Token | - |
Token ID | 12 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
aw | +0.100 |
course | +0.094 |
Run | +0.081 |
crow | +0.080 |
Too | +0.078 |
Neg logit contributions | |
nie | -0.095 |
ilda | -0.094 |
any | -0.093 |
Jackie | -0.093 |
ingu | -0.091 |
Token | life |
Token ID | 6042 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
ilda | +0.022 |
nie | +0.022 |
organ | +0.021 |
any | +0.021 |
Em | +0.021 |
Neg logit contributions | |
aw | -0.024 |
course | -0.024 |
Run | -0.020 |
crow | -0.020 |
Too | -0.019 |
Token | mountain |
Token ID | 8598 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
ilda | +0.027 |
nie | +0.027 |
any | +0.026 |
Em | +0.026 |
organ | +0.026 |
Neg logit contributions | |
aw | -0.025 |
course | -0.024 |
Run | -0.020 |
crow | -0.020 |
Too | -0.020 |
Token | in |
Token ID | 287 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
aw | +0.017 |
course | +0.016 |
Run | +0.014 |
crow | +0.014 |
Too | +0.014 |
Neg logit contributions | |
nie | -0.018 |
ilda | -0.018 |
any | -0.018 |
organ | -0.017 |
Em | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
nie | +0.065 |
Jackie | +0.065 |
ilda | +0.065 |
any | +0.064 |
Em | +0.064 |
Neg logit contributions | |
aw | -0.061 |
course | -0.054 |
crow | -0.047 |
Run | -0.046 |
Too | -0.045 |
Token | middle |
Token ID | 3504 |
Feature activation | +7.50e+00 |
Pos logit contributions | |
aw | +0.020 |
course | +0.019 |
crow | +0.016 |
Run | +0.016 |
Too | +0.015 |
Neg logit contributions | |
nie | -0.021 |
ilda | -0.021 |
any | -0.020 |
organ | -0.020 |
Em | -0.020 |
Token | of |
Token ID | 286 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
aw | +0.270 |
course | +0.262 |
Run | +0.248 |
Too | +0.229 |
crow | +0.222 |
Neg logit contributions | |
nie | -0.321 |
any | -0.318 |
ilda | -0.318 |
cere | -0.308 |
Jackie | -0.307 |
Token | the |
Token ID | 262 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ilda | +0.051 |
organ | +0.051 |
nie | +0.050 |
Em | +0.049 |
any | +0.049 |
Neg logit contributions | |
aw | -0.037 |
course | -0.036 |
crow | -0.028 |
Run | -0.027 |
goose | -0.026 |
Token | valley |
Token ID | 19272 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
aw | +0.008 |
course | +0.008 |
crow | +0.007 |
Run | +0.006 |
goose | +0.006 |
Neg logit contributions | |
organ | -0.008 |
ilda | -0.008 |
nie | -0.008 |
Em | -0.008 |
any | -0.008 |
Token | ! |
Token ID | 0 |
Feature activation | +8.67e-02 |
Pos logit contributions | |
any | +0.007 |
nie | +0.007 |
ilda | +0.007 |
Jackie | +0.006 |
organ | +0.006 |
Neg logit contributions | |
aw | -0.007 |
course | -0.007 |
Run | -0.006 |
Too | -0.006 |
crow | -0.006 |
Token | With |
Token ID | 2080 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
aw | +0.004 |
course | +0.003 |
crow | +0.003 |
Run | +0.003 |
goose | +0.003 |
Neg logit contributions | |
ilda | -0.004 |
organ | -0.004 |
nie | -0.004 |
Em | -0.004 |
any | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
aw | +0.036 |
course | +0.032 |
crow | +0.029 |
ar | +0.026 |
Too | +0.026 |
Neg logit contributions | |
nie | -0.041 |
organ | -0.041 |
any | -0.040 |
Jackie | -0.039 |
Em | -0.039 |
Token | slide |
Token ID | 10649 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
aw | +0.015 |
course | +0.015 |
crow | +0.011 |
Run | +0.010 |
ar | +0.010 |
Neg logit contributions | |
organ | -0.028 |
nie | -0.028 |
ilda | -0.028 |
any | -0.028 |
Em | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
Run | +0.149 |
hawk | +0.140 |
course | +0.139 |
Too | +0.134 |
aw | +0.133 |
Neg logit contributions | |
nie | -0.111 |
any | -0.110 |
organ | -0.107 |
ingu | -0.104 |
ilda | -0.103 |
Token | the |
Token ID | 262 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
aw | +0.014 |
course | +0.013 |
crow | +0.011 |
Too | +0.011 |
Run | +0.011 |
Neg logit contributions | |
organ | -0.015 |
nie | -0.014 |
Jackie | -0.014 |
any | -0.014 |
Em | -0.014 |
Token | sees |
Token ID | 7224 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
aw | +0.016 |
course | +0.016 |
crow | +0.013 |
ar | +0.012 |
Run | +0.011 |
Neg logit contributions | |
nie | -0.028 |
organ | -0.028 |
any | -0.027 |
cere | -0.027 |
Em | -0.027 |
Token | aw |
Token ID | 707 |
Feature activation | +7.48e+00 |
Pos logit contributions | |
course | +0.036 |
ar | +0.031 |
ishly | +0.026 |
Too | +0.026 |
hawk | +0.023 |
Neg logit contributions | |
to | -0.158 |
organ | -0.157 |
cere | -0.154 |
iddles | -0.150 |
ingu | -0.147 |
Token | . |
Token ID | 13 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
course | +0.351 |
aw | +0.307 |
Run | +0.289 |
crow | +0.289 |
Too | +0.279 |
Neg logit contributions | |
ilda | -0.258 |
organ | -0.256 |
to | -0.256 |
iddles | -0.250 |
any | -0.242 |
Token | But |
Token ID | 887 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
aw | +0.004 |
course | +0.004 |
crow | +0.003 |
Run | +0.003 |
hawk | +0.003 |
Neg logit contributions | |
Em | -0.004 |
organ | -0.004 |
ingu | -0.004 |
ilda | -0.004 |
nie | -0.004 |
Token | there |
Token ID | 612 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
aw | +0.144 |
course | +0.121 |
crow | +0.115 |
hawk | +0.107 |
ican | +0.104 |
Neg logit contributions | |
nie | -0.133 |
Jackie | -0.127 |
daddy | -0.127 |
Em | -0.124 |
organ | -0.121 |
Token | was |
Token ID | 373 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
organ | +0.011 |
nie | +0.009 |
ingu | +0.009 |
cere | +0.008 |
ilda | +0.008 |
Neg logit contributions | |
aw | -0.022 |
course | -0.021 |
Run | -0.019 |
crow | -0.019 |
Leave | -0.019 |
Token | one |
Token ID | 530 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
course | +0.058 |
aw | +0.054 |
crow | +0.050 |
ican | +0.048 |
ar | +0.048 |
Neg logit contributions | |
organ | -0.042 |
die | -0.039 |
nie | -0.039 |
bie | -0.036 |
Jackie | -0.035 |
Token | tired |
Token ID | 10032 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
aw | +0.025 |
course | +0.025 |
crow | +0.020 |
Run | +0.019 |
Too | +0.019 |
Neg logit contributions | |
