |
overed | +0.007 |
: | +0.007 |
Neg logit contributions | |
handed | -0.010 |
cash | -0.010 |
cand | -0.010 |
moderation | -0.009 |
handful | -0.009 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
handed | +0.006 |
cash | +0.006 |
cand | +0.006 |
moderation | +0.006 |
handful | +0.006 |
Neg logit contributions | |
above | -0.007 |
ary | -0.007 |
overed | -0.007 |
below | -0.007 |
ols | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -5.60e-03 |
Pos logit contributions | |
handed | +0.036 |
cand | +0.035 |
cash | +0.034 |
toy | +0.032 |
moderation | +0.032 |
Neg logit contributions | |
ary | -0.032 |
above | -0.032 |
overed | -0.030 |
ols | -0.030 |
behold | -0.029 |
Token | be |
Token ID | 307 |
Feature activation | +8.05e-03 |
Pos logit contributions | |
handed | +0.008 |
cash | +0.007 |
cand | +0.007 |
moderation | +0.007 |
toy | +0.007 |
Neg logit contributions | |
above | -0.009 |
overed | -0.008 |
ary | -0.008 |
below | -0.008 |
ols | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
above | +0.010 |
ary | +0.009 |
below | +0.009 |
overed | +0.009 |
: | +0.008 |
Neg logit contributions | |
handed | -0.014 |
cash | -0.014 |
cand | -0.014 |
moderation | -0.013 |
dishes | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
handed | +0.025 |
cash | +0.024 |
cand | +0.024 |
moderation | +0.022 |
dishes | +0.022 |
Neg logit contributions | |
above | -0.024 |
ary | -0.023 |
overed | -0.022 |
below | -0.022 |
behold | -0.021 |
Token | harbor |
Token ID | 25451 |
Feature activation | -6.33e-02 |
Pos logit contributions | |
handed | +0.018 |
cash | +0.017 |
cand | +0.017 |
moderation | +0.016 |
dishes | +0.015 |
Neg logit contributions | |
above | -0.017 |
ary | -0.016 |
overed | -0.016 |
below | -0.016 |
: | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
handed | +0.113 |
cash | +0.111 |
cand | +0.109 |
moderation | +0.104 |
dishes | +0.100 |
Neg logit contributions | |
above | -0.078 |
ary | -0.071 |
below | -0.070 |
overed | -0.067 |
: | -0.065 |
Token | thanked |
Token ID | 26280 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
handed | +0.016 |
cash | +0.015 |
cand | +0.015 |
moderation | +0.014 |
dishes | +0.014 |
Neg logit contributions | |
above | -0.014 |
ary | -0.014 |
overed | -0.013 |
below | -0.013 |
: | -0.012 |
Token | them |
Token ID | 606 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
above | +0.022 |
overed | +0.022 |
ary | +0.021 |
below | +0.020 |
brewing | +0.020 |
Neg logit contributions | |
cash | -0.018 |
cand | -0.018 |
handed | -0.017 |
moderation | -0.016 |
candy | -0.016 |
Token | all |
Token ID | 477 |
Feature activation | +5.36e-03 |
Pos logit contributions | |
handed | +0.029 |
cash | +0.027 |
cand | +0.027 |
moderation | +0.026 |
dishes | +0.025 |
Neg logit contributions | |
above | -0.015 |
ary | -0.014 |
below | -0.013 |
overed | -0.013 |
: | -0.013 |
Token | for |
Token ID | 329 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
above | +0.007 |
ary | +0.007 |
below | +0.007 |
: | +0.006 |
overed | +0.006 |
Neg logit contributions | |
handed | -0.009 |
cash | -0.009 |
cand | -0.009 |
moderation | -0.008 |
dishes | -0.008 |
Token | boat |
Token ID | 8848 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
handed | +0.012 |
cash | +0.011 |
cand | +0.011 |
moderation | +0.009 |
dishes | +0.009 |
Neg logit contributions | |
above | -0.026 |
ary | -0.025 |
overed | -0.024 |
below | -0.024 |
behold | -0.023 |
Token | moved |
Token ID | 3888 |
Feature activation | -6.13e-03 |
Pos logit contributions | |
handed | +0.034 |
cash | +0.033 |
cand | +0.033 |
toy | +0.030 |
handful | +0.030 |
Neg logit contributions | |
above | -0.026 |
ary | -0.025 |
overed | -0.024 |
below | -0.023 |
ols | -0.023 |
Token | quietly |
Token ID | 12703 |
Feature activation | -7.76e-03 |
Pos logit contributions | |
handed | +0.010 |
handful | +0.009 |
toy | +0.009 |
cand | +0.009 |
cash | +0.009 |
Neg logit contributions | |
ary | -0.007 |
overed | -0.007 |
ols | -0.007 |
above | -0.007 |
behold | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | -8.83e-03 |
Pos logit contributions | |
handed | +0.014 |
cash | +0.014 |
cand | +0.013 |
moderation | +0.013 |
dishes | +0.012 |
Neg logit contributions | |
above | -0.009 |
ary | -0.009 |
below | -0.008 |
overed | -0.008 |
: | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
handed | +0.014 |
cash | +0.013 |
cand | +0.013 |
moderation | +0.012 |
dishes | +0.012 |
Neg logit contributions | |
above | -0.013 |
ary | -0.012 |
below | -0.012 |
overed | -0.012 |
: | -0.011 |
Token | harbor |
Token ID | 25451 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
handed | +0.021 |
cash | +0.020 |
cand | +0.019 |
moderation | +0.018 |
handful | +0.017 |
Neg logit contributions | |
above | -0.022 |
ary | -0.020 |
below | -0.020 |
overed | -0.019 |
: | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -2.66e-03 |
Pos logit contributions | |
handed | +0.112 |
cash | +0.109 |
cand | +0.108 |
moderation | +0.104 |
dishes | +0.099 |
Neg logit contributions | |
above | -0.079 |
ary | -0.073 |
below | -0.071 |
overed | -0.069 |
: | -0.067 |
Token | It |
Token ID | 632 |
Feature activation | -7.45e-03 |
Pos logit contributions | |
handed | +0.004 |
cash | +0.003 |
cand | +0.003 |
moderation | +0.003 |
handful | +0.003 |
Neg logit contributions | |
above | -0.004 |
ary | -0.004 |
overed | -0.004 |
below | -0.004 |
brewing | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -2.73e-03 |
Pos logit contributions | |
handed | +0.011 |
cash | +0.011 |
cand | +0.011 |
toy | +0.010 |
handful | +0.010 |
Neg logit contributions | |
ary | -0.010 |
above | -0.010 |
overed | -0.010 |
ols | -0.009 |
ores | -0.009 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
handed | +0.003 |
cash | +0.003 |
cand | +0.003 |
toy | +0.003 |
handful | +0.003 |
Neg logit contributions | |
ary | -0.005 |
overed | -0.005 |
ols | -0.005 |
above | -0.005 |
below | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -3.34e-03 |
Pos logit contributions | |
handed | +0.032 |
cand | +0.031 |
toy | +0.030 |
cash | +0.029 |
candy | +0.029 |
Neg logit contributions | |
ary | -0.034 |
above | -0.032 |
ols | -0.032 |
behold | -0.031 |
overed | -0.031 |
Token | Another |
Token ID | 6023 |
Feature activation | +6.40e-03 |
Pos logit contributions | |
above | +0.012 |
ary | +0.011 |
overed | +0.011 |
below | +0.011 |
brewing | +0.011 |
Neg logit contributions | |
handed | -0.009 |
cash | -0.009 |
cand | -0.008 |
moderation | -0.008 |
These | -0.008 |
Token | boat |
Token ID | 8848 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
above | +0.012 |
ary | +0.012 |
below | +0.011 |
overed | +0.011 |
: | +0.011 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.007 |
cand | -0.007 |
moderation | -0.006 |
dishes | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -6.24e-04 |
Pos logit contributions | |
handed | +0.019 |
toy | +0.017 |
cand | +0.017 |
cash | +0.017 |
lest | +0.016 |
Neg logit contributions | |
ary | -0.016 |
above | -0.016 |
ores | -0.015 |
overed | -0.015 |
behold | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
handed | +0.001 |
cash | +0.001 |
cand | +0.001 |
toy | +0.001 |
handful | +0.001 |
Neg logit contributions | |
ary | -0.001 |
above | -0.001 |
overed | -0.001 |
behold | -0.001 |
ols | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
handed | +0.022 |
cand | +0.021 |
cash | +0.021 |
lest | +0.020 |
moderation | +0.019 |
Neg logit contributions | |
above | -0.015 |
below | -0.013 |
ary | -0.012 |
: | -0.012 |
overed | -0.012 |
Token | harbor |
Token ID | 25451 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
handed | +0.023 |
cand | +0.023 |
cash | +0.022 |
lest | +0.021 |
moderation | +0.021 |
Neg logit contributions | |
above | -0.021 |
below | -0.020 |
ary | -0.018 |
over | -0.018 |
: | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +5.69e-03 |
Pos logit contributions | |
handed | +0.116 |
cash | +0.112 |
cand | +0.111 |
moderation | +0.106 |
dishes | +0.103 |
Neg logit contributions | |
above | -0.071 |
ary | -0.066 |
below | -0.063 |
overed | -0.063 |
: | -0.059 |
Token | It |
Token ID | 632 |
Feature activation | -3.84e-03 |
Pos logit contributions | |
above | +0.010 |
ary | +0.009 |
overed | +0.009 |
below | +0.009 |
behold | +0.008 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.007 |
cand | -0.007 |
moderation | -0.006 |
dishes | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -2.79e-03 |
Pos logit contributions | |
toy | +0.004 |
handful | +0.004 |
plastic | +0.004 |
cand | +0.004 |
lest | +0.004 |
Neg logit contributions | |
overed | -0.007 |
ores | -0.007 |
ary | -0.006 |
ols | -0.006 |
above | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -1.82e-03 |
Pos logit contributions | |
toy | +0.003 |
cash | +0.002 |
cand | +0.002 |
plastic | +0.002 |
handed | +0.002 |
Neg logit contributions | |
ary | -0.005 |
overed | -0.005 |
above | -0.005 |
ols | -0.005 |
below | -0.005 |
Token | bigger |
Token ID | 5749 |
Feature activation | +9.05e-03 |
Pos logit contributions | |
handed | +0.002 |
cash | +0.002 |
cand | +0.002 |
moderation | +0.002 |
dishes | +0.002 |
Neg logit contributions | |
above | -0.003 |
ary | -0.003 |
overed | -0.003 |
below | -0.003 |
behold | -0.003 |
Token | boat |
Token ID | 8848 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
handed | +0.002 |
cash | +0.002 |
cand | +0.002 |
moderation | +0.002 |
dishes | +0.002 |
Neg logit contributions | |
above | -0.003 |
ary | -0.003 |
overed | -0.003 |
below | -0.003 |
behold | -0.003 |
Token | zoom |
Token ID | 19792 |
Feature activation | +8.52e-03 |
Pos logit contributions | |
cash | +0.023 |
handed | +0.023 |
cand | +0.023 |
toy | +0.022 |
handful | +0.021 |
Neg logit contributions | |
ary | -0.023 |
above | -0.023 |
ores | -0.022 |
overed | -0.022 |
ols | -0.021 |
Token | ed |
Token ID | 276 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
above | +0.014 |
ary | +0.013 |
below | +0.013 |
ols | +0.013 |
behold | +0.012 |
Neg logit contributions | |
handed | -0.011 |
cash | -0.010 |
cand | -0.010 |
toy | -0.009 |
handful | -0.009 |
Token | around |
Token ID | 1088 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
handed | +0.034 |
cash | +0.034 |
cand | +0.033 |
handful | +0.031 |
toy | +0.031 |
Neg logit contributions | |
above | -0.021 |
ary | -0.021 |
overed | -0.020 |
below | -0.019 |
behold | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
handed | +0.034 |
cash | +0.033 |
cand | +0.032 |
handful | +0.030 |
toy | +0.030 |
Neg logit contributions | |
above | -0.032 |
ary | -0.032 |
overed | -0.030 |
ols | -0.029 |
below | -0.029 |
Token | harbor |
Token ID | 25451 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
handed | +0.026 |
cash | +0.024 |
cand | +0.024 |
dishes | +0.022 |
moderation | +0.022 |
Neg logit contributions | |
above | -0.026 |
ary | -0.025 |
overed | -0.025 |
below | -0.023 |
behold | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +6.30e-03 |
Pos logit contributions | |
handed | +0.105 |
cash | +0.101 |
cand | +0.099 |
moderation | +0.096 |
dishes | +0.091 |
Neg logit contributions | |
above | -0.083 |
ary | -0.077 |
overed | -0.074 |
below | -0.074 |
: | -0.070 |
Token | with |
Token ID | 351 |
Feature activation | -3.14e-03 |
Pos logit contributions | |
above | +0.009 |
ary | +0.008 |
below | +0.008 |
overed | +0.008 |
: | +0.007 |
Neg logit contributions | |
handed | -0.011 |
cand | -0.010 |
cash | -0.010 |
moderation | -0.010 |
dishes | -0.009 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
handed | +0.005 |
cash | +0.004 |
cand | +0.004 |
moderation | +0.004 |
dishes | +0.004 |
Neg logit contributions | |
above | -0.005 |
ary | -0.005 |
below | -0.005 |
overed | -0.005 |
behold | -0.004 |
Token | my |
Token ID | 1820 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
handed | +0.019 |
cash | +0.018 |
cand | +0.018 |
moderation | +0.017 |
dishes | +0.016 |
Neg logit contributions | |
above | -0.024 |
ary | -0.023 |
below | -0.022 |
: | -0.022 |
overed | -0.022 |
Token | steering |
Token ID | 19702 |
Feature activation | -1.20e-04 |
Pos logit contributions | |
handed | +0.040 |
cash | +0.038 |
cand | +0.037 |
moderation | +0.035 |
dishes | +0.034 |
Neg logit contributions | |
above | -0.033 |
ary | -0.031 |
overed | -0.030 |
below | -0.029 |
: | -0.028 |
Token | rock |
Token ID | 3881 |
Feature activation | +6.45e-03 |
Pos logit contributions | |
above | +0.019 |
ary | +0.018 |
overed | +0.018 |
below | +0.018 |
: | +0.017 |
Neg logit contributions | |
handed | -0.013 |
cash | -0.012 |
cand | -0.012 |
moderation | -0.011 |
dishes | -0.010 |
Token | far |
Token ID | 1290 |
Feature activation | +3.33e-04 |
Pos logit contributions | |
ary | +0.007 |
behold | +0.007 |
overed | +0.007 |
above | +0.007 |
Jas | +0.007 |
Neg logit contributions | |
handed | -0.011 |
toy | -0.010 |
cash | -0.010 |
cand | -0.010 |
dishes | -0.010 |
Token | away |
Token ID | 1497 |
Feature activation | +7.31e-03 |
Pos logit contributions | |
above | +0.001 |
ary | +0.001 |
overed | +0.001 |
behold | +0.000 |
below | +0.000 |
Neg logit contributions | |
handed | -0.000 |
cash | -0.000 |
cand | -0.000 |
toy | -0.000 |
dishes | -0.000 |
Token | in |
Token ID | 287 |
Feature activation | -8.90e-03 |
Pos logit contributions | |
ary | +0.010 |
overed | +0.009 |
above | +0.009 |
ols | +0.009 |
behold | +0.008 |
Neg logit contributions | |
handed | -0.012 |
cash | -0.011 |
toy | -0.011 |
cand | -0.011 |
dishes | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
cand | +0.017 |
cash | +0.017 |
handed | +0.017 |
lest | +0.016 |
These | +0.016 |
Neg logit contributions | |
above | -0.010 |
below | -0.009 |
behold | -0.008 |
over | -0.008 |
ary | -0.008 |
Token | sea |
Token ID | 5417 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
handed | +0.024 |
cash | +0.024 |
cand | +0.023 |
moderation | +0.021 |
handful | +0.021 |
Neg logit contributions | |
above | -0.025 |
below | -0.022 |
ary | -0.022 |
: | -0.021 |
overed | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -5.84e-03 |
Pos logit contributions | |
handed | +0.114 |
cash | +0.109 |
cand | +0.108 |
moderation | +0.103 |
dishes | +0.101 |
Neg logit contributions | |
above | -0.071 |
ary | -0.068 |
overed | -0.065 |
below | -0.062 |
behold | -0.061 |
Token | He |
Token ID | 679 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
handed | +0.009 |
moderation | +0.008 |
cand | +0.008 |
cash | +0.008 |
lest | +0.007 |
Neg logit contributions | |
above | -0.009 |
ary | -0.009 |
below | -0.009 |
: | -0.009 |
overed | -0.008 |
Token | thought |
Token ID | 1807 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
cash | +0.006 |
toy | +0.006 |
cand | +0.006 |
handful | +0.005 |
candy | +0.005 |
Neg logit contributions | |
above | -0.012 |
ores | -0.012 |
overed | -0.012 |
ols | -0.012 |
below | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | +5.98e-03 |
Pos logit contributions | |
above | +0.017 |
ary | +0.016 |
overed | +0.015 |
below | +0.015 |
ols | +0.015 |
Neg logit contributions | |
handed | -0.017 |
cand | -0.016 |
cash | -0.016 |
moderation | -0.015 |
dishes | -0.015 |
Token | would |
Token ID | 561 |
Feature activation | +2.81e-03 |
Pos logit contributions | |
above | +0.008 |
overed | +0.008 |
ary | +0.008 |
ores | +0.008 |
below | +0.008 |
Neg logit contributions | |
cand | -0.009 |
handed | -0.009 |
toy | -0.009 |
cash | -0.008 |
dishes | -0.008 |
Token | boat |
Token ID | 8848 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
handed | +0.010 |
cash | +0.010 |
cand | +0.009 |
dishes | +0.008 |
toy | +0.008 |
Neg logit contributions | |
above | -0.019 |
ary | -0.019 |
overed | -0.019 |
below | -0.018 |
ols | -0.018 |
Token | had |
Token ID | 550 |
Feature activation | -9.56e-03 |
Pos logit contributions | |
handed | +0.044 |
cash | +0.043 |
cand | +0.042 |
toy | +0.040 |
handful | +0.039 |
Neg logit contributions | |
above | -0.036 |
ary | -0.035 |
overed | -0.033 |
ores | -0.033 |
ols | -0.032 |
Token | escaped |
Token ID | 13537 |
Feature activation | +8.53e-03 |
Pos logit contributions | |
handed | +0.014 |
cash | +0.014 |
cand | +0.013 |
moderation | +0.013 |
dishes | +0.012 |
Neg logit contributions | |
above | -0.014 |
ary | -0.014 |
overed | -0.013 |
below | -0.013 |
: | -0.012 |
Token | from |
Token ID | 422 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
ary | +0.011 |
overed | +0.011 |
ols | +0.011 |
behold | +0.010 |
above | +0.010 |
Neg logit contributions | |
handed | -0.013 |
cash | -0.012 |
toy | -0.012 |
handful | -0.012 |
cand | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +2.30e-03 |
Pos logit contributions | |
ary | +0.038 |
overed | +0.036 |
ols | +0.035 |
above | +0.035 |
: | +0.033 |
Neg logit contributions | |
handed | -0.030 |
cash | -0.028 |
moderation | -0.028 |
cand | -0.027 |
toy | -0.027 |
Token | harbor |
Token ID | 25451 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
ary | +0.004 |
above | +0.004 |
overed | +0.004 |
ols | +0.004 |
: | +0.004 |
Neg logit contributions | |
handed | -0.003 |
cash | -0.003 |
cand | -0.002 |
dishes | -0.002 |
toy | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -9.87e-03 |
Pos logit contributions | |
handed | +0.112 |
cash | +0.109 |
cand | +0.108 |
moderation | +0.103 |
dishes | +0.099 |
Neg logit contributions | |
above | -0.074 |
ary | -0.068 |
below | -0.066 |
overed | -0.065 |
: | -0.061 |
Token | was |
Token ID | 373 |
Feature activation | +2.95e-03 |
Pos logit contributions | |
handed | +0.016 |
cand | +0.015 |
cash | +0.015 |
moderation | +0.014 |
toy | +0.014 |
Neg logit contributions | |
above | -0.013 |
ary | -0.013 |
overed | -0.012 |
ols | -0.012 |
below | -0.012 |
Token | now |
Token ID | 783 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
above | +0.005 |
ary | +0.005 |
ols | +0.005 |
overed | +0.005 |
below | +0.005 |
Neg logit contributions | |
handed | -0.003 |
cash | -0.003 |
cand | -0.003 |
toy | -0.003 |
handful | -0.003 |
Token | safe |
Token ID | 3338 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
handed | +0.018 |
cash | +0.017 |
cand | +0.017 |
moderation | +0.016 |
handful | +0.015 |
Neg logit contributions | |
above | -0.022 |
ary | -0.022 |
overed | -0.021 |
below | -0.020 |
ols | -0.020 |
Token | in |
Token ID | 287 |
Feature activation | -5.04e-03 |
Pos logit contributions | |
handed | +0.017 |
cand | +0.016 |
cash | +0.016 |
toy | +0.015 |
dishes | +0.015 |
Neg logit contributions | |
ary | -0.013 |
above | -0.011 |
behold | -0.011 |
overed | -0.011 |
ols | -0.011 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
toy | +0.007 |
cash | +0.007 |
cand | +0.007 |
plastic | +0.006 |
handed | +0.006 |
Neg logit contributions | |
overed | -0.011 |
ary | -0.011 |
above | -0.011 |
ols | -0.011 |
behold | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -4.69e-03 |
Pos logit contributions | |
cand | +0.027 |
handed | +0.027 |
toy | +0.027 |
candy | +0.026 |
cash | +0.025 |
Neg logit contributions | |
ary | -0.035 |
ols | -0.033 |
behold | -0.033 |
above | -0.032 |
overed | -0.032 |
Token | be |
Token ID | 307 |
Feature activation | +5.10e-03 |
Pos logit contributions | |
handed | +0.007 |
cash | +0.007 |
cand | +0.006 |
moderation | +0.006 |
toy | +0.006 |
Neg logit contributions | |
above | -0.007 |
overed | -0.007 |
ary | -0.006 |
below | -0.006 |
ols | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
above | +0.006 |
ary | +0.006 |
overed | +0.006 |
below | +0.006 |
behold | +0.005 |
Neg logit contributions | |
handed | -0.009 |
cash | -0.009 |
cand | -0.009 |
moderation | -0.008 |
dishes | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
handed | +0.023 |
cash | +0.022 |
cand | +0.022 |
moderation | +0.021 |
dishes | +0.020 |
Neg logit contributions | |
above | -0.021 |
ary | -0.019 |
below | -0.019 |
overed | -0.019 |
: | -0.018 |
Token | port |
Token ID | 2493 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
handed | +0.015 |
cash | +0.014 |
cand | +0.014 |
moderation | +0.013 |
dishes | +0.013 |
Neg logit contributions | |
above | -0.018 |
ary | -0.017 |
overed | -0.016 |
below | -0.016 |
behold | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -4.55e-03 |
Pos logit contributions | |
handed | +0.117 |
cash | +0.114 |
cand | +0.113 |
moderation | +0.107 |
handful | +0.103 |
Neg logit contributions | |
above | -0.069 |
ary | -0.063 |
below | -0.061 |
overed | -0.058 |
: | -0.057 |
Token | The |
Token ID | 383 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
handed | +0.007 |
cand | +0.007 |
cash | +0.007 |
moderation | +0.006 |
dishes | +0.006 |
Neg logit contributions | |
above | -0.007 |
ary | -0.006 |
below | -0.006 |
overed | -0.006 |
: | -0.006 |
Token | boat |
Token ID | 8848 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
handed | +0.014 |
cash | +0.014 |
cand | +0.013 |
dishes | +0.012 |
moderation | +0.012 |
Neg logit contributions | |
above | -0.023 |
ary | -0.022 |
overed | -0.022 |
below | -0.021 |
behold | -0.021 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.64e-03 |
Pos logit contributions | |
handed | +0.036 |
cash | +0.035 |
cand | +0.035 |
toy | +0.033 |
dishes | +0.031 |
Neg logit contributions | |
above | -0.031 |
ary | -0.031 |
overed | -0.030 |
ols | -0.028 |
ores | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | +3.62e-03 |
Pos logit contributions | |
above | +0.003 |
ary | +0.003 |
overed | +0.003 |
below | +0.003 |
ols | +0.003 |
Neg logit contributions | |
handed | -0.004 |
cand | -0.004 |
cash | -0.004 |
moderation | -0.004 |
dishes | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | -2.32e-03 |
Pos logit contributions | |
above | +0.018 |
overed | +0.018 |
ary | +0.018 |
ores | +0.017 |
below | +0.017 |
Neg logit contributions | |
handed | -0.019 |
cash | -0.019 |
cand | -0.019 |
toy | -0.018 |
handful | -0.017 |
Token | been |
Token ID | 587 |
Feature activation | -8.39e-03 |
Pos logit contributions | |
handed | +0.004 |
cash | +0.003 |
cand | +0.003 |
moderation | +0.003 |
dishes | +0.003 |
Neg logit contributions | |
above | -0.003 |
ary | -0.003 |
below | -0.003 |
overed | -0.003 |
: | -0.003 |
Token | playing |
Token ID | 2712 |
Feature activation | -7.19e-03 |
Pos logit contributions | |
handed | +0.013 |
cash | +0.012 |
cand | +0.012 |
moderation | +0.011 |
dishes | +0.011 |
Neg logit contributions | |
above | -0.012 |
ary | -0.012 |
overed | -0.011 |
below | -0.011 |
: | -0.011 |
Token | around |
Token ID | 1088 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