organ | -0.024 |
ilda | -0.024 |
nie | -0.023 |
any | -0.023 |
Em | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
aw | +0.030 |
course | +0.029 |
Too | +0.025 |
Run | +0.025 |
crow | +0.024 |
Neg logit contributions | |
nie | -0.023 |
ilda | -0.023 |
Jackie | -0.023 |
Em | -0.023 |
organ | -0.023 |
Token | stops |
Token ID | 9911 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
course | +0.002 |
aw | +0.002 |
crow | +0.002 |
Run | +0.001 |
Too | +0.001 |
Neg logit contributions | |
nie | -0.002 |
organ | -0.002 |
Jackie | -0.002 |
ilda | -0.002 |
any | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
aw | +0.040 |
course | +0.039 |
crow | +0.032 |
Run | +0.031 |
goose | +0.030 |
Neg logit contributions | |
ilda | -0.042 |
organ | -0.041 |
nie | -0.041 |
Em | -0.040 |
any | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
Jackie | +0.045 |
organ | +0.043 |
Em | +0.043 |
ilda | +0.043 |
any | +0.042 |
Neg logit contributions | |
aw | -0.055 |
course | -0.045 |
crow | -0.041 |
Too | -0.040 |
goose | -0.039 |
Token | middle |
Token ID | 3504 |
Feature activation | +7.48e+00 |
Pos logit contributions | |
aw | +0.022 |
course | +0.021 |
Run | +0.018 |
crow | +0.017 |
hawk | +0.017 |
Neg logit contributions | |
ingu | -0.016 |
cere | -0.016 |
nie | -0.016 |
Jackie | -0.016 |
isha | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
course | +0.342 |
aw | +0.335 |
Run | +0.324 |
hawk | +0.317 |
ican | +0.315 |
Neg logit contributions | |
cere | -0.222 |
nie | -0.220 |
and | -0.215 |
any | -0.215 |
ilda | -0.211 |
Token | the |
Token ID | 262 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
ilda | +0.048 |
organ | +0.048 |
Jackie | +0.048 |
Em | +0.047 |
nie | +0.047 |
Neg logit contributions | |
aw | -0.043 |
course | -0.039 |
crow | -0.034 |
Run | -0.031 |
Too | -0.031 |
Token | pool |
Token ID | 5933 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
aw | +0.018 |
course | +0.017 |
crow | +0.014 |
Run | +0.013 |
Too | +0.013 |
Neg logit contributions | |
nie | -0.019 |
ingu | -0.018 |
cere | -0.018 |
Em | -0.018 |
isha | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
course | +0.135 |
aw | +0.133 |
Too | +0.126 |
Run | +0.126 |
hawk | +0.125 |
Neg logit contributions | |
Jackie | -0.067 |
nie | -0.065 |
any | -0.063 |
ilda | -0.063 |
cere | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
nie | +0.006 |
ilda | +0.006 |
any | +0.006 |
organ | +0.006 |
Em | +0.006 |
Neg logit contributions | |
aw | -0.005 |
course | -0.004 |
crow | -0.004 |
Run | -0.004 |
goose | -0.003 |
Token | big |
Token ID | 1263 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ilda | +0.014 |
Em | +0.013 |
nie | +0.013 |
organ | +0.013 |
isha | +0.013 |
Neg logit contributions | |
aw | -0.016 |
course | -0.015 |
crow | -0.013 |
Run | -0.012 |
Too | -0.012 |
Token | red |
Token ID | 2266 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
aw | +0.059 |
course | +0.053 |
crow | +0.050 |
Run | +0.047 |
Too | +0.045 |
Neg logit contributions | |
Jackie | -0.046 |
nie | -0.045 |
ilda | -0.045 |
designs | -0.045 |
isha | -0.044 |
Token | circle |
Token ID | 9197 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
aw | +0.085 |
course | +0.081 |
crow | +0.075 |
Run | +0.073 |
roads | +0.069 |
Neg logit contributions | |
organ | -0.059 |
ilda | -0.059 |
nie | -0.058 |
Jackie | -0.058 |
cere | -0.058 |
Token | in |
Token ID | 287 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
course | +0.103 |
aw | +0.103 |
Run | +0.093 |
Too | +0.091 |
crow | +0.090 |
Neg logit contributions | |
ilda | -0.080 |
nie | -0.078 |
any | -0.077 |
organ | -0.076 |
cere | -0.076 |
Token | the |
Token ID | 262 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
organ | +0.052 |
nie | +0.051 |
ilda | +0.051 |
Jackie | +0.051 |
Em | +0.051 |
Neg logit contributions | |
aw | -0.047 |
course | -0.042 |
crow | -0.037 |
Run | -0.035 |
Too | -0.035 |
Token | middle |
Token ID | 3504 |
Feature activation | +7.40e+00 |
Pos logit contributions | |
aw | +0.015 |
Run | +0.015 |
course | +0.015 |
neither | +0.013 |
goose | +0.013 |
Neg logit contributions | |
Em | -0.021 |
cere | -0.021 |
any | -0.020 |
nie | -0.020 |
isha | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -9.11e-02 |
Pos logit contributions | |
course | +0.330 |
aw | +0.320 |
Run | +0.315 |
Too | +0.303 |
hawk | +0.298 |
Neg logit contributions | |
nie | -0.244 |
any | -0.237 |
ilda | -0.237 |
cere | -0.233 |
organ | -0.225 |
Token |
|
Token ID | 198 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
organ | +0.004 |
ilda | +0.004 |
Em | +0.004 |
nie | +0.004 |
ingu | +0.004 |
Neg logit contributions | |
aw | -0.004 |
course | -0.003 |
crow | -0.003 |
Run | -0.003 |
Too | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
ilda | +0.012 |
nie | +0.012 |
any | +0.012 |
organ | +0.012 |
ingu | +0.011 |
Neg logit contributions | |
aw | -0.011 |
course | -0.010 |
crow | -0.008 |
Run | -0.008 |
fountain | -0.008 |
Token | " |
Token ID | 1 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
Em | +0.010 |
nie | +0.010 |
organ | +0.010 |
isha | +0.009 |
die | +0.009 |
Neg logit contributions | |
course | -0.012 |
aw | -0.012 |
crow | -0.011 |
hy | -0.010 |
hawk | -0.010 |
Token | Wow |
Token ID | 22017 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
aw | +0.031 |
course | +0.029 |
crow | +0.024 |
Run | +0.023 |
goose | +0.023 |
Neg logit contributions | |
organ | -0.036 |
Em | -0.035 |
ilda | -0.034 |
nie | -0.034 |
any | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
aw | +0.032 |
course | +0.028 |
crow | +0.026 |
ar | +0.024 |
Too | +0.023 |
Neg logit contributions | |
nie | -0.033 |
organ | -0.032 |
Jackie | -0.032 |
any | -0.032 |
cere | -0.032 |
Token | slide |
Token ID | 10649 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
aw | +0.013 |
course | +0.013 |
crow | +0.010 |
ar | +0.009 |
Run | +0.009 |
Neg logit contributions | |
nie | -0.022 |
Em | -0.022 |
organ | -0.022 |
cere | -0.022 |
any | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
Run | +0.140 |
course | +0.138 |
aw | +0.134 |
hawk | +0.133 |
Too | +0.131 |
Neg logit contributions | |
nie | -0.110 |
any | -0.105 |
organ | -0.100 |
ilda | -0.099 |
cere | -0.098 |
Token | the |
Token ID | 262 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
aw | +0.011 |
course | +0.010 |
crow | +0.009 |
Too | +0.008 |
ar | +0.008 |
Neg logit contributions | |
organ | -0.010 |
nie | -0.010 |
Jackie | -0.010 |
Em | -0.010 |
any | -0.010 |
Token | sees |
Token ID | 7224 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
aw | +0.014 |
course | +0.014 |
crow | +0.011 |
ar | +0.010 |
Run | +0.010 |
Neg logit contributions | |
nie | -0.023 |
cere | -0.023 |
organ | -0.023 |
any | -0.023 |
Em | -0.023 |
Token | aw |
Token ID | 707 |
Feature activation | +7.39e+00 |
Pos logit contributions | |
course | +0.035 |
ar | +0.032 |
Too | +0.026 |
ishly | +0.026 |
hawk | +0.024 |
Neg logit contributions | |
cere | -0.151 |
organ | -0.150 |
to | -0.150 |
iddles | -0.143 |
designs | -0.142 |
Token | . |
Token ID | 13 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
course | +0.336 |
aw | +0.303 |
Run | +0.277 |
crow | +0.276 |
Too | +0.270 |
Neg logit contributions | |
ilda | -0.268 |
organ | -0.262 |
to | -0.260 |
iddles | -0.255 |
any | -0.255 |
Token | They |
Token ID | 1119 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
organ | +0.001 |
nie | +0.001 |
Em | +0.001 |
ilda | +0.001 |
ingu | +0.001 |
Neg logit contributions | |
aw | -0.001 |
course | -0.001 |
crow | -0.001 |
Run | -0.001 |
goose | -0.001 |
Token | also |
Token ID | 635 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
aw | +0.074 |
course | +0.071 |
crow | +0.058 |
Run | +0.056 |
Too | +0.054 |
Neg logit contributions | |
ilda | -0.083 |
organ | -0.083 |
nie | -0.082 |
Em | -0.081 |
any | -0.081 |
Token | like |
Token ID | 588 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
nie | +0.027 |
organ | +0.026 |
ilda | +0.026 |
any | +0.026 |
Em | +0.026 |
Neg logit contributions | |
aw | -0.029 |
course | -0.027 |
crow | -0.023 |
Run | -0.023 |
Too | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
aw | +0.090 |
course | +0.088 |
crow | +0.076 |
Run | +0.072 |
Too | +0.072 |
Neg logit contributions | |
organ | -0.069 |
ilda | -0.067 |
nie | -0.067 |
Em | -0.066 |
Jackie | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
organ | +0.008 |
nie | +0.008 |
ilda | +0.008 |
Em | +0.008 |
Jackie | +0.008 |
Neg logit contributions | |
aw | -0.010 |
course | -0.009 |
crow | -0.008 |
Run | -0.008 |
Too | -0.008 |
Token | They |
Token ID | 1119 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
aw | +0.016 |
course | +0.015 |
crow | +0.013 |
Run | +0.012 |
goose | +0.012 |
Neg logit contributions | |
organ | -0.016 |
ilda | -0.016 |
Em | -0.016 |
nie | -0.016 |
any | -0.016 |
Token | danced |
Token ID | 39480 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
aw | +0.106 |
course | +0.103 |
crow | +0.091 |
Run | +0.087 |
Too | +0.086 |
Neg logit contributions | |
organ | -0.062 |
Em | -0.062 |
ilda | -0.061 |
nie | -0.060 |
any | -0.059 |
Token | in |
Token ID | 287 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
organ | +0.065 |
Em | +0.062 |
nie | +0.062 |
Jackie | +0.061 |
ilda | +0.061 |
Neg logit contributions | |
course | -0.086 |
aw | -0.083 |
crow | -0.072 |
Too | -0.072 |
Run | -0.071 |
Token | the |
Token ID | 262 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
Jackie | +0.048 |
Em | +0.047 |
organ | +0.046 |
ilda | +0.046 |
nie | +0.046 |
Neg logit contributions | |
aw | -0.052 |
course | -0.047 |
crow | -0.043 |
Too | -0.042 |
Run | -0.042 |
Token | middle |
Token ID | 3504 |
Feature activation | +7.38e+00 |
Pos logit contributions | |
aw | +0.021 |
course | +0.020 |
Run | +0.018 |
neither | +0.017 |
crow | +0.017 |
Neg logit contributions | |
Em | -0.022 |
ilda | -0.021 |
isha | -0.021 |
Jackie | -0.021 |
any | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Run | +0.316 |
hawk | +0.301 |
course | +0.301 |
Too | +0.298 |
ican | +0.292 |
Neg logit contributions | |
Em | -0.242 |
and | -0.242 |
isha | -0.235 |
nie | -0.233 |
any | -0.229 |
Token | the |
Token ID | 262 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
ilda | +0.057 |
organ | +0.057 |
nie | +0.056 |
Em | +0.056 |
any | +0.055 |
Neg logit contributions | |
aw | -0.041 |
course | -0.039 |
crow | -0.031 |
Run | -0.030 |
goose | -0.029 |
Token | party |
Token ID | 2151 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
aw | +0.019 |
course | +0.018 |
crow | +0.015 |
Run | +0.015 |
Too | +0.014 |
Neg logit contributions | |
Em | -0.021 |
ilda | -0.021 |
organ | -0.021 |
nie | -0.021 |
isha | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
ilda | +0.018 |
isha | +0.017 |
any | +0.017 |
organ | +0.017 |
iddles | +0.017 |
Neg logit contributions | |
course | -0.020 |
aw | -0.019 |
Run | -0.018 |
Too | -0.017 |
crow | -0.017 |
Token | They |
Token ID | 1119 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
aw | +0.013 |
course | +0.013 |
crow | +0.011 |
Run | +0.010 |
goose | +0.010 |
Neg logit contributions | |
ilda | -0.016 |
organ | -0.015 |
nie | -0.015 |
Em | -0.015 |
any | -0.015 |
Token | pet |
Token ID | 4273 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
organ | +0.004 |
nie | +0.004 |
ilda | +0.004 |
cere | +0.004 |
Em | +0.004 |
Neg logit contributions | |
aw | -0.007 |
course | -0.007 |
crow | -0.006 |
Run | -0.006 |
Too | -0.006 |
Token | als |
Token ID | 874 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
course | +0.071 |
aw | +0.065 |
Too | +0.063 |
roads | +0.061 |
Run | +0.059 |
Neg logit contributions | |
cere | -0.070 |
Jackie | -0.069 |
isha | -0.068 |
ilda | -0.068 |
to | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
course | +0.024 |
aw | +0.024 |
Too | +0.021 |
Run | +0.021 |
crow | +0.020 |
Neg logit contributions | |
ilda | -0.022 |
any | -0.021 |
Jackie | -0.021 |
organ | -0.021 |
isha | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