handed | +0.012 |
cash | +0.012 |
cand | +0.012 |
moderation | +0.011 |
dishes | +0.011 |
Neg logit contributions | |
above | -0.009 |
ary | -0.009 |
overed | -0.008 |
below | -0.008 |
behold | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
handed | +0.032 |
cash | +0.030 |
cand | +0.029 |
moderation | +0.028 |
dishes | +0.028 |
Neg logit contributions | |
ary | -0.029 |
above | -0.029 |
overed | -0.029 |
ols | -0.027 |
behold | -0.027 |
Token | port |
Token ID | 2493 |
Feature activation | -6.13e-02 |
Pos logit contributions | |
handed | +0.024 |
cash | +0.022 |
cand | +0.022 |
moderation | +0.020 |
dishes | +0.020 |
Neg logit contributions | |
above | -0.025 |
ary | -0.024 |
overed | -0.023 |
below | -0.022 |
behold | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -7.21e-03 |
Pos logit contributions | |
handed | +0.104 |
cash | +0.100 |
cand | +0.099 |
moderation | +0.093 |
dishes | +0.091 |
Neg logit contributions | |
above | -0.080 |
ary | -0.075 |
overed | -0.072 |
below | -0.072 |
: | -0.067 |
Token | it |
Token ID | 340 |
Feature activation | -6.30e-03 |
Pos logit contributions | |
handed | +0.012 |
cash | +0.011 |
cand | +0.011 |
moderation | +0.010 |
dishes | +0.010 |
Neg logit contributions | |
above | -0.010 |
ary | -0.009 |
overed | -0.009 |
below | -0.009 |
behold | -0.008 |
Token | had |
Token ID | 550 |
Feature activation | -1.23e-03 |
Pos logit contributions | |
handed | +0.010 |
cash | +0.010 |
cand | +0.010 |
toy | +0.009 |
dishes | +0.009 |
Neg logit contributions | |
above | -0.008 |
ary | -0.008 |
overed | -0.008 |
below | -0.007 |
ols | -0.007 |
Token | made |
Token ID | 925 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
handed | +0.002 |
cash | +0.002 |
cand | +0.002 |
moderation | +0.002 |
dishes | +0.002 |
Neg logit contributions | |
above | -0.002 |
ary | -0.002 |
overed | -0.002 |
below | -0.002 |
: | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -2.29e-03 |
Pos logit contributions | |
handed | +0.023 |
cash | +0.022 |
cand | +0.022 |
moderation | +0.020 |
dishes | +0.020 |
Neg logit contributions | |
above | -0.024 |
ary | -0.023 |
overed | -0.022 |
below | -0.022 |
: | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
above | +0.002 |
ary | +0.002 |
below | +0.002 |
behold | +0.002 |
overed | +0.002 |
Neg logit contributions | |
handed | -0.003 |
cand | -0.003 |
cash | -0.003 |
moderation | -0.003 |
lest | -0.003 |
Token | edge |
Token ID | 5743 |
Feature activation | -2.32e-03 |
Pos logit contributions | |
ary | +0.019 |
above | +0.018 |
overed | +0.018 |
ols | +0.017 |
behold | +0.017 |
Neg logit contributions | |
handed | -0.015 |
cash | -0.015 |
cand | -0.014 |
dishes | -0.014 |
toy | -0.013 |
Token | of |
Token ID | 286 |
Feature activation | -1.60e-03 |
Pos logit contributions | |
handed | +0.004 |
cash | +0.004 |
cand | +0.004 |
moderation | +0.004 |
dishes | +0.003 |
Neg logit contributions | |
above | -0.003 |
ary | -0.003 |
overed | -0.003 |
ols | -0.003 |
below | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +1.36e-03 |
Pos logit contributions | |
handed | +0.003 |
cash | +0.002 |
cand | +0.002 |
moderation | +0.002 |
dishes | +0.002 |
Neg logit contributions | |
above | -0.002 |
ary | -0.002 |
below | -0.002 |
overed | -0.002 |
behold | -0.002 |
Token | shore |
Token ID | 15191 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
ary | +0.002 |
above | +0.002 |
overed | +0.002 |
ols | +0.002 |
behold | +0.002 |
Neg logit contributions | |
handed | -0.002 |
cash | -0.002 |
cand | -0.002 |
dishes | -0.002 |
toy | -0.001 |
Token | line |
Token ID | 1370 |
Feature activation | -6.13e-02 |
Pos logit contributions | |
handed | +0.079 |
cash | +0.077 |
cand | +0.076 |
moderation | +0.072 |
redd | +0.069 |
Neg logit contributions | |
above | -0.055 |
below | -0.050 |
ary | -0.050 |
: | -0.048 |
overed | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | +6.88e-03 |
Pos logit contributions | |
handed | +0.108 |
cash | +0.105 |
cand | +0.104 |
moderation | +0.098 |
dishes | +0.095 |
Neg logit contributions | |
above | -0.077 |
ary | -0.072 |
below | -0.070 |
overed | -0.069 |
: | -0.066 |
Token | just |
Token ID | 655 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
above | +0.009 |
ary | +0.008 |
below | +0.008 |
overed | +0.008 |
behold | +0.007 |
Neg logit contributions | |
handed | -0.012 |
cand | -0.012 |
cash | -0.012 |
moderation | -0.011 |
dishes | -0.011 |
Token | stood |
Token ID | 6204 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
above | +0.024 |
ary | +0.023 |
overed | +0.022 |
below | +0.021 |
ols | +0.021 |
Neg logit contributions | |
handed | -0.035 |
cash | -0.034 |
cand | -0.033 |
moderation | -0.031 |
dishes | -0.031 |
Token | there |
Token ID | 612 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
ary | +0.027 |
ols | +0.026 |
oline | +0.024 |
behold | +0.024 |
overed | +0.024 |
Neg logit contributions | |
handed | -0.025 |
handful | -0.024 |
cash | -0.024 |
moderation | -0.023 |
toy | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +4.09e-03 |
Pos logit contributions | |
handed | +0.026 |
cash | +0.025 |
cand | +0.024 |
moderation | +0.023 |
dishes | +0.023 |
Neg logit contributions | |
above | -0.016 |
ary | -0.015 |
overed | -0.014 |
below | -0.014 |
: | -0.013 |
Token | outside |
Token ID | 2354 |
Feature activation | +2.07e-03 |
Pos logit contributions | |
handed | +0.010 |
cash | +0.010 |
toy | +0.010 |
cand | +0.009 |
handful | +0.009 |
Neg logit contributions | |
overed | -0.009 |
behold | -0.009 |
above | -0.008 |
ary | -0.008 |
ols | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +4.75e-03 |
Pos logit contributions | |
above | +0.003 |
overed | +0.003 |
ary | +0.003 |
behold | +0.003 |
ols | +0.003 |
Neg logit contributions | |
handed | -0.003 |
cash | -0.003 |
cand | -0.003 |
toy | -0.003 |
dishes | -0.003 |
Token | Her |
Token ID | 2332 |
Feature activation | +9.69e-04 |
Pos logit contributions | |
above | +0.008 |
ary | +0.008 |
overed | +0.007 |
below | +0.007 |
: | +0.007 |
Neg logit contributions | |
handed | -0.006 |
cash | -0.006 |
cand | -0.006 |
moderation | -0.005 |
dishes | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.30e-03 |
Pos logit contributions | |
above | +0.001 |
ary | +0.001 |
overed | +0.001 |
below | +0.001 |
behold | +0.001 |
Neg logit contributions | |
handed | -0.001 |
cash | -0.001 |
cand | -0.001 |
moderation | -0.001 |
dishes | -0.001 |
Token | my |
Token ID | 1820 |
Feature activation | -3.19e-03 |
Pos logit contributions | |
above | +0.002 |
ary | +0.002 |
overed | +0.002 |
below | +0.002 |
behold | +0.002 |
Neg logit contributions | |
handed | -0.002 |
cash | -0.002 |
cand | -0.002 |
moderation | -0.002 |
dishes | -0.001 |
Token | kne |
Token ID | 24813 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
handed | +0.005 |
cash | +0.005 |
cand | +0.005 |
moderation | +0.005 |
dishes | +0.005 |
Neg logit contributions | |
above | -0.004 |
ary | -0.004 |
overed | -0.004 |
below | -0.004 |
behold | -0.004 |
Token | eled |
Token ID | 18449 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
above | +0.065 |
ary | +0.065 |
overed | +0.062 |
below | +0.060 |
ols | +0.059 |
Neg logit contributions | |
handed | -0.074 |
cash | -0.071 |
cand | -0.069 |
moderation | -0.066 |
handful | -0.065 |
Token | beside |
Token ID | 13970 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
handed | +0.027 |
cash | +0.026 |
cand | +0.026 |
moderation | +0.025 |
dishes | +0.024 |
Neg logit contributions | |
above | -0.022 |
ary | -0.021 |
overed | -0.020 |
below | -0.020 |
: | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | +2.14e-03 |
Pos logit contributions | |
above | +0.018 |
ary | +0.017 |
below | +0.017 |
overed | +0.016 |
: | +0.016 |
Neg logit contributions | |
handed | -0.016 |
cand | -0.014 |
cash | -0.014 |
moderation | -0.013 |
dishes | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -2.86e-03 |
Pos logit contributions | |
above | +0.003 |
ary | +0.003 |
below | +0.003 |
overed | +0.003 |
: | +0.003 |
Neg logit contributions | |
handed | -0.003 |
cash | -0.003 |
cand | -0.003 |
moderation | -0.003 |
dishes | -0.003 |
Token | showed |
Token ID | 3751 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
handed | +0.005 |
cand | +0.005 |
cash | +0.005 |
moderation | +0.005 |
dishes | +0.004 |
Neg logit contributions | |
above | -0.004 |
ary | -0.004 |
below | -0.003 |
overed | -0.003 |
: | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -4.14e-03 |
Pos logit contributions | |
above | +0.008 |
ary | +0.007 |
overed | +0.007 |
below | +0.007 |
behold | +0.007 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.006 |
cand | -0.006 |
moderation | -0.006 |
dishes | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
handed | +0.006 |
cash | +0.005 |
moderation | +0.004 |
cand | +0.004 |
toy | +0.004 |
Neg logit contributions | |
above | -0.007 |
overed | -0.007 |
ary | -0.007 |
ols | -0.006 |
below | -0.006 |
Token | He |
Token ID | 1544 |
Feature activation | -6.09e-03 |
Pos logit contributions | |
handed | +0.018 |
cash | +0.017 |
cand | +0.017 |
moderation | +0.016 |
dishes | +0.016 |
Neg logit contributions | |
above | -0.020 |
ary | -0.019 |
overed | -0.019 |
below | -0.019 |
: | -0.018 |
Token | took |
Token ID | 1718 |
Feature activation | -9.14e-03 |
Pos logit contributions | |
cash | +0.009 |
cand | +0.009 |
handed | +0.008 |
toy | +0.008 |
handful | +0.008 |
Neg logit contributions | |
above | -0.009 |
ols | -0.009 |
overed | -0.009 |
ary | -0.009 |
ores | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +1.99e-04 |
Pos logit contributions | |
handed | +0.014 |
cash | +0.013 |
cand | +0.013 |
moderation | +0.012 |
dishes | +0.012 |
Neg logit contributions | |
above | -0.014 |
ary | -0.013 |
below | -0.013 |
overed | -0.012 |
over | -0.012 |
Token | pr |
Token ID | 778 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
above | +0.000 |
ary | +0.000 |
: | +0.000 |
below | +0.000 |
over | +0.000 |
Neg logit contributions | |
handed | -0.000 |
moderation | -0.000 |
Your | -0.000 |
cash | -0.000 |
cand | -0.000 |
Token | unes |
Token ID | 4015 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
above | +0.060 |
ary | +0.056 |
overed | +0.054 |
below | +0.054 |
behold | +0.051 |
Neg logit contributions | |
handed | -0.079 |
cash | -0.076 |
cand | -0.075 |
moderation | -0.071 |
dishes | -0.069 |
Token | home |
Token ID | 1363 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
above | +0.028 |
ary | +0.026 |
below | +0.025 |
overed | +0.023 |
: | +0.023 |
Neg logit contributions | |
handed | -0.048 |
cash | -0.047 |
cand | -0.045 |
moderation | -0.045 |
dishes | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | -2.88e-03 |
Pos logit contributions | |
handed | +0.026 |
cash | +0.025 |
cand | +0.025 |
moderation | +0.024 |
redd | +0.023 |
Neg logit contributions | |
above | -0.015 |
ary | -0.014 |
below | -0.013 |
: | -0.013 |
overed | -0.013 |
Token | placed |
Token ID | 4624 |
Feature activation | -1.66e-03 |
Pos logit contributions | |
handed | +0.005 |
cash | +0.005 |
cand | +0.005 |
moderation | +0.004 |
dishes | +0.004 |
Neg logit contributions | |
above | -0.004 |
ary | -0.003 |
below | -0.003 |
overed | -0.003 |
behold | -0.003 |