course | +0.002 |
aw | +0.002 |
crow | +0.002 |
roads | +0.002 |
Too | +0.002 |
Neg logit contributions | |
cere | -0.002 |
Jackie | -0.002 |
designs | -0.002 |
die | -0.002 |
organ | -0.002 |
Token | yellow |
Token ID | 7872 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
isha | +0.011 |
Jackie | +0.011 |
ilda | +0.011 |
Em | +0.011 |
die | +0.011 |
Neg logit contributions | |
course | -0.014 |
aw | -0.014 |
crow | -0.012 |
Run | -0.011 |
Too | -0.011 |
Token | middle |
Token ID | 3504 |
Feature activation | +7.38e+00 |
Pos logit contributions | |
aw | +0.057 |
course | +0.054 |
roads | +0.048 |
Run | +0.047 |
crow | +0.047 |
Neg logit contributions | |
Jackie | -0.039 |
designs | -0.038 |
cere | -0.038 |
any | -0.037 |
design | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
course | +0.356 |
aw | +0.341 |
Run | +0.324 |
Too | +0.319 |
crow | +0.303 |
Neg logit contributions | |
any | -0.219 |
cere | -0.211 |
ilda | -0.210 |
designs | -0.201 |
nie | -0.198 |
Token | It |
Token ID | 632 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
organ | +0.004 |
to | +0.004 |
Em | +0.004 |
Jackie | +0.004 |
isha | +0.004 |
Neg logit contributions | |
course | -0.005 |
aw | -0.005 |
crow | -0.004 |
hawk | -0.004 |
ican | -0.004 |
Token | smells |
Token ID | 25760 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
aw | +0.026 |
course | +0.025 |
crow | +0.022 |
Run | +0.021 |
Too | +0.020 |
Neg logit contributions | |
organ | -0.025 |
nie | -0.025 |
cere | -0.024 |
isha | -0.024 |
Jackie | -0.024 |
Token | nice |
Token ID | 3621 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
Jackie | +0.029 |
cere | +0.027 |
organ | +0.027 |
ingu | +0.026 |
isha | +0.025 |
Neg logit contributions | |
course | -0.037 |
aw | -0.035 |
Run | -0.032 |
ican | -0.031 |
crow | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
course | +0.032 |
aw | +0.031 |
crow | +0.027 |
Too | +0.026 |
Run | +0.026 |
Neg logit contributions | |
organ | -0.031 |
any | -0.031 |
ilda | -0.031 |
cere | -0.031 |
nie | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
aw | +0.044 |
course | +0.036 |
crow | +0.034 |
ar | +0.033 |
bye | +0.032 |
Neg logit contributions | |
nie | -0.035 |
Em | -0.033 |
any | -0.033 |
Jackie | -0.033 |
organ | -0.032 |
Token | slide |
Token ID | 10649 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
aw | +0.015 |
course | +0.014 |
crow | +0.012 |
ar | +0.011 |
Run | +0.011 |
Neg logit contributions | |
nie | -0.025 |
cere | -0.024 |
Em | -0.024 |
organ | -0.024 |
any | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
Run | +0.147 |
hawk | +0.145 |
course | +0.139 |
Too | +0.139 |
crow | +0.136 |
Neg logit contributions | |
nie | -0.102 |
cere | -0.096 |
organ | -0.094 |
neatly | -0.094 |
ingu | -0.091 |
Token | the |
Token ID | 262 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
aw | +0.026 |
course | +0.024 |
crow | +0.021 |
Too | +0.020 |
ar | +0.020 |
Neg logit contributions | |
organ | -0.020 |
nie | -0.020 |
Em | -0.020 |
Jackie | -0.019 |
ilda | -0.019 |
Token | sees |
Token ID | 7224 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
aw | +0.016 |
course | +0.015 |
crow | +0.013 |
ar | +0.012 |
Run | +0.011 |
Neg logit contributions | |
nie | -0.026 |
cere | -0.025 |
Em | -0.025 |
organ | -0.025 |
any | -0.025 |
Token | aw |
Token ID | 707 |
Feature activation | +7.38e+00 |
Pos logit contributions | |
ar | +0.045 |
course | +0.043 |
Too | +0.040 |
hawk | +0.040 |
bye | +0.036 |
Neg logit contributions | |
cere | -0.138 |
magnets | -0.136 |
iddles | -0.135 |
designs | -0.133 |
ingu | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
course | +0.363 |
aw | +0.317 |
Run | +0.308 |
crow | +0.307 |
Too | +0.307 |
Neg logit contributions | |
ilda | -0.221 |
organ | -0.219 |
iddles | -0.218 |
to | -0.218 |
isha | -0.208 |
Token | They |
Token ID | 1119 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
aw | +0.015 |
course | +0.015 |
crow | +0.012 |
Run | +0.011 |
goose | +0.011 |
Neg logit contributions | |
organ | -0.014 |
Em | -0.014 |
ilda | -0.014 |
Jackie | -0.013 |
ingu | -0.013 |
Token | have |
Token ID | 423 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
aw | +0.082 |
course | +0.075 |
crow | +0.067 |
Run | +0.064 |
Too | +0.062 |
Neg logit contributions | |
organ | -0.069 |
nie | -0.068 |
ilda | -0.066 |
ingu | -0.066 |
any | -0.066 |
Token | a |
Token ID | 257 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
organ | +0.001 |
Em | +0.001 |
cere | +0.001 |
die | +0.001 |
nie | +0.001 |
Neg logit contributions | |
course | -0.001 |
aw | -0.001 |
crow | -0.001 |
Run | -0.001 |
aroo | -0.001 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Em | +0.008 |
nie | +0.007 |
isha | +0.007 |
organ | +0.007 |
ilda | +0.007 |
Neg logit contributions | |
aw | -0.009 |
course | -0.008 |
crow | -0.007 |
Run | -0.007 |
Too | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
aw | +0.096 |
course | +0.093 |
bye | +0.088 |
Too | +0.088 |
Run | +0.085 |
Neg logit contributions | |
ingu | -0.101 |
Jackie | -0.099 |
daddy | -0.095 |
cere | -0.094 |
iddles | -0.092 |
Token | big |
Token ID | 1263 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ilda | +0.012 |
organ | +0.012 |
nie | +0.012 |
Em | +0.012 |
any | +0.012 |
Neg logit contributions | |
aw | -0.013 |
course | -0.012 |
crow | -0.010 |
Run | -0.010 |
goose | -0.009 |
Token | hole |
Token ID | 7604 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
aw | +0.054 |
course | +0.048 |
crow | +0.044 |
Run | +0.043 |
Too | +0.043 |
Neg logit contributions | |
nie | -0.043 |
cere | -0.042 |
isha | -0.041 |
die | -0.041 |
daddy | -0.041 |
Token | in |
Token ID | 287 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
aw | +0.140 |
course | +0.140 |
crow | +0.126 |
Too | +0.125 |
Run | +0.122 |
Neg logit contributions | |
nie | -0.063 |
organ | -0.056 |
cere | -0.056 |
ilda | -0.055 |
Jackie | -0.054 |
Token | the |
Token ID | 262 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