Token | them |
Token ID | 606 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
handed | +0.003 |
cash | +0.003 |
cand | +0.003 |
moderation | +0.003 |
dishes | +0.003 |
Neg logit contributions | |
above | -0.002 |
ary | -0.002 |
below | -0.001 |
overed | -0.001 |
: | -0.001 |
Token | remove |
Token ID | 4781 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
handed | +0.004 |
cash | +0.004 |
cand | +0.004 |
moderation | +0.003 |
handful | +0.003 |
Neg logit contributions | |
above | -0.004 |
ary | -0.004 |
below | -0.004 |
overed | -0.004 |
behold | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | -6.45e-03 |
Pos logit contributions | |
above | +0.016 |
below | +0.014 |
over | +0.014 |
ary | +0.013 |
: | +0.013 |
Neg logit contributions | |
handed | -0.018 |
cash | -0.017 |
cand | -0.016 |
moderation | -0.016 |
lest | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +9.98e-03 |
Pos logit contributions | |
handed | +0.014 |
cash | +0.014 |
cand | +0.013 |
moderation | +0.013 |
redd | +0.013 |
Neg logit contributions | |
above | -0.006 |
below | -0.005 |
ary | -0.005 |
over | -0.005 |
: | -0.005 |
Token | but |
Token ID | 475 |
Feature activation | -1.75e-03 |
Pos logit contributions | |
above | +0.015 |
ary | +0.014 |
below | +0.014 |
: | +0.013 |
over | +0.013 |
Neg logit contributions | |
handed | -0.016 |
cash | -0.015 |
cand | -0.014 |
moderation | -0.013 |
handful | -0.013 |
Token | he |
Token ID | 339 |
Feature activation | -5.27e-03 |
Pos logit contributions | |
handed | +0.002 |
cash | +0.002 |
cand | +0.002 |
moderation | +0.002 |
handful | +0.002 |
Neg logit contributions | |
above | -0.003 |
ary | -0.003 |
below | -0.003 |
overed | -0.003 |
: | -0.003 |
Token | didn |
Token ID | 1422 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
cand | +0.007 |
handed | +0.007 |
cash | +0.007 |
toy | +0.007 |
moderation | +0.007 |
Neg logit contributions | |
above | -0.009 |
overed | -0.008 |
below | -0.008 |
ols | -0.008 |
ary | -0.008 |
Token | 't |
Token ID | 470 |
Feature activation | +4.19e-03 |
Pos logit contributions | |
above | +0.077 |
overed | +0.071 |
below | +0.070 |
behold | +0.068 |
ary | +0.067 |
Neg logit contributions | |
handed | -0.065 |
cash | -0.060 |
cand | -0.056 |
These | -0.055 |
moderation | -0.055 |
Token | know |
Token ID | 760 |
Feature activation | -2.64e-03 |
Pos logit contributions | |
above | +0.007 |
ary | +0.007 |
overed | +0.006 |
below | +0.006 |
behold | +0.006 |
Neg logit contributions | |
handed | -0.006 |
cash | -0.005 |
cand | -0.005 |
moderation | -0.005 |
dishes | -0.005 |
Token | how |
Token ID | 703 |
Feature activation | +9.58e-03 |
Pos logit contributions | |
handed | +0.004 |
cash | +0.004 |
cand | +0.004 |
moderation | +0.004 |
dishes | +0.004 |
Neg logit contributions | |
above | -0.004 |
ary | -0.003 |
below | -0.003 |
overed | -0.003 |
: | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +6.34e-04 |
Pos logit contributions | |
above | +0.011 |
ary | +0.011 |
overed | +0.010 |
below | +0.010 |
behold | +0.010 |
Neg logit contributions | |
handed | -0.017 |
cash | -0.017 |
cand | -0.016 |
moderation | -0.016 |
dishes | -0.015 |
Token | He |
Token ID | 679 |
Feature activation | +1.52e-04 |
Pos logit contributions | |
above | +0.001 |
ary | +0.001 |
below | +0.001 |
: | +0.001 |
overed | +0.001 |
Neg logit contributions | |
handed | -0.001 |
cand | -0.001 |
cash | -0.001 |
moderation | -0.001 |
lest | -0.001 |
Token | new |
Token ID | 649 |
Feature activation | +4.38e-03 |
Pos logit contributions | |
above | +0.024 |
ary | +0.024 |
overed | +0.023 |
below | +0.022 |
behold | +0.022 |
Neg logit contributions | |
handed | -0.019 |
cash | -0.018 |
cand | -0.018 |
moderation | -0.016 |
dishes | -0.016 |
Token | things |
Token ID | 1243 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
above | +0.009 |
ary | +0.009 |
overed | +0.009 |
below | +0.009 |
: | +0.009 |
Neg logit contributions | |
handed | -0.004 |
cash | -0.003 |
cand | -0.003 |
moderation | -0.003 |
dishes | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -8.80e-03 |
Pos logit contributions | |
above | +0.015 |
ary | +0.015 |
overed | +0.014 |
below | +0.014 |
behold | +0.014 |
Neg logit contributions | |
handed | -0.021 |
cand | -0.021 |
cash | -0.020 |
moderation | -0.019 |
dishes | -0.019 |
Token | read |
Token ID | 1100 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
handed | +0.014 |
cash | +0.013 |
cand | +0.013 |
moderation | +0.012 |
handful | +0.012 |
Neg logit contributions | |
above | -0.013 |
ary | -0.012 |
below | -0.012 |
: | -0.011 |
behold | -0.011 |
Token | many |
Token ID | 867 |
Feature activation | +3.79e-03 |
Pos logit contributions | |
above | +0.035 |
ary | +0.034 |
overed | +0.034 |
below | +0.032 |
brewing | +0.031 |
Neg logit contributions | |
cand | -0.024 |
cash | -0.023 |
handed | -0.022 |
candy | -0.021 |
dishes | -0.021 |
Token | books |
Token ID | 3835 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
above | +0.007 |
ary | +0.007 |
overed | +0.007 |
below | +0.007 |
brewing | +0.006 |
Neg logit contributions | |
handed | -0.004 |
cand | -0.004 |
cash | -0.004 |
moderation | -0.004 |
dishes | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +7.02e-03 |
Pos logit contributions | |
above | +0.059 |
overed | +0.058 |
ary | +0.056 |
behold | +0.055 |
brewing | +0.054 |
Neg logit contributions | |
handed | -0.073 |
cand | -0.071 |
cash | -0.070 |
toy | -0.065 |
candy | -0.064 |
Token | She |
Token ID | 1375 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
above | +0.011 |
ary | +0.011 |
below | +0.010 |
overed | +0.010 |
: | +0.010 |
Neg logit contributions | |
handed | -0.010 |
cash | -0.010 |
cand | -0.009 |
moderation | -0.009 |
dishes | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
ols | +0.031 |
above | +0.031 |
overed | +0.030 |
ores | +0.030 |
below | +0.029 |
Neg logit contributions | |
cash | -0.024 |
cand | -0.023 |
toy | -0.022 |
handed | -0.021 |
candy | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -3.60e-03 |
Pos logit contributions | |
above | +0.022 |
ary | +0.021 |
overed | +0.021 |
below | +0.020 |
ols | +0.020 |
Neg logit contributions | |
handed | -0.011 |
cash | -0.011 |
cand | -0.011 |
moderation | -0.010 |
dishes | -0.009 |
Token | brown |
Token ID | 7586 |
Feature activation | +7.46e-03 |
Pos logit contributions | |
handed | +0.004 |
cash | +0.004 |
cand | +0.004 |
moderation | +0.004 |
dishes | +0.003 |
Neg logit contributions | |
above | -0.007 |
ary | -0.006 |
below | -0.006 |
overed | -0.006 |
: | -0.006 |
Token | so |
Token ID | 523 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
handed | +0.004 |
cash | +0.004 |
cand | +0.004 |
toy | +0.003 |
moderation | +0.003 |
Neg logit contributions | |
above | -0.004 |
ary | -0.004 |
overed | -0.004 |
ols | -0.004 |
below | -0.004 |
Token | excited |
Token ID | 6568 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
handed | +0.024 |
cash | +0.024 |
cand | +0.023 |
moderation | +0.022 |
dishes | +0.020 |
Neg logit contributions | |
above | -0.033 |
ary | -0.031 |
below | -0.031 |
overed | -0.030 |
: | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | -4.64e-04 |
Pos logit contributions | |
handed | +0.040 |
cash | +0.038 |
cand | +0.038 |
moderation | +0.036 |
dishes | +0.035 |
Neg logit contributions | |
above | -0.029 |
ary | -0.027 |
overed | -0.026 |
below | -0.026 |
behold | -0.025 |
Token | explore |
Token ID | 7301 |
Feature activation | -8.63e-03 |
Pos logit contributions | |
handed | +0.001 |
cash | +0.001 |
cand | +0.001 |
toy | +0.001 |
moderation | +0.001 |
Neg logit contributions | |
overed | -0.001 |
above | -0.001 |
ary | -0.001 |
below | -0.001 |
ols | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -2.31e-03 |
Pos logit contributions | |
handed | +0.013 |
cand | +0.012 |
cash | +0.012 |
moderation | +0.011 |
handful | +0.011 |
Neg logit contributions | |
ary | -0.013 |
overed | -0.012 |
above | -0.012 |
ols | -0.011 |
below | -0.011 |
Token | gall |
Token ID | 7976 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
handed | +0.003 |
cash | +0.003 |
cand | +0.003 |
moderation | +0.003 |
dishes | +0.003 |
Neg logit contributions | |
above | -0.003 |
ary | -0.003 |
overed | -0.003 |
below | -0.003 |
: | -0.003 |
Token | oped |
Token ID | 19458 |
Feature activation | +2.00e-03 |
Pos logit contributions | |
above | +0.063 |
below | +0.055 |
ary | +0.055 |
overed | +0.053 |
behold | +0.053 |
Neg logit contributions | |
handed | -0.083 |
cash | -0.076 |
cand | -0.075 |
handful | -0.071 |
moderation | -0.071 |
Token | around |
Token ID | 1088 |
Feature activation | -9.63e-03 |
Pos logit contributions | |
ary | +0.002 |
overed | +0.002 |
above | +0.002 |
behold | +0.002 |
ols | +0.002 |
Neg logit contributions | |
handed | -0.004 |
cash | -0.004 |
cand | -0.003 |
toy | -0.003 |
handful | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
handed | +0.015 |
toy | +0.014 |
cash | +0.014 |
cand | +0.013 |
handful | +0.013 |
Neg logit contributions | |
overed | -0.013 |
ary | -0.013 |
ols | -0.012 |
above | -0.012 |
ores | -0.011 |
Token | field |
Token ID | 2214 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
handed | +0.029 |
cash | +0.028 |
cand | +0.028 |
moderation | +0.026 |
dishes | +0.026 |
Neg logit contributions | |
above | -0.021 |
ary | -0.020 |
overed | -0.019 |
below | -0.018 |
: | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +1.79e-03 |
Pos logit contributions | |
handed | +0.038 |
cash | +0.037 |
cand | +0.037 |
moderation | +0.035 |
dishes | +0.034 |
Neg logit contributions | |
above | -0.025 |
ary | -0.023 |
below | -0.022 |
overed | -0.022 |
: | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
above | +0.028 |
ary | +0.027 |
overed | +0.026 |
below | +0.025 |
behold | +0.024 |
Neg logit contributions | |
handed | -0.030 |
cand | -0.029 |
cash | -0.029 |
moderation | -0.027 |
dishes | -0.026 |
Token | pretty |
Token ID | 2495 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
ary | +0.023 |
overed | +0.023 |
above | +0.023 |
ores | +0.022 |
brewing | +0.021 |
Neg logit contributions | |
cand | -0.018 |
cash | -0.018 |
handed | -0.018 |
candy | -0.016 |
dishes | -0.016 |
Token | flowers |
Token ID | 12734 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
cand | +0.015 |
handed | +0.015 |
cash | +0.015 |
toy | +0.013 |
candy | +0.013 |
Neg logit contributions | |
ary | -0.021 |
above | -0.020 |
overed | -0.020 |
ores | -0.019 |
brewing | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +5.37e-03 |
Pos logit contributions | |
above | +0.022 |
ary | +0.021 |
overed | +0.020 |
below | +0.019 |
behold | +0.019 |
Neg logit contributions | |
handed | -0.034 |
cand | -0.032 |
cash | -0.032 |
moderation | -0.030 |
dishes | -0.030 |
Token | trees |
Token ID | 7150 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
above | +0.009 |
ary | +0.008 |
overed | +0.008 |
below | +0.008 |
: | +0.008 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.007 |
cand | -0.007 |
moderation | -0.007 |
dishes | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +8.55e-03 |
Pos logit contributions | |
ary | +0.025 |
above | +0.024 |
overed | +0.024 |
behold | +0.023 |
ores | +0.022 |
Neg logit contributions | |