organ | +0.047 |
nie | +0.047 |
Jackie | +0.047 |
cere | +0.046 |
ilda | +0.046 |
Neg logit contributions | |
aw | -0.055 |
course | -0.047 |
crow | -0.042 |
Too | -0.040 |
Run | -0.039 |
Token | middle |
Token ID | 3504 |
Feature activation | +7.38e+00 |
Pos logit contributions | |
aw | +0.015 |
course | +0.014 |
Run | +0.012 |
crow | +0.011 |
Too | +0.011 |
Neg logit contributions | |
nie | -0.017 |
cere | -0.017 |
ilda | -0.017 |
ingu | -0.017 |
any | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
aw | +0.313 |
course | +0.309 |
Run | +0.298 |
Too | +0.287 |
ican | +0.281 |
Neg logit contributions | |
nie | -0.255 |
cere | -0.254 |
ilda | -0.249 |
any | -0.246 |
isha | -0.238 |
Token |
|
Token ID | 198 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
aw | +0.006 |
course | +0.005 |
crow | +0.005 |
Run | +0.004 |
goose | +0.004 |
Neg logit contributions | |
ilda | -0.007 |
nie | -0.007 |
organ | -0.007 |
any | -0.007 |
Em | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
nie | +0.012 |
ilda | +0.012 |
any | +0.012 |
organ | +0.012 |
Em | +0.011 |
Neg logit contributions | |
aw | -0.009 |
course | -0.009 |
crow | -0.007 |
Run | -0.007 |
fountain | -0.007 |
Token | " |
Token ID | 1 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
Em | +0.010 |
organ | +0.010 |
nie | +0.009 |
die | +0.009 |
isha | +0.009 |
Neg logit contributions | |
course | -0.011 |
aw | -0.011 |
crow | -0.009 |
goose | -0.009 |
ican | -0.009 |
Token | Thirty |
Token ID | 38856 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
aw | +0.037 |
course | +0.036 |
crow | +0.029 |
Run | +0.027 |
goose | +0.027 |
Neg logit contributions | |
organ | -0.044 |
ilda | -0.044 |
nie | -0.044 |
Em | -0.044 |
any | -0.043 |
Token | had |
Token ID | 550 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
ilda | +0.000 |
organ | +0.000 |
nie | +0.000 |
Em | +0.000 |
any | +0.000 |
Neg logit contributions | |
aw | -0.000 |
course | -0.000 |
crow | -0.000 |
Run | -0.000 |
goose | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
cere | +0.060 |
nie | +0.060 |
ingu | +0.060 |
organ | +0.060 |
ilda | +0.059 |
Neg logit contributions | |
course | -0.066 |
aw | -0.063 |
crow | -0.057 |
Run | -0.055 |
Too | -0.053 |
Token | hole |
Token ID | 7604 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
ilda | +0.018 |
organ | +0.018 |
nie | +0.018 |
Em | +0.017 |
ingu | +0.017 |
Neg logit contributions | |
aw | -0.020 |
course | -0.020 |
crow | -0.017 |
Run | -0.016 |
Too | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
course | +0.133 |
aw | +0.132 |
crow | +0.115 |
Run | +0.114 |
Too | +0.114 |
Neg logit contributions | |
nie | -0.077 |
ilda | -0.076 |
organ | -0.075 |
any | -0.074 |
cere | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
cere | +0.052 |
organ | +0.052 |
ilda | +0.051 |
nie | +0.051 |
Jackie | +0.051 |
Neg logit contributions | |
aw | -0.052 |
course | -0.047 |
crow | -0.041 |
Run | -0.040 |
Too | -0.039 |
Token | middle |
Token ID | 3504 |
Feature activation | +7.37e+00 |
Pos logit contributions | |
aw | +0.013 |
course | +0.012 |
Run | +0.011 |
crow | +0.010 |
Too | +0.010 |
Neg logit contributions | |
nie | -0.013 |
ilda | -0.013 |
cere | -0.013 |
ingu | -0.012 |
any | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
course | +0.309 |
aw | +0.303 |
Run | +0.279 |
Too | +0.268 |
hawk | +0.256 |
Neg logit contributions | |
nie | -0.281 |
cere | -0.280 |
ilda | -0.275 |
any | -0.273 |
organ | -0.265 |
Token | She |
Token ID | 1375 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
organ | +0.006 |
cere | +0.005 |
ilda | +0.005 |
to | +0.005 |
nie | +0.005 |
Neg logit contributions | |
course | -0.004 |
aw | -0.004 |
crow | -0.003 |
Run | -0.003 |
hawk | -0.003 |
Token | wondered |
Token ID | 14028 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
ilda | +0.001 |
Em | +0.001 |
any | +0.001 |
organ | +0.001 |
iddles | +0.001 |
Neg logit contributions | |
aw | -0.001 |
course | -0.001 |
Run | -0.001 |
fountain | -0.001 |
dove | -0.001 |
Token | what |
Token ID | 644 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
organ | +0.030 |
any | +0.029 |
Em | +0.029 |
ilda | +0.029 |
nie | +0.029 |
Neg logit contributions | |
aw | -0.027 |
course | -0.026 |
no | -0.021 |
goose | -0.020 |
crow | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
organ | +0.145 |
ilda | +0.142 |
nie | +0.142 |
Em | +0.141 |
Jackie | +0.138 |
Neg logit contributions | |
aw | -0.125 |
course | -0.120 |
Run | -0.103 |
crow | -0.100 |
Too | -0.098 |
Token | with |
Token ID | 351 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
aw | +0.029 |
course | +0.028 |
Run | +0.025 |
crow | +0.024 |
Too | +0.024 |
Neg logit contributions | |
nie | -0.023 |
ilda | -0.023 |
organ | -0.023 |
any | -0.023 |
to | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
aw | +0.142 |
course | +0.129 |
crow | +0.119 |
Run | +0.117 |
Too | +0.116 |
Neg logit contributions | |
Jackie | -0.135 |
ingu | -0.130 |
cere | -0.130 |
nie | -0.130 |
die | -0.128 |
Token | hole |
Token ID | 7604 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
aw | +0.001 |
course | +0.001 |
crow | +0.001 |
Run | +0.001 |
Too | +0.001 |
Neg logit contributions | |
nie | -0.001 |
ilda | -0.001 |
organ | -0.001 |
Em | -0.001 |
die | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
aw | +0.131 |
course | +0.129 |
crow | +0.114 |
Too | +0.112 |
Run | +0.111 |
Neg logit contributions | |
nie | -0.096 |
ilda | -0.092 |
any | -0.092 |
organ | -0.090 |
Jackie | -0.090 |
Token | the |
Token ID | 262 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
organ | +0.067 |
nie | +0.067 |
Jackie | +0.067 |
ilda | +0.066 |
cere | +0.066 |
Neg logit contributions | |
aw | -0.066 |
course | -0.057 |
crow | -0.050 |
Run | -0.048 |
Too | -0.048 |
Token | middle |
Token ID | 3504 |
Feature activation | +7.36e+00 |
Pos logit contributions | |
aw | +0.031 |
course | +0.029 |
crow | +0.024 |
Run | +0.024 |
Too | +0.023 |
Neg logit contributions | |
nie | -0.035 |
ilda | -0.034 |
any | -0.034 |
ingu | -0.034 |
Em | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
aw | +0.288 |
course | +0.283 |
Run | +0.259 |
Too | +0.248 |
ican | +0.239 |
Neg logit contributions | |
nie | -0.287 |
any | -0.284 |
cere | -0.281 |
ilda | -0.280 |
Jackie | -0.273 |
Token | She |
Token ID | 1375 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
ilda | +0.019 |
organ | +0.019 |
nie | +0.019 |
Em | +0.019 |
any | +0.019 |
Neg logit contributions | |
aw | -0.017 |
course | -0.017 |
crow | -0.014 |
Run | -0.013 |
goose | -0.013 |
Token | stepped |
Token ID | 10764 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
ilda | +0.001 |
organ | +0.001 |
nie | +0.001 |
Em | +0.001 |
any | +0.001 |
Neg logit contributions | |
aw | -0.001 |
course | -0.001 |
crow | -0.000 |
Run | -0.000 |
goose | -0.000 |
Token | into |
Token ID | 656 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
ilda | +0.023 |
organ | +0.022 |
nie | +0.022 |
Em | +0.022 |
Jackie | +0.022 |
Neg logit contributions | |
aw | -0.025 |
course | -0.025 |
crow | -0.021 |
Run | -0.020 |
Too | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
ilda | +0.055 |
organ | +0.055 |
nie | +0.054 |
Em | +0.054 |
any | +0.054 |
Neg logit contributions | |
aw | -0.041 |
course | -0.039 |
crow | -0.031 |
Run | -0.029 |
goose | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
aw | +0.032 |
course | +0.031 |
crow | +0.025 |
Too | +0.024 |
ar | +0.024 |
Neg logit contributions | |
nie | -0.035 |
Jackie | -0.035 |
any | -0.035 |
ilda | -0.034 |
Em | -0.034 |
Token | slide |
Token ID | 10649 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
aw | +0.016 |
course | +0.016 |
crow | +0.013 |
Run | +0.012 |
Too | +0.012 |
Neg logit contributions | |
nie | -0.021 |
ilda | -0.021 |
Em | -0.021 |
any | -0.021 |
cere | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
course | +0.125 |
aw | +0.123 |
Run | +0.121 |
hawk | +0.117 |
ican | +0.113 |
Neg logit contributions | |
nie | -0.114 |
ilda | -0.109 |
any | -0.109 |
organ | -0.103 |
cere | -0.101 |
Token | the |
Token ID | 262 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
aw | +0.023 |
course | +0.021 |
crow | +0.018 |
Too | +0.018 |
ar | +0.018 |
Neg logit contributions | |
nie | -0.023 |
Jackie | -0.023 |
any | -0.022 |
organ | -0.022 |
ilda | -0.022 |
Token | sees |
Token ID | 7224 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
aw | +0.018 |
course | +0.017 |
crow | +0.014 |
Run | +0.013 |
ar | +0.013 |
Neg logit contributions | |
nie | -0.023 |
cere | -0.023 |
any | -0.022 |
ilda | -0.022 |
Em | -0.022 |
Token | aw |
Token ID | 707 |
Feature activation | +7.35e+00 |
Pos logit contributions | |
course | +0.103 |
crow | +0.092 |
ar | +0.092 |
Too | +0.092 |
Run | +0.089 |
Neg logit contributions | |
cere | -0.117 |
ilda | -0.114 |
Em | -0.114 |
nie | -0.113 |
organ | -0.113 |
Token | . |
Token ID | 13 |
Feature activation | +5.69e-02 |
Pos logit contributions | |
course | +0.345 |
aw | +0.298 |
crow | +0.289 |
Run | +0.285 |
Too | +0.279 |
Neg logit contributions | |
ilda | -0.256 |
to | -0.248 |
any | -0.240 |
organ | -0.236 |
nie | -0.235 |
Token | They |
Token ID | 1119 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
aw | +0.002 |
course | +0.002 |
crow | +0.002 |
Run | +0.002 |
goose | +0.002 |
Neg logit contributions | |
Em | -0.002 |
Jackie | -0.002 |
ilda | -0.002 |
organ | -0.002 |
isha | -0.002 |
Token | had |
Token ID | 550 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
aw | +0.083 |
course | +0.077 |
crow | +0.068 |
Too | +0.065 |
Run | +0.064 |
Neg logit contributions | |
nie | -0.079 |
organ | -0.076 |
ilda | -0.076 |
any | -0.075 |
Jackie | -0.075 |
Token | a |
Token ID | 257 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
organ | +0.048 |
supposed | +0.044 |
unp | +0.044 |
cere | +0.043 |
nie | +0.043 |
Neg logit contributions | |
course | -0.076 |
crow | -0.074 |
aw | -0.070 |
ican | -0.068 |
aroo | -0.068 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
nie | +0.013 |
die | +0.013 |
isha | +0.012 |
Em | +0.012 |
bie | +0.012 |
Neg logit contributions | |
aw | -0.018 |
course | -0.017 |
crow | -0.016 |
Run | -0.014 |
ican | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
aw | +0.032 |
course | +0.030 |
crow | +0.025 |
Too | +0.023 |
Run | +0.023 |
Neg logit contributions | |
organ | -0.035 |
Jackie | -0.034 |
nie | -0.034 |
to | -0.033 |
any | -0.033 |
Token | swings |
Token ID | 26728 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
aw | +0.016 |
course | +0.016 |
crow | +0.012 |
Run | +0.011 |
Too | +0.011 |
Neg logit contributions | |
organ | -0.025 |
nie | -0.025 |
ilda | -0.025 |
Em | -0.024 |
any | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Run | +0.226 |
Too | +0.224 |
aw | +0.220 |
course | +0.213 |
ican | +0.208 |
Neg logit contributions | |
organ | -0.151 |
neatly | -0.145 |
nie | -0.138 |
ingu | -0.137 |
daddy | -0.134 |
Token | the |
Token ID | 262 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
aw | +0.007 |
course | +0.007 |
crow | +0.005 |
Too | +0.005 |
ar | +0.005 |
Neg logit contributions | |
organ | -0.009 |
nie | -0.009 |
Jackie | -0.008 |
any | -0.008 |
Em | -0.008 |
Token | sees |
Token ID | 7224 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
aw | +0.013 |
course | +0.013 |
crow | +0.010 |
Run | +0.009 |
Too | +0.008 |
Neg logit contributions | |
nie | -0.026 |
organ | -0.026 |
ilda | -0.026 |
Em | -0.026 |
any | -0.026 |
Token | aw |
Token ID | 707 |
Feature activation | +7.35e+00 |
Pos logit contributions | |
course | +0.042 |
ar | +0.036 |
Too | +0.031 |
ishly | +0.031 |
hawk | +0.030 |
Neg logit contributions | |
cere | -0.152 |
organ | -0.151 |
to | -0.148 |
ingu | -0.145 |
nie | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
course | +0.328 |
aw | +0.297 |
Run | +0.268 |
crow | +0.268 |
Too | +0.258 |
Neg logit contributions | |
ilda | -0.274 |
organ | -0.274 |
to | -0.266 |
iddles | -0.261 |
any | -0.259 |
Token | But |