handed | -0.032 |
cand | -0.032 |
cash | -0.031 |
candy | -0.029 |
handful | -0.029 |
Token | |
Token ID | 220 |
Feature activation | +1.79e-03 |
Pos logit contributions | |
above | +0.013 |
ary | +0.013 |
overed | +0.012 |
below | +0.012 |
: | +0.012 |
Neg logit contributions | |
handed | -0.013 |
cand | -0.011 |
cash | -0.011 |
moderation | -0.011 |
dishes | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e-03 |
Pos logit contributions | |
above | +0.003 |
ary | +0.003 |
overed | +0.003 |
below | +0.003 |
behold | +0.003 |
Neg logit contributions | |
handed | -0.002 |
cash | -0.002 |
cand | -0.002 |
moderation | -0.002 |
dishes | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
handed | +0.002 |
cand | +0.002 |
cash | +0.002 |
moderation | +0.002 |
dishes | +0.002 |
Neg logit contributions | |
above | -0.002 |
ary | -0.002 |
overed | -0.001 |
below | -0.001 |
: | -0.001 |
Token | L |
Token ID | 43 |
Feature activation | +4.48e-03 |
Pos logit contributions | |
handed | +0.019 |
cand | +0.018 |
cash | +0.018 |
moderation | +0.017 |
dishes | +0.017 |
Neg logit contributions | |
ary | -0.018 |
above | -0.018 |
overed | -0.017 |
behold | -0.017 |
below | -0.016 |
Token | ily |
Token ID | 813 |
Feature activation | +6.80e-03 |
Pos logit contributions | |
above | +0.006 |
ary | +0.005 |
below | +0.005 |
overed | +0.005 |
ols | +0.005 |
Neg logit contributions | |
handed | -0.008 |
cand | -0.008 |
cash | -0.007 |
moderation | -0.007 |
dishes | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +2.61e-03 |
Pos logit contributions | |
handed | +0.015 |
cash | +0.014 |
cand | +0.014 |
moderation | +0.013 |
dishes | +0.013 |
Neg logit contributions | |
above | -0.014 |
ary | -0.014 |
overed | -0.013 |
below | -0.013 |
: | -0.013 |
Token | glad |
Token ID | 9675 |
Feature activation | -3.47e-03 |
Pos logit contributions | |
above | +0.004 |
ary | +0.004 |
overed | +0.004 |
below | +0.004 |
ols | +0.004 |
Neg logit contributions | |
handed | -0.004 |
cash | -0.003 |
cand | -0.003 |
moderation | -0.003 |
handful | -0.003 |
Token | when |
Token ID | 618 |
Feature activation | +1.05e-04 |
Pos logit contributions | |
cand | +0.004 |
handed | +0.004 |
cash | +0.004 |
candy | +0.004 |
toy | +0.003 |
Neg logit contributions | |
ary | -0.006 |
above | -0.006 |
overed | -0.006 |
behold | -0.006 |
rounded | -0.006 |
Token | she |
Token ID | 673 |
Feature activation | +5.46e-03 |
Pos logit contributions | |
above | +0.000 |
ary | +0.000 |
overed | +0.000 |
below | +0.000 |
ols | +0.000 |
Neg logit contributions | |
handed | -0.000 |
cash | -0.000 |
cand | -0.000 |
moderation | -0.000 |
dishes | -0.000 |
Token | understood |
Token ID | 7247 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
overed | +0.008 |
above | +0.008 |
ores | +0.008 |
lights | +0.008 |
ols | +0.007 |
Neg logit contributions | |
handed | -0.008 |
toy | -0.007 |
cash | -0.007 |
cand | -0.007 |
candy | -0.006 |
Token | how |
Token ID | 703 |
Feature activation | +6.78e-03 |
Pos logit contributions | |
above | +0.024 |
ary | +0.023 |
overed | +0.022 |
below | +0.022 |
behold | +0.021 |
Neg logit contributions | |
handed | -0.030 |
cash | -0.028 |
cand | -0.028 |
moderation | -0.027 |
dishes | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +6.18e-03 |
Pos logit contributions | |
above | +0.011 |
ary | +0.011 |
overed | +0.010 |
below | +0.010 |
behold | +0.010 |
Neg logit contributions | |
handed | -0.009 |
cash | -0.008 |
cand | -0.008 |
moderation | -0.008 |
dishes | -0.008 |
Token | stay |
Token ID | 2652 |
Feature activation | +4.75e-03 |
Pos logit contributions | |
above | +0.009 |
ary | +0.009 |
below | +0.008 |
overed | +0.008 |
: | +0.008 |
Neg logit contributions | |
handed | -0.009 |
cash | -0.009 |
cand | -0.009 |
moderation | -0.008 |
dishes | -0.008 |
Token | safe |
Token ID | 3338 |
Feature activation | -3.46e-03 |
Pos logit contributions | |
above | +0.007 |
ary | +0.006 |
overed | +0.006 |
below | +0.006 |
behold | +0.006 |
Neg logit contributions | |
handed | -0.008 |
cash | -0.007 |
cand | -0.007 |
moderation | -0.007 |
dishes | -0.007 |
Token | around |
Token ID | 1088 |
Feature activation | -2.67e-03 |
Pos logit contributions | |
handed | +0.006 |
cash | +0.006 |
cand | +0.006 |
moderation | +0.006 |
dishes | +0.006 |
Neg logit contributions | |
above | -0.004 |
ary | -0.004 |
overed | -0.004 |
below | -0.004 |
behold | -0.003 |
Token | traffic |
Token ID | 4979 |
Feature activation | -2.43e-03 |
Pos logit contributions | |
handed | +0.004 |
cash | +0.004 |
cand | +0.003 |
toy | +0.003 |
dishes | +0.003 |
Neg logit contributions | |
overed | -0.004 |
ary | -0.004 |
above | -0.004 |
behold | -0.004 |
ores | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | +4.37e-03 |
Pos logit contributions | |
handed | +0.007 |
cand | +0.006 |
toy | +0.006 |
cash | +0.006 |
lest | +0.006 |
Neg logit contributions | |
overed | -0.007 |
above | -0.006 |
ores | -0.006 |
ols | -0.006 |
Jas | -0.006 |
Token | wings |
Token ID | 12098 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
above | +0.006 |
ary | +0.006 |
overed | +0.005 |
below | +0.005 |
: | +0.005 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.007 |
cand | -0.007 |
moderation | -0.006 |
handful | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +3.05e-03 |
Pos logit contributions | |
above | +0.023 |
ary | +0.021 |
below | +0.020 |
overed | +0.020 |
: | +0.019 |
Neg logit contributions | |
handed | -0.034 |
cash | -0.033 |
cand | -0.033 |
moderation | -0.031 |
dishes | -0.030 |
Token | he |
Token ID | 339 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
above | +0.004 |
ary | +0.004 |
below | +0.004 |
overed | +0.004 |
: | +0.004 |
Neg logit contributions | |
handed | -0.005 |
cash | -0.005 |
cand | -0.005 |
moderation | -0.004 |
dishes | -0.004 |
Token | could |
Token ID | 714 |
Feature activation | +2.24e-03 |
Pos logit contributions | |
cand | +0.021 |
handed | +0.021 |
cash | +0.020 |
toy | +0.020 |
lest | +0.019 |
Neg logit contributions | |
above | -0.020 |
overed | -0.019 |
ores | -0.019 |
ary | -0.019 |
ols | -0.018 |
Token | fly |
Token ID | 6129 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
overed | +0.003 |
above | +0.003 |
ores | +0.003 |
ary | +0.003 |
brewing | +0.003 |
Neg logit contributions | |
handed | -0.003 |
cash | -0.003 |
cand | -0.003 |
moderation | -0.003 |
toy | -0.003 |
Token | away |
Token ID | 1497 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
overed | +0.024 |
ary | +0.024 |
ols | +0.022 |
above | +0.022 |
Jas | +0.022 |
Neg logit contributions | |
handed | -0.028 |
toy | -0.025 |
cand | -0.025 |
handful | -0.025 |
candy | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +8.13e-03 |
Pos logit contributions | |
above | +0.025 |
ary | +0.024 |
overed | +0.022 |
below | +0.022 |
behold | +0.021 |
Neg logit contributions | |
handed | -0.040 |
cash | -0.038 |
cand | -0.038 |
moderation | -0.036 |
dishes | -0.035 |
Token | He |
Token ID | 679 |
Feature activation | -6.02e-03 |
Pos logit contributions | |
above | +0.013 |
ary | +0.012 |
below | +0.012 |
overed | +0.012 |
: | +0.012 |
Neg logit contributions | |
handed | -0.011 |
cand | -0.011 |
cash | -0.011 |
moderation | -0.010 |
dishes | -0.010 |
Token | flew |
Token ID | 13112 |
Feature activation | +6.71e-03 |
Pos logit contributions | |
cash | +0.008 |
cand | +0.008 |
toy | +0.008 |
handed | +0.007 |
handful | +0.007 |
Neg logit contributions | |
ores | -0.009 |
above | -0.009 |
overed | -0.009 |
ary | -0.009 |
ols | -0.009 |
Token | higher |
Token ID | 2440 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
ary | +0.009 |
ols | +0.008 |
above | +0.008 |
overed | +0.008 |
behold | +0.008 |
Neg logit contributions | |
handed | -0.010 |
cash | -0.010 |
handful | -0.010 |
cand | -0.010 |
toy | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -2.33e-03 |
Pos logit contributions | |
above | +0.004 |
ary | +0.004 |
overed | +0.004 |
: | +0.004 |
below | +0.004 |
Neg logit contributions | |
handed | -0.005 |
cash | -0.005 |
cand | -0.005 |
moderation | -0.004 |
dishes | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | +4.55e-03 |
Pos logit contributions | |
handed | +0.003 |
cash | +0.003 |
cand | +0.003 |
moderation | +0.003 |
dishes | +0.003 |
Neg logit contributions | |
above | -0.004 |
ary | -0.004 |
overed | -0.003 |
below | -0.003 |
: | -0.003 |
Token | â |
Token ID | 22940 |
Feature activation | +6.12e-03 |
Pos logit contributions | |
above | +0.006 |
ary | +0.005 |
: | +0.005 |
below | +0.005 |
overed | +0.005 |
Neg logit contributions | |
handed | -0.008 |
cash | -0.008 |
moderation | -0.008 |
cand | -0.008 |
handful | -0.007 |
Token | € |
Token ID | 26391 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
above | +0.008 |
ary | +0.008 |
overed | +0.008 |
below | +0.008 |
: | +0.007 |
Neg logit contributions | |
handed | -0.010 |
cash | -0.010 |
cand | -0.009 |
moderation | -0.009 |
dishes | -0.009 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
above | +0.024 |
ary | +0.022 |
below | +0.022 |
overed | +0.022 |
behold | +0.020 |
Neg logit contributions | |
handed | -0.021 |
cash | -0.019 |
cand | -0.019 |
moderation | -0.018 |
handful | -0.017 |
Token | s |
Token ID | 82 |
Feature activation | +8.36e-03 |
Pos logit contributions | |
handed | +0.021 |
cash | +0.020 |
cand | +0.020 |
moderation | +0.018 |
dishes | +0.018 |
Neg logit contributions | |
above | -0.019 |
ary | -0.018 |
overed | -0.017 |
below | -0.017 |
behold | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -8.11e-04 |
Pos logit contributions | |
above | +0.013 |
ary | +0.013 |
overed | +0.012 |
below | +0.012 |
: | +0.011 |
Neg logit contributions | |
handed | -0.012 |
cash | -0.011 |
cand | -0.011 |
moderation | -0.011 |
dishes | -0.010 |
Token | lovely |
Token ID | 14081 |
Feature activation | -8.31e-03 |
Pos logit contributions | |
handed | +0.001 |
cand | +0.001 |
cash | +0.001 |
moderation | +0.001 |
Those | +0.001 |
Neg logit contributions | |
above | -0.001 |
ary | -0.001 |
: | -0.001 |
below | -0.001 |
brewing | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | -7.27e-03 |
Pos logit contributions | |
handed | +0.012 |
cash | +0.011 |
cand | +0.011 |
moderation | +0.010 |
lest | +0.010 |
Neg logit contributions | |
above | -0.014 |
: | -0.012 |
below | -0.012 |
ary | -0.012 |
overed | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +7.78e-03 |
Pos logit contributions | |
handed | +0.012 |
cash | +0.011 |
cand | +0.011 |
moderation | +0.010 |
dishes | +0.010 |
Neg logit contributions | |
above | -0.010 |
ary | -0.009 |
overed | -0.009 |
below | -0.009 |
behold | -0.009 |
Token | Let |
Token ID | 3914 |
Feature activation | -8.43e-03 |
Pos logit contributions | |
above | +0.011 |
ary | +0.011 |
below | +0.010 |
: | +0.010 |
over | +0.010 |
Neg logit contributions | |
handed | -0.012 |
cand | -0.011 |
cash | -0.011 |
moderation | -0.010 |
dishes | -0.010 |
Token | brave |
Token ID | 14802 |
Feature activation | +7.80e-03 |
Pos logit contributions | |
above | +0.004 |
ary | +0.003 |
below | +0.003 |
overed | +0.003 |
: | +0.003 |
Neg logit contributions | |
handed | -0.003 |
cash | -0.003 |
cand | -0.002 |
moderation | -0.002 |
dishes | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +3.77e-03 |
Pos logit contributions | |
ary | +0.010 |
above | +0.010 |
overed | +0.010 |
behold | +0.010 |
below | +0.009 |
Neg logit contributions | |
handed | -0.012 |
cand | -0.012 |
cash | -0.012 |
dishes | -0.011 |
toy | -0.011 |
Token | clever |
Token ID | 14169 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
above | +0.006 |
ary | +0.006 |
below | +0.006 |
overed | +0.006 |
: | +0.005 |
Neg logit contributions | |
handed | -0.005 |
cash | -0.005 |
cand | -0.005 |
moderation | -0.005 |
dishes | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +5.53e-03 |
Pos logit contributions | |
ary | +0.014 |
above | +0.014 |
overed | +0.014 |
behold | +0.013 |
below | +0.012 |
Neg logit contributions | |
handed | -0.017 |
cand | -0.017 |
cash | -0.016 |
toy | -0.016 |
dishes | -0.016 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
above | +0.008 |
ary | +0.008 |
below | +0.008 |
overed | +0.008 |
: | +0.008 |
Neg logit contributions | |
handed | -0.008 |
cand | -0.008 |
cash | -0.008 |
moderation | -0.007 |
dishes | -0.007 |
Token | Once |
Token ID | 7454 |
Feature activation | +7.31e-03 |
Pos logit contributions | |
ary | +0.035 |
above | +0.034 |
overed | +0.034 |
ols | +0.033 |
behold | +0.033 |
Neg logit contributions | |
handed | -0.018 |
Those | -0.016 |
These | -0.015 |
toy | -0.015 |
handful | -0.015 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
above | +0.012 |
ary | +0.011 |
overed | +0.011 |
below | +0.010 |
ols | +0.010 |
Neg logit contributions | |
handed | -0.010 |
cand | -0.009 |
cash | -0.009 |
moderation | -0.009 |
handful | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -8.90e-03 |
Pos logit contributions | |
above | +0.028 |
ary | +0.026 |
below | +0.025 |
: | +0.025 |
overed | +0.024 |
Neg logit contributions | |
handed | -0.027 |
cash | -0.027 |
cand | -0.026 |
lest | -0.024 |
dishes | -0.023 |
Token | time |
Token ID | 640 |
Feature activation | +1.05e-03 |
Pos logit contributions | |
handed | +0.017 |
cash | +0.017 |
cand | +0.016 |
moderation | +0.016 |
dishes | +0.015 |
Neg logit contributions | |
above | -0.010 |
ary | -0.009 |
overed | -0.008 |
below | -0.008 |
behold | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
above | +0.001 |
ary | +0.001 |
: | +0.001 |
overed | +0.001 |
below | +0.001 |
Neg logit contributions | |
handed | -0.002 |
cash | -0.002 |
cand | -0.002 |
moderation | -0.002 |
dishes | -0.001 |
Token | there |
Token ID | 612 |
Feature activation | +1.06e-03 |
Pos logit contributions | |
above | +0.022 |
ary | +0.021 |
overed | +0.020 |
below | +0.020 |
ols | +0.019 |
Neg logit contributions | |
handed | -0.020 |
cash | -0.019 |
cand | -0.019 |
moderation | -0.018 |
handful | -0.017 |
Token | it |
Token ID | 340 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
above | +0.014 |
ary | +0.013 |
overed | +0.012 |
below | +0.012 |
: | +0.012 |
Neg logit contributions | |
handed | -0.013 |
cash | -0.012 |
cand | -0.012 |
moderation | -0.011 |
dishes | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | +8.61e-03 |
Pos logit contributions | |
above | +0.018 |
ary | +0.017 |
overed | +0.016 |
below | +0.016 |
ols | +0.016 |
Neg logit contributions | |
handed | -0.021 |
cash | -0.020 |
cand | -0.020 |
handful | -0.018 |
toy | -0.018 |
Token | all |
Token ID | 477 |
Feature activation | -8.84e-03 |
Pos logit contributions | |
overed | +0.015 |
ary | +0.014 |
ols | +0.014 |
below | +0.013 |
behold | +0.013 |
Neg logit contributions | |
handful | -0.010 |
cand | -0.010 |
candy | -0.010 |
cash | -0.009 |
healthy | -0.009 |
Token | gone |
Token ID | 3750 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
handed | +0.015 |
cash | +0.014 |
cand | +0.014 |
moderation | +0.013 |
These | +0.012 |
Neg logit contributions | |
above | -0.013 |
below | -0.011 |
ary | -0.011 |
over | -0.011 |
overed | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +6.56e-03 |
Pos logit contributions | |
handed | +0.050 |
cash | +0.048 |
cand | +0.048 |
moderation | +0.045 |
dishes | +0.044 |
Neg logit contributions | |
above | -0.027 |
ary | -0.025 |
overed | -0.024 |
below | -0.024 |
: | -0.022 |
Token | It |
Token ID | 632 |
Feature activation | -4.02e-03 |
Pos logit contributions | |
above | +0.009 |
: | +0.009 |
ary | +0.009 |
overed | +0.009 |
over | +0.008 |
Neg logit contributions | |
handed | -0.011 |
moderation | -0.010 |
cand | -0.010 |
lest | -0.009 |
cash | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -3.63e-03 |
Pos logit contributions | |
handed | +0.007 |
cash | +0.007 |
cand | +0.007 |
moderation | +0.006 |
dishes | +0.006 |
Neg logit contributions | |
above | -0.005 |
ary | -0.005 |
overed | -0.005 |
below | -0.005 |
: | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -4.24e-03 |
Pos logit contributions | |
handed | +0.004 |
cand | +0.004 |
cash | +0.004 |
moderation | +0.004 |
toy | +0.004 |
Neg logit contributions | |
above | -0.006 |
ary | -0.006 |
overed | -0.006 |
below | -0.006 |
ols | -0.006 |
Token | best |
Token ID | 1266 |
Feature activation | +2.48e-04 |
Pos logit contributions | |
handed | +0.005 |
cand | +0.004 |
cash | +0.004 |
moderation | +0.004 |
handful | +0.004 |
Neg logit contributions | |
above | -0.008 |
ary | -0.007 |
below | -0.007 |
brewing | -0.007 |
: | -0.007 |
Token | hot |
Token ID | 3024 |
Feature activation | +4.80e-03 |
Pos logit contributions | |
above | +0.000 |
below | +0.000 |
ores | +0.000 |
ary | +0.000 |
brewing | +0.000 |
Neg logit contributions | |
handed | -0.000 |
cash | -0.000 |
cand | -0.000 |
moderation | -0.000 |
redd | -0.000 |
Token | dog |
Token ID | 3290 |
Feature activation | +9.97e-03 |
Pos logit contributions | |
above | +0.008 |
ary | +0.007 |
below | +0.007 |
overed | +0.007 |
: | +0.007 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.006 |
cand | -0.006 |
moderation | -0.006 |
handful | -0.006 |
Token | from |
Token ID | 422 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
above | +0.011 |
over | +0.010 |
ary | +0.010 |
below | +0.009 |
: | +0.009 |
Neg logit contributions | |
cand | -0.025 |
moderation | -0.025 |
handed | -0.025 |
cash | -0.024 |
redd | -0.024 |
Token | her |
Token ID | 607 |
Feature activation | +5.75e-03 |
Pos logit contributions | |
overed | +0.055 |
lights | +0.055 |
ols | +0.055 |
ary | +0.054 |
brewing | +0.052 |
Neg logit contributions | |
cash | -0.034 |
handed | -0.032 |
moderation | -0.029 |
toy | -0.028 |
candy | -0.027 |
Token | head |
Token ID | 1182 |
Feature activation | -4.30e-04 |
Pos logit contributions | |
above | +0.010 |
ary | +0.010 |
below | +0.009 |
: | +0.009 |
overed | +0.009 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.007 |
cand | -0.007 |
moderation | -0.006 |
redd | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -5.26e-03 |
Pos logit contributions | |
handed | +0.001 |
cand | +0.001 |
cash | +0.001 |
moderation | +0.001 |
dishes | +0.001 |
Neg logit contributions | |
above | -0.000 |
ary | -0.000 |
below | -0.000 |
: | -0.000 |
overed | -0.000 |
Token | gave |
Token ID | 2921 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
handed | +0.010 |
cash | +0.009 |
cand | +0.009 |
moderation | +0.009 |
dishes | +0.008 |
Neg logit contributions | |
above | -0.007 |
ary | -0.006 |
below | -0.006 |
overed | -0.006 |
: | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | -5.37e-03 |
Pos logit contributions | |
handed | +0.004 |
cash | +0.003 |
cand | +0.003 |
moderation | +0.003 |
dishes | +0.003 |
Neg logit contributions | |
above | -0.003 |
ary | -0.002 |
below | -0.002 |
overed | -0.002 |
: | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
handed | +0.010 |
cash | +0.009 |
cand | +0.009 |
moderation | +0.009 |
dishes | +0.008 |
Neg logit contributions | |
above | -0.007 |
ary | -0.006 |
overed | -0.006 |
below | -0.006 |
behold | -0.006 |
Token | him |
Token ID | 683 |
Feature activation | +2.56e-04 |
Pos logit contributions | |
handed | +0.016 |
cash | +0.016 |
cand | +0.015 |
moderation | +0.015 |
dishes | +0.014 |
Neg logit contributions | |
above | -0.017 |
ary | -0.016 |
overed | -0.016 |
below | -0.016 |
behold | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.71e-04 |
Pos logit contributions | |
above | +0.000 |
ary | +0.000 |
below | +0.000 |
overed | +0.000 |
: | +0.000 |
Neg logit contributions | |
handed | -0.001 |
cash | -0.000 |
cand | -0.000 |
moderation | -0.000 |
dishes | -0.000 |
Token | " |
Token ID | 366 |
Feature activation | -2.03e-03 |
Pos logit contributions | |
handed | +0.000 |
cand | +0.000 |
cash | +0.000 |
lest | +0.000 |
moderation | +0.000 |
Neg logit contributions | |
above | -0.000 |
: | -0.000 |
below | -0.000 |
ary | -0.000 |
overed | -0.000 |
Token | Here |
Token ID | 4342 |
Feature activation | -2.82e-03 |
Pos logit contributions | |
cand | +0.003 |
dishes | +0.003 |
handful | +0.003 |
handed | +0.003 |
business | +0.003 |
Neg logit contributions | |
above | -0.002 |
behold | -0.002 |
ary | -0.002 |
below | -0.002 |
te | -0.002 |
Token | for |
Token ID | 329 |
Feature activation | +8.38e-03 |
Pos logit contributions | |
cand | +0.005 |
handed | +0.005 |
cash | +0.005 |
handful | +0.004 |
toy | +0.004 |
Neg logit contributions | |
above | -0.006 |
overed | -0.006 |
ols | -0.006 |
ary | -0.006 |
below | -0.006 |
Token | Tim |
Token ID | 5045 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
above | +0.014 |
ary | +0.014 |
overed | +0.013 |
below | +0.013 |
: | +0.013 |
Neg logit contributions | |
handed | -0.011 |
cash | -0.010 |
cand | -0.010 |
moderation | -0.010 |
dishes | -0.009 |
Token | my |
Token ID | 1820 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
handed | +0.045 |
cash | +0.044 |
cand | +0.043 |
redd | +0.040 |
handful | +0.040 |
Neg logit contributions | |
above | -0.045 |
ary | -0.044 |
: | -0.042 |
over | -0.040 |
below | -0.038 |
Token | 's |
Token ID | 338 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
cash | +0.059 |
handed | +0.059 |
cand | +0.056 |
redd | +0.054 |
moderation | +0.054 |
Neg logit contributions | |
above | -0.050 |
ary | -0.046 |
: | -0.045 |
below | -0.044 |
over | -0.041 |
Token | robot |
Token ID | 9379 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
handed | +0.040 |
cash | +0.038 |
cand | +0.037 |
moderation | +0.034 |
dishes | +0.032 |
Neg logit contributions | |
above | -0.059 |
ary | -0.056 |
overed | -0.054 |
below | -0.054 |
: | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -3.00e-03 |
Pos logit contributions | |
handed | +0.045 |
cash | +0.044 |
cand | +0.043 |
moderation | +0.041 |
dishes | +0.040 |
Neg logit contributions | |
above | -0.030 |
ary | -0.028 |
below | -0.026 |
overed | -0.026 |
: | -0.025 |
Token | but |
Token ID | 475 |
Feature activation | +1.76e-03 |
Pos logit contributions | |
handed | +0.004 |
cand | +0.004 |
cash | +0.004 |
moderation | +0.004 |
dishes | +0.003 |
Neg logit contributions | |
above | -0.005 |
ary | -0.005 |
below | -0.005 |
overed | -0.005 |
: | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | -5.10e-03 |
Pos logit contributions | |
above | +0.003 |
ary | +0.003 |
overed | +0.003 |
below | +0.003 |
: | +0.003 |
Neg logit contributions | |
handed | -0.002 |
cash | -0.002 |
cand | -0.002 |
moderation | -0.002 |
dishes | -0.002 |
Token | couldn |