Token ID | 887 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
organ | +0.003 |
ilda | +0.003 |
Em | +0.003 |
nie | +0.003 |
any | +0.003 |
Neg logit contributions | |
aw | -0.003 |
course | -0.003 |
crow | -0.002 |
Run | -0.002 |
goose | -0.002 |
Token | sometimes |
Token ID | 3360 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
aw | +0.141 |
course | +0.114 |
crow | +0.103 |
hy | +0.096 |
Run | +0.095 |
Neg logit contributions | |
Jackie | -0.146 |
nie | -0.138 |
daddy | -0.137 |
die | -0.132 |
Em | -0.131 |
Token | , |
Token ID | 11 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
aw | +0.027 |
course | +0.026 |
crow | +0.020 |
Too | +0.020 |
Run | +0.019 |
Neg logit contributions | |
Jackie | -0.038 |
nie | -0.037 |
ilda | -0.037 |
organ | -0.037 |
isha | -0.036 |
Token | Sam |
Token ID | 3409 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
aw | +0.026 |
course | +0.024 |
crow | +0.020 |
Too | +0.019 |
Run | +0.019 |
Neg logit contributions | |
Jackie | -0.032 |
organ | -0.031 |
ilda | -0.031 |
Em | -0.031 |
nie | -0.031 |
Token | The |
Token ID | 383 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
organ | +0.001 |
Em | +0.001 |
ilda | +0.001 |
nie | +0.001 |
Jackie | +0.001 |
Neg logit contributions | |
aw | -0.001 |
course | -0.001 |
crow | -0.000 |
Run | -0.000 |
goose | -0.000 |
Token | bird |
Token ID | 6512 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
aw | +0.058 |
course | +0.056 |
ishly | +0.055 |
Leave | +0.053 |
ar | +0.053 |
Neg logit contributions | |
daddy | -0.049 |
crystals | -0.046 |
crystal | -0.045 |
designs | -0.044 |
design | -0.044 |
Token | sits |
Token ID | 10718 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
aw | +0.100 |
course | +0.099 |
crow | +0.091 |
Run | +0.088 |
Too | +0.084 |
Neg logit contributions | |
die | -0.108 |
nie | -0.107 |
organ | -0.107 |
cere | -0.105 |
ingu | -0.104 |
Token | on |
Token ID | 319 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
organ | +0.007 |
to | +0.006 |
iddles | +0.006 |
any | +0.006 |
nie | +0.006 |
Neg logit contributions | |
course | -0.010 |
aw | -0.009 |
crow | -0.008 |
Run | -0.008 |
hy | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
aw | +0.029 |
crow | +0.027 |
course | +0.027 |
Too | +0.025 |
Run | +0.025 |
Neg logit contributions | |
Jackie | -0.017 |
isha | -0.017 |
daddy | -0.017 |
cere | -0.017 |
die | -0.016 |
Token | middle |
Token ID | 3504 |
Feature activation | +7.34e+00 |
Pos logit contributions | |
course | +0.015 |
aw | +0.014 |
crow | +0.014 |
ar | +0.013 |
ishly | +0.012 |
Neg logit contributions | |
nie | -0.017 |
ilda | -0.017 |
any | -0.016 |
cere | -0.015 |
to | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Run | +0.335 |
Too | +0.321 |
ishly | +0.318 |
course | +0.316 |
Bad | +0.310 |
Neg logit contributions | |
and | -0.221 |
nie | -0.210 |
cere | -0.196 |
to | -0.194 |
bie | -0.193 |
Token | balances |
Token ID | 25223 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
aw | +0.005 |
course | +0.005 |
crow | +0.004 |
Run | +0.004 |
Too | +0.004 |
Neg logit contributions | |
organ | -0.005 |
ilda | -0.005 |
nie | -0.005 |
cere | -0.005 |
to | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -8.98e-02 |
Pos logit contributions | |
organ | +0.018 |
cere | +0.018 |
die | +0.018 |
nie | +0.017 |
Jackie | +0.017 |
Neg logit contributions | |
course | -0.027 |
aw | -0.025 |
crow | -0.024 |
Too | -0.024 |
Leave | -0.023 |
Token | They |
Token ID | 1119 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
organ | +0.004 |
ilda | +0.004 |
Em | +0.004 |
nie | +0.004 |
ingu | +0.004 |
Neg logit contributions | |
aw | -0.004 |
course | -0.003 |
crow | -0.003 |
Run | -0.003 |
goose | -0.003 |
Token | g |
Token ID | 308 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
aw | +0.071 |
course | +0.066 |
crow | +0.058 |
Run | +0.056 |
Too | +0.054 |
Neg logit contributions | |
organ | -0.062 |
nie | -0.061 |
ingu | -0.061 |
ilda | -0.060 |
any | -0.059 |
Token | She |
Token ID | 1375 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
aw | +0.007 |
course | +0.007 |
crow | +0.006 |
Run | +0.005 |
goose | +0.005 |
Neg logit contributions | |
organ | -0.011 |
ilda | -0.011 |
Em | -0.011 |
any | -0.011 |
nie | -0.011 |
Token | got |
Token ID | 1392 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
course | +0.004 |
aw | +0.003 |
crow | +0.003 |
Run | +0.003 |
goose | +0.003 |
Neg logit contributions | |
nie | -0.003 |
organ | -0.003 |
ilda | -0.003 |
Em | -0.003 |
any | -0.003 |
Token | stuck |
Token ID | 7819 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
organ | +0.030 |
ilda | +0.028 |
nie | +0.028 |
Em | +0.027 |
any | +0.027 |
Neg logit contributions | |
course | -0.029 |
aw | -0.029 |
crow | -0.023 |
Run | -0.022 |
Too | -0.021 |
Token | in |
Token ID | 287 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
organ | +0.014 |
ilda | +0.014 |
nie | +0.013 |
any | +0.013 |
Em | +0.013 |
Neg logit contributions | |
course | -0.019 |
aw | -0.019 |
crow | -0.016 |
Too | -0.016 |
Run | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
organ | +0.044 |
cere | +0.042 |
Em | +0.042 |
Jackie | +0.042 |
ilda | +0.042 |
Neg logit contributions | |
aw | -0.057 |
course | -0.050 |
crow | -0.048 |
bye | -0.047 |
ar | -0.046 |
Token | middle |
Token ID | 3504 |
Feature activation | +7.34e+00 |
Pos logit contributions | |
aw | +0.012 |
course | +0.011 |
Run | +0.009 |
ar | +0.009 |
crow | +0.009 |
Neg logit contributions | |
cere | -0.013 |
nie | -0.013 |
organ | -0.012 |
Em | -0.012 |
ingu | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
course | +0.333 |
aw | +0.323 |
Run | +0.323 |
ican | +0.312 |
hawk | +0.307 |
Neg logit contributions | |
and | -0.219 |
cere | -0.215 |
nie | -0.214 |
any | -0.212 |
ilda | -0.212 |
Token | She |
Token ID | 1375 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
aw | +0.006 |
course | +0.006 |
crow | +0.005 |
Run | +0.005 |
goose | +0.005 |
Neg logit contributions | |
organ | -0.007 |
ilda | -0.007 |
Em | -0.007 |