Token ID | 3521 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
handed | +0.009 |
cash | +0.008 |
cand | +0.008 |
toy | +0.008 |
candy | +0.007 |
Neg logit contributions | |
above | -0.007 |
ols | -0.006 |
below | -0.006 |
overed | -0.006 |
ary | -0.006 |
Token | 't |
Token ID | 470 |
Feature activation | -2.41e-03 |
Pos logit contributions | |
above | +0.036 |
ary | +0.033 |
overed | +0.033 |
below | +0.033 |
behold | +0.032 |
Neg logit contributions | |
handed | -0.040 |
cash | -0.037 |
cand | -0.037 |
moderation | -0.035 |
dishes | -0.034 |
Token | find |
Token ID | 1064 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
handed | +0.003 |
cash | +0.002 |
toy | +0.002 |
moderation | +0.002 |
cand | +0.002 |
Neg logit contributions | |
overed | -0.005 |
above | -0.005 |
ocked | -0.005 |
arted | -0.004 |
brewing | -0.004 |
Token | for |
Token ID | 329 |
Feature activation | +5.05e-03 |
Pos logit contributions | |
handed | +0.014 |
cand | +0.013 |
cash | +0.013 |
dishes | +0.012 |
moderation | +0.012 |
Neg logit contributions | |
ary | -0.009 |
above | -0.009 |
overed | -0.009 |
behold | -0.008 |
below | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -9.77e-03 |
Pos logit contributions | |
above | +0.008 |
ary | +0.007 |
below | +0.007 |
behold | +0.007 |
: | +0.007 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.007 |
cand | -0.007 |
lest | -0.006 |
Those | -0.006 |
Token | moment |
Token ID | 2589 |
Feature activation | +2.83e-04 |
Pos logit contributions | |
handed | +0.012 |
cash | +0.010 |
cand | +0.010 |
moderation | +0.010 |
Those | +0.010 |
Neg logit contributions | |
above | -0.017 |
ary | -0.017 |
: | -0.016 |
below | -0.016 |
brewing | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
above | +0.000 |
ary | +0.000 |
overed | +0.000 |
behold | +0.000 |
below | +0.000 |
Neg logit contributions | |
handed | -0.000 |
cand | -0.000 |
cash | -0.000 |
moderation | -0.000 |
toy | -0.000 |
Token | but |
Token ID | 475 |
Feature activation | -7.14e-03 |
Pos logit contributions | |
above | +0.008 |
below | +0.007 |
ary | +0.007 |
overed | +0.007 |
: | +0.007 |
Neg logit contributions | |
handed | -0.008 |
cand | -0.008 |
cash | -0.008 |
dishes | -0.007 |
moderation | -0.007 |
Token | then |
Token ID | 788 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
handed | +0.009 |
cash | +0.008 |
cand | +0.008 |
moderation | +0.008 |
dishes | +0.007 |
Neg logit contributions | |
above | -0.013 |
ary | -0.012 |
overed | -0.012 |
below | -0.012 |
ols | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | +5.38e-03 |
Pos logit contributions | |
handed | +0.016 |
cash | +0.014 |
cand | +0.014 |
moderation | +0.013 |
dishes | +0.012 |
Neg logit contributions | |
above | -0.032 |
ary | -0.031 |
overed | -0.030 |
below | -0.030 |
: | -0.030 |
Token | smiled |
Token ID | 13541 |
Feature activation | +9.51e-03 |
Pos logit contributions | |
ols | +0.010 |
overed | +0.010 |
ores | +0.010 |
above | +0.010 |
below | +0.010 |
Neg logit contributions | |
cash | -0.005 |
toy | -0.005 |
's | -0.005 |
poor | -0.005 |
cand | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +4.16e-03 |
Pos logit contributions | |
ary | +0.013 |
behold | +0.013 |
overed | +0.012 |
above | +0.012 |
ols | +0.012 |
Neg logit contributions | |
handed | -0.014 |
cash | -0.014 |
toy | -0.014 |
cand | -0.013 |
candy | -0.013 |
Token | said |
Token ID | 531 |
Feature activation | -6.40e-03 |
Pos logit contributions | |
above | +0.006 |
ary | +0.005 |
overed | +0.005 |
below | +0.005 |
: | +0.005 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.007 |
cand | -0.006 |
moderation | -0.006 |
dishes | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +4.71e-03 |
Pos logit contributions | |
handed | +0.010 |
cash | +0.010 |
cand | +0.009 |
moderation | +0.009 |
dishes | +0.009 |
Neg logit contributions | |
above | -0.009 |
ary | -0.009 |
overed | -0.009 |
: | -0.008 |
below | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | +1.95e-03 |
Pos logit contributions | |
above | +0.009 |
ary | +0.009 |
below | +0.009 |
overed | +0.009 |
: | +0.009 |
Neg logit contributions | |
handed | -0.007 |
cand | -0.007 |
cash | -0.006 |
moderation | -0.006 |
dishes | -0.006 |
Token | How |
Token ID | 2437 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
above | +0.003 |
ary | +0.003 |
overed | +0.003 |
below | +0.003 |
behold | +0.002 |
Neg logit contributions | |
handed | -0.003 |
cash | -0.003 |
cand | -0.003 |
moderation | -0.003 |
dishes | -0.003 |
Token | do |
Token ID | 466 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
above | +0.033 |
ary | +0.030 |
overed | +0.030 |
below | +0.029 |
ols | +0.027 |
Neg logit contributions | |
handed | -0.040 |
cash | -0.039 |
cand | -0.038 |
moderation | -0.037 |
dishes | -0.036 |
Token | you |
Token ID | 345 |
Feature activation | -7.56e-04 |
Pos logit contributions | |
above | +0.058 |
ary | +0.056 |
overed | +0.054 |
below | +0.054 |
: | +0.052 |
Neg logit contributions | |
handed | -0.041 |
cash | -0.039 |
cand | -0.038 |
moderation | -0.035 |
dishes | -0.033 |
Token | write |
Token ID | 3551 |
Feature activation | -5.32e-03 |
Pos logit contributions | |
handed | +0.001 |
cash | +0.001 |
cand | +0.001 |
moderation | +0.001 |
dishes | +0.001 |
Neg logit contributions | |
overed | -0.001 |
above | -0.001 |
ary | -0.001 |
below | -0.001 |
ores | -0.001 |
Token | this |
Token ID | 428 |
Feature activation | -4.42e-03 |
Pos logit contributions | |
handed | +0.007 |
cand | +0.007 |
cash | +0.007 |
candy | +0.007 |
toy | +0.006 |
Neg logit contributions | |
overed | -0.008 |
ary | -0.008 |
above | -0.008 |
below | -0.008 |
arted | -0.007 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -1.52e-03 |
Pos logit contributions | |
handed | +0.006 |
cash | +0.006 |
cand | +0.006 |
moderation | +0.005 |
toy | +0.005 |
Neg logit contributions | |
above | -0.007 |
ary | -0.007 |
overed | -0.007 |
below | -0.007 |
brewing | -0.006 |
Token | writing |
Token ID | 3597 |
Feature activation | +2.71e-03 |
Pos logit contributions | |
handed | +0.002 |
cash | +0.002 |
cand | +0.002 |
moderation | +0.002 |
dishes | +0.001 |
Neg logit contributions | |
above | -0.003 |
ary | -0.003 |
overed | -0.003 |
below | -0.003 |
behold | -0.002 |
Token | ?" |
Token ID | 1701 |
Feature activation | +5.88e-03 |
Pos logit contributions | |
above | +0.003 |
ary | +0.003 |
overed | +0.003 |
below | +0.003 |
ores | +0.003 |
Neg logit contributions | |
handed | -0.004 |
cand | -0.004 |
cash | -0.004 |
toy | -0.004 |
candy | -0.004 |
Token | He |
Token ID | 679 |
Feature activation | +4.39e-03 |
Pos logit contributions | |
above | +0.011 |
ary | +0.011 |
below | +0.011 |
overed | +0.010 |
behold | +0.010 |
Neg logit contributions | |
handed | -0.007 |
cand | -0.006 |
cash | -0.006 |
moderation | -0.006 |
dishes | -0.005 |
Token | asked |
Token ID | 1965 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
above | +0.006 |
ary | +0.006 |
overed | +0.006 |
below | +0.006 |
ores | +0.005 |
Neg logit contributions | |
handed | -0.007 |
cash | -0.007 |
cand | -0.007 |
moderation | -0.006 |
handful | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
above | +0.010 |
ary | +0.010 |
overed | +0.009 |
below | +0.009 |
: | +0.009 |
Neg logit contributions | |
handed | -0.008 |
cash | -0.007 |
cand | -0.007 |
moderation | -0.007 |
dishes | -0.006 |
Token | good |
Token ID | 922 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
handed | +0.018 |
cash | +0.015 |
cand | +0.015 |
moderation | +0.014 |
Those | +0.014 |
Neg logit contributions | |
above | -0.022 |
ary | -0.021 |
: | -0.020 |
below | -0.020 |
behold | -0.020 |
Token | day |
Token ID | 1110 |
Feature activation | +8.61e-03 |
Pos logit contributions | |
above | +0.012 |
ary | +0.011 |
overed | +0.010 |
below | +0.010 |
: | +0.010 |
Neg logit contributions | |
handed | -0.018 |
cash | -0.017 |
cand | -0.017 |
moderation | -0.016 |
redd | -0.016 |
Token | at |
Token ID | 379 |
Feature activation | +3.05e-03 |
Pos logit contributions | |
above | +0.011 |
ary | +0.010 |
overed | +0.010 |
behold | +0.009 |
below | +0.009 |
Neg logit contributions | |
handed | -0.015 |
cand | -0.014 |
cash | -0.014 |
moderation | -0.013 |
dishes | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -3.84e-03 |
Pos logit contributions | |
above | +0.004 |
ary | +0.004 |
overed | +0.004 |
below | +0.004 |
: | +0.004 |
Neg logit contributions | |
handed | -0.005 |
cash | -0.005 |
cand | -0.005 |
moderation | -0.004 |
dishes | -0.004 |
Token | market |
Token ID | 1910 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
handed | +0.005 |
cash | +0.005 |
cand | +0.005 |
moderation | +0.004 |
dishes | +0.004 |
Neg logit contributions | |
above | -0.007 |
ary | -0.006 |
overed | -0.006 |
below | -0.006 |
: | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -2.16e-03 |
Pos logit contributions | |
handed | +0.074 |
cash | +0.072 |
cand | +0.071 |
moderation | +0.066 |
dishes | +0.065 |
Neg logit contributions | |
above | -0.049 |
ary | -0.047 |
overed | -0.045 |
behold | -0.043 |
below | -0.042 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
handed | +0.002 |
cash | +0.002 |
cand | +0.002 |
moderation | +0.002 |
These | +0.002 |
Neg logit contributions | |
above | -0.004 |
ary | -0.004 |
overed | -0.004 |
below | -0.004 |
brewing | -0.004 |
Token | L |
Token ID | 43 |
Feature activation | -5.16e-03 |
Pos logit contributions | |
ary | +0.027 |
above | +0.026 |
overed | +0.026 |
behold | +0.025 |
brewing | +0.024 |
Neg logit contributions | |
handed | -0.016 |
These | -0.015 |
Those | -0.015 |
cand | -0.014 |
moderation | -0.014 |
Token | ily |
Token ID | 813 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
handed | +0.010 |
cash | +0.009 |
cand | +0.009 |
moderation | +0.009 |
handful | +0.008 |
Neg logit contributions | |
above | -0.006 |
ary | -0.006 |
overed | -0.005 |
below | -0.005 |
: | -0.005 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.63e-03 |
Pos logit contributions | |
above | +0.033 |
ary | +0.032 |
overed | +0.030 |
below | +0.029 |
ols | +0.028 |
Neg logit contributions | |
handed | -0.041 |
cash | -0.039 |
cand | -0.038 |
moderation | -0.036 |
dishes | -0.035 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
above | +0.011 |
ary | +0.011 |
overed | +0.011 |
below | +0.010 |
ols | +0.010 |
Neg logit contributions | |
handed | -0.010 |
cand | -0.009 |
cash | -0.009 |
moderation | -0.009 |
toy | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
above | +0.022 |
ary | +0.021 |
below | +0.020 |
: | +0.019 |
overed | +0.019 |
Neg logit contributions | |
handed | -0.021 |
cash | -0.021 |
cand | -0.020 |
lest | -0.019 |
handful | -0.018 |
Token | time |
Token ID | 640 |
Feature activation | -1.81e-03 |
Pos logit contributions | |
handed | +0.024 |
cash | +0.024 |
cand | +0.023 |
moderation | +0.022 |
dishes | +0.022 |
Neg logit contributions | |
above | -0.013 |
ary | -0.012 |
overed | -0.011 |
below | -0.011 |
: | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
handed | +0.003 |
cash | +0.003 |
cand | +0.003 |
moderation | +0.003 |
redd | +0.003 |
Neg logit contributions | |
above | -0.002 |
ary | -0.002 |
: | -0.002 |
overed | -0.002 |
below | -0.002 |
Token | there |
Token ID | 612 |
Feature activation | -2.61e-03 |
Pos logit contributions | |
above | +0.015 |
ary | +0.015 |
overed | +0.014 |
below | +0.014 |
: | +0.013 |
Neg logit contributions | |
handed | -0.015 |
cash | -0.015 |
cand | -0.014 |
moderation | -0.013 |
dishes | -0.013 |
Token | were |
Token ID | 547 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
handed | +0.004 |
cash | +0.004 |
cand | +0.004 |
moderation | +0.004 |
dishes | +0.004 |
Neg logit contributions | |
above | -0.003 |
ary | -0.003 |
overed | -0.003 |
below | -0.003 |
ols | -0.003 |
Token | two |
Token ID | 734 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
handed | +0.048 |
cash | +0.044 |
cand | +0.039 |
lest | +0.039 |
moderation | +0.038 |
Neg logit contributions | |
above | -0.074 |
ary | -0.071 |
: | -0.069 |
below | -0.068 |
behold | -0.067 |
Token | wild |
Token ID | 4295 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
handed | +0.045 |
cash | +0.039 |
moderation | +0.038 |
cand | +0.037 |
redd | +0.035 |
Neg logit contributions | |
above | -0.040 |
ary | -0.038 |
: | -0.037 |
below | -0.036 |
ols | -0.034 |
Token | creatures |
Token ID | 8109 |
Feature activation | -8.48e-03 |
Pos logit contributions | |
cand | +0.027 |
handed | +0.027 |
cash | +0.026 |
dishes | +0.024 |
toy | +0.024 |
Neg logit contributions | |
above | -0.032 |
ary | -0.031 |
overed | -0.030 |
below | -0.029 |
behold | -0.029 |
Token | who |
Token ID | 508 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
handed | +0.011 |
cand | +0.010 |
cash | +0.010 |
toy | +0.010 |
handful | +0.009 |
Neg logit contributions | |
above | -0.014 |
ary | -0.013 |
overed | -0.013 |
behold | -0.013 |
below | -0.013 |
Token | lived |
Token ID | 5615 |
Feature activation | -9.87e-03 |
Pos logit contributions | |
handed | +0.038 |
cand | +0.036 |
cash | +0.036 |
toy | +0.034 |
moderation | +0.033 |
Neg logit contributions | |
above | -0.032 |
overed | -0.031 |
ary | -0.031 |
below | -0.029 |
brewing | -0.028 |
Token | near |
Token ID | 1474 |
Feature activation | +4.86e-03 |
Pos logit contributions | |
handed | +0.013 |
cash | +0.013 |
toy | +0.013 |
cand | +0.013 |
moderation | +0.012 |
Neg logit contributions | |
ary | -0.008 |
ols | -0.007 |
behold | -0.007 |
above | -0.007 |
overed | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -3.27e-03 |
Pos logit contributions | |
above | +0.006 |
: | +0.005 |
over | +0.005 |
ary | +0.005 |
below | +0.005 |
Neg logit contributions | |
handed | -0.009 |
lest | -0.009 |
cash | -0.009 |
cand | -0.008 |
redd | -0.008 |
Token | sea |
Token ID | 5417 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
handed | +0.004 |
cash | +0.004 |
cand | +0.004 |
moderation | +0.004 |
dishes | +0.004 |
Neg logit contributions | |
above | -0.005 |
ary | -0.005 |
below | -0.005 |
overed | -0.005 |
: | -0.005 |
Token | with |
Token ID | 351 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
handed | +0.071 |
cash | +0.067 |
cand | +0.066 |
moderation | +0.063 |
dishes | +0.061 |
Neg logit contributions | |
above | -0.059 |
ary | -0.058 |
overed | -0.056 |
below | -0.053 |
behold | -0.052 |
Token | his |
Token ID | 465 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
handed | +0.025 |
cash | +0.022 |
lest | +0.022 |
cand | +0.020 |
moderation | +0.019 |
Neg logit contributions | |
above | -0.029 |
ary | -0.027 |
over | -0.027 |
: | -0.027 |
below | -0.026 |
Token | family |
Token ID | 1641 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
handed | +0.012 |
cash | +0.012 |
cand | +0.012 |
moderation | +0.011 |
toy | +0.011 |
Neg logit contributions | |
above | -0.018 |
ary | -0.017 |
overed | -0.017 |
below | -0.016 |
behold | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -7.68e-03 |
Pos logit contributions | |
handed | +0.076 |
cash | +0.073 |
cand | +0.073 |
moderation | +0.069 |
dishes | +0.067 |
Neg logit contributions | |
above | -0.043 |
ary | -0.040 |
overed | -0.038 |
below | -0.038 |
: | -0.036 |
Token | Every |
Token ID | 3887 |
Feature activation | -6.79e-03 |
Pos logit contributions | |
handed | +0.012 |
cash | +0.011 |
cand | +0.010 |
moderation | +0.010 |
dishes | +0.010 |
Neg logit contributions | |
above | -0.012 |
ary | -0.012 |
below | -0.011 |
overed | -0.011 |
: | -0.011 |
Token | day |
Token ID | 1110 |
Feature activation | +6.01e-03 |
Pos logit contributions | |
toy | +0.007 |
handed | +0.007 |
moderation | +0.007 |
cash | +0.007 |
cand | +0.007 |
Neg logit contributions | |
above | -0.012 |
overed | -0.012 |
ols | -0.011 |
below | -0.011 |
ary | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +8.34e-04 |
Pos logit contributions | |
above | +0.007 |
: | +0.007 |
ary | +0.007 |
below | +0.007 |
overed | +0.006 |
Neg logit contributions | |
handed | -0.012 |
cash | -0.010 |
moderation | -0.010 |
redd | -0.009 |
cand | -0.009 |
Token | Fl |
Token ID | 1610 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
above | +0.001 |
ary | +0.001 |
below | +0.001 |
: | +0.001 |
overed | +0.001 |
Neg logit contributions | |
handed | -0.001 |
cash | -0.001 |
moderation | -0.001 |
cand | -0.001 |
dishes | -0.001 |
Token | duck |
Token ID | 22045 |
Feature activation | -6.46e-04 |
Pos logit contributions | |
handed | +0.022 |
cash | +0.020 |
cand | +0.020 |
moderation | +0.019 |
handful | +0.018 |
Neg logit contributions | |
above | -0.025 |
ary | -0.024 |
below | -0.023 |
overed | -0.023 |
behold | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | +1.94e-03 |
Pos logit contributions | |
handed | +0.001 |
cash | +0.001 |
cand | +0.001 |
moderation | +0.001 |
dishes | +0.001 |
Neg logit contributions | |
above | -0.001 |
ary | -0.001 |
overed | -0.001 |
below | -0.001 |
behold | -0.001 |
Token | clean |
Token ID | 3424 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
above | +0.003 |
overed | +0.003 |
ary | +0.003 |
below | +0.003 |
ols | +0.003 |
Neg logit contributions | |
handed | -0.003 |
cand | -0.003 |
moderation | -0.003 |
cash | -0.003 |
handful | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -8.11e-04 |
Pos logit contributions | |
handed | +0.029 |
cash | +0.027 |
cand | +0.027 |
moderation | +0.026 |
handful | +0.024 |
Neg logit contributions | |
above | -0.024 |
ary | -0.021 |
below | -0.021 |
overed | -0.021 |
: | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -3.36e-03 |
Pos logit contributions | |
handed | +0.001 |
cash | +0.001 |
cand | +0.001 |
moderation | +0.001 |
dishes | +0.001 |
Neg logit contributions | |
above | -0.001 |
ary | -0.001 |
overed | -0.001 |
below | -0.001 |
: | -0.001 |
Token | navy |
Token ID | 23956 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
handed | +0.004 |
cash | +0.004 |
cand | +0.004 |
moderation | +0.003 |
dishes | +0.003 |
Neg logit contributions | |
above | -0.006 |
ary | -0.006 |
overed | -0.006 |
below | -0.006 |
: | -0.006 |
Token | boat |
Token ID | 8848 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
handed | +0.054 |
cash | +0.052 |
cand | +0.051 |
moderation | +0.047 |
dishes | +0.046 |
Neg logit contributions | |
above | -0.065 |
ary | -0.063 |
overed | -0.060 |
below | -0.059 |
behold | -0.057 |
Token | took |
Token ID | 1718 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
handed | +0.018 |
cand | +0.018 |
cash | +0.018 |
toy | +0.018 |
dishes | +0.016 |
Neg logit contributions | |
ary | -0.019 |
above | -0.018 |
overed | -0.018 |
ols | -0.018 |
ores | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
handed | +0.019 |
cash | +0.018 |
cand | +0.018 |
moderation | +0.017 |
dishes | +0.016 |
Neg logit contributions | |
above | -0.018 |
ary | -0.017 |
below | -0.016 |
overed | -0.016 |
: | -0.016 |
Token | duck |
Token ID | 22045 |
Feature activation | -1.24e-03 |
Pos logit contributions | |
above | +0.032 |
below | +0.030 |
ary | +0.028 |
overed | +0.027 |
brewing | +0.027 |
Neg logit contributions | |
handed | -0.026 |
cash | -0.023 |
moderation | -0.022 |
cand | -0.022 |
Those | -0.021 |
Token | back |
Token ID | 736 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
cash | +0.002 |
handed | +0.002 |
cand | +0.002 |
These | +0.002 |
Those | +0.002 |
Neg logit contributions | |
above | -0.001 |
over | -0.001 |
below | -0.001 |
ary | -0.001 |
around | -0.001 |
Token | see |
Token ID | 766 |
Feature activation | +3.18e-03 |
Pos logit contributions | |
cash | +0.009 |
handed | +0.009 |
cand | +0.008 |
money | +0.008 |
toy | +0.008 |
Neg logit contributions | |
overed | -0.017 |
brewing | -0.016 |
lights | -0.016 |
ocked | -0.016 |
above | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
above | +0.006 |
ary | +0.006 |
overed | +0.006 |
below | +0.005 |
behold | +0.005 |
Neg logit contributions | |
handed | -0.004 |
cash | -0.004 |
cand | -0.003 |
toy | -0.003 |
moderation | -0.003 |
Token | house |
Token ID | 2156 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
above | +0.031 |
ary | +0.030 |
overed | +0.029 |
below | +0.028 |
ols | +0.028 |
Neg logit contributions | |
handed | -0.017 |
cash | -0.017 |
cand | -0.016 |
moderation | -0.014 |
toy | -0.014 |
Token | near |
Token ID | 1474 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
handed | +0.019 |
cash | +0.019 |
cand | +0.019 |
toy | +0.018 |
dishes | +0.017 |
Neg logit contributions | |
ary | -0.021 |
overed | -0.019 |
above | -0.019 |
behold | -0.019 |
arted | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
ary | +0.028 |
overed | +0.027 |
above | +0.027 |
ols | +0.025 |
below | +0.024 |
Neg logit contributions | |
handed | -0.021 |
cash | -0.021 |
cand | -0.020 |
toy | -0.019 |
dishes | -0.019 |
Token | mill |
Token ID | 3939 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
above | +0.022 |
ary | +0.022 |
overed | +0.021 |
behold | +0.020 |
below | +0.020 |
Neg logit contributions | |
handed | -0.014 |
cash | -0.013 |
cand | -0.013 |
dishes | -0.012 |
toy | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +2.47e-03 |
Pos logit contributions | |
handed | +0.072 |
cash | +0.068 |
cand | +0.067 |
dishes | +0.062 |
toy | +0.062 |
Neg logit contributions | |
ary | -0.049 |
above | -0.049 |
overed | -0.046 |
behold | -0.044 |
ores | -0.042 |
Token | The |
Token ID | 383 |
Feature activation | -1.70e-03 |
Pos logit contributions | |
above | +0.004 |
ary | +0.004 |
overed | +0.004 |
below | +0.004 |
brewing | +0.004 |
Neg logit contributions | |
handed | -0.003 |
cash | -0.003 |
cand | -0.003 |
moderation | -0.002 |
These | -0.002 |
Token | house |
Token ID | 2156 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
handed | +0.002 |
cash | +0.002 |
cand | +0.002 |
moderation | +0.001 |
dishes | +0.001 |
Neg logit contributions | |
above | -0.003 |
ary | -0.003 |
overed | -0.003 |
below | -0.003 |
behold | -0.003 |
Token | has |
Token ID | 468 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
cand | +0.018 |
cash | +0.017 |
toy | +0.017 |
dishes | +0.017 |
money | +0.015 |
Neg logit contributions | |
ary | -0.040 |
above | -0.037 |
overed | -0.035 |
arted | -0.035 |
behold | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | -4.48e-03 |
Pos logit contributions | |
above | +0.019 |
ary | +0.018 |
below | +0.018 |
overed | +0.018 |
: | +0.017 |
Neg logit contributions | |
handed | -0.015 |
cash | -0.013 |
cand | -0.013 |
moderation | -0.012 |
lest | -0.012 |