nie | -0.007 |
any | -0.007 |
Token | could |
Token ID | 714 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
aw | +0.002 |
course | +0.002 |
crow | +0.002 |
Run | +0.002 |
goose | +0.002 |
Neg logit contributions | |
organ | -0.002 |
ilda | -0.002 |
nie | -0.002 |
Em | -0.002 |
any | -0.002 |
Token | not |
Token ID | 407 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
organ | +0.099 |
ilda | +0.095 |
nie | +0.088 |
to | +0.087 |
Jackie | +0.087 |
Neg logit contributions | |
aw | -0.129 |
course | -0.123 |
crow | -0.107 |
Run | -0.098 |
Too | -0.094 |
Token | move |
Token ID | 1445 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
aw | +0.017 |
course | +0.016 |
crow | +0.013 |
Run | +0.012 |
goose | +0.012 |
Neg logit contributions | |
ilda | -0.024 |
Em | -0.024 |
nie | -0.024 |
isha | -0.024 |
ingu | -0.024 |
Token | Jane |
Token ID | 12091 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ilda | +0.023 |
Em | +0.022 |
nie | +0.022 |
any | +0.022 |
ingu | +0.022 |
Neg logit contributions | |
aw | -0.018 |
course | -0.016 |
crow | -0.012 |
goose | -0.012 |
Run | -0.012 |
Token | hopped |
Token ID | 45230 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
aw | +0.007 |
course | +0.007 |
crow | +0.006 |
Run | +0.005 |
Too | +0.005 |
Neg logit contributions | |
nie | -0.006 |
ilda | -0.006 |
any | -0.006 |
Em | -0.006 |
Jackie | -0.006 |
Token | on |
Token ID | 319 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
aw | +0.055 |
course | +0.053 |
crow | +0.045 |
Too | +0.045 |
Run | +0.045 |
Neg logit contributions | |
Jackie | -0.035 |
ilda | -0.034 |
nie | -0.034 |
to | -0.034 |
Em | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +4.23e-03 |
Pos logit contributions | |
Jackie | +0.007 |
ilda | +0.007 |
organ | +0.007 |
cere | +0.007 |
Em | +0.007 |
Neg logit contributions | |
aw | -0.009 |
course | -0.009 |
crow | -0.008 |
Too | -0.008 |
Run | -0.008 |
Token | sees |
Token ID | 7224 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
aw | +0.000 |
course | +0.000 |
crow | +0.000 |
Run | +0.000 |
Too | +0.000 |
Neg logit contributions | |
nie | -0.000 |
ilda | -0.000 |
any | -0.000 |
Em | -0.000 |
Jackie | -0.000 |
Token | aw |
Token ID | 707 |
Feature activation | +7.34e+00 |
Pos logit contributions | |
course | +0.106 |
aw | +0.103 |
Too | +0.093 |
crow | +0.090 |
Run | +0.090 |
Neg logit contributions | |
ilda | -0.116 |
Jackie | -0.116 |
nie | -0.114 |
Em | -0.113 |
organ | -0.112 |
Token | and |
Token ID | 290 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
course | +0.334 |
Run | +0.282 |
crow | +0.279 |
Too | +0.276 |
hawk | +0.276 |
Neg logit contributions | |
to | -0.256 |
ilda | -0.246 |
any | -0.245 |
iddles | -0.234 |
nie | -0.232 |
Token | before |
Token ID | 878 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
any | +0.010 |
ilda | +0.010 |
nie | +0.010 |
Jackie | +0.010 |
to | +0.010 |
Neg logit contributions | |
course | -0.011 |
aw | -0.011 |
crow | -0.009 |
Too | -0.009 |
Run | -0.008 |
Token | long |
Token ID | 890 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
aw | +0.058 |
course | +0.054 |
crow | +0.046 |
Too | +0.042 |
Run | +0.040 |
Neg logit contributions | |
Jackie | -0.076 |
ilda | -0.076 |
Em | -0.073 |
any | -0.072 |
isha | -0.071 |
Token | she |
Token ID | 673 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
aw | +0.018 |
course | +0.017 |
Too | +0.015 |
crow | +0.014 |
Run | +0.014 |
Neg logit contributions | |
ilda | -0.022 |
Jackie | -0.022 |
any | -0.021 |
nie | -0.021 |
cere | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
organ | +0.015 |
ilda | +0.015 |
nie | +0.015 |
Em | +0.015 |
any | +0.015 |
Neg logit contributions | |
aw | -0.018 |
course | -0.018 |
crow | -0.015 |
Run | -0.015 |
Too | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
daddy | +0.038 |
ingu | +0.037 |
Jackie | +0.036 |
cere | +0.035 |
magnets | +0.035 |
Neg logit contributions | |
Too | -0.056 |
course | -0.054 |
aw | -0.052 |
ican | -0.049 |
Run | -0.048 |
Token | sandbox |
Token ID | 35204 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
ilda | +0.015 |
organ | +0.015 |
nie | +0.014 |
Em | +0.014 |
ingu | +0.014 |
Neg logit contributions | |
aw | -0.014 |
course | -0.013 |
crow | -0.011 |
Run | -0.011 |
Too | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
Run | +0.163 |
Too | +0.159 |
aw | +0.157 |
course | +0.157 |
Leave | +0.153 |
Neg logit contributions | |
neatly | -0.080 |
unp | -0.079 |
cere | -0.079 |
organ | -0.076 |
iddles | -0.076 |
Token | a |
Token ID | 257 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
aw | +0.028 |
course | +0.026 |
crow | +0.024 |
Too | +0.022 |
ar | +0.021 |
Neg logit contributions | |
organ | -0.026 |
nie | -0.025 |
Jackie | -0.025 |
Em | -0.025 |
ilda | -0.025 |
Token | sees |
Token ID | 7224 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Em | +0.015 |
nie | +0.015 |
ingu | +0.015 |
cere | +0.015 |
organ | +0.015 |
Neg logit contributions | |
aw | -0.012 |
course | -0.011 |
crow | -0.009 |
Run | -0.008 |
Too | -0.008 |
Token | aw |
Token ID | 707 |
Feature activation | +7.33e+00 |
Pos logit contributions | |
course | +0.065 |
hawk | +0.064 |
ar | +0.060 |
crow | +0.060 |
Too | +0.060 |
Neg logit contributions | |
cere | -0.114 |
magnets | -0.110 |
polished | -0.108 |
crystals | -0.107 |
neatly | -0.107 |
Token | . |
Token ID | 13 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
course | +0.357 |
aw | +0.301 |
Run | +0.301 |
crow | +0.300 |
Too | +0.299 |
Neg logit contributions | |
to | -0.230 |
ilda | -0.225 |
iddles | -0.221 |
organ | -0.219 |
aghetti | -0.212 |
Token | They |
Token ID | 1119 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
aw | +0.003 |
course | +0.003 |
crow | +0.003 |
Run | +0.003 |
goose | +0.002 |
Neg logit contributions | |
organ | -0.003 |
ilda | -0.003 |
Em | -0.003 |
nie | -0.003 |
any | -0.003 |
Token | have |
Token ID | 423 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
aw | +0.081 |
course | +0.077 |
crow | +0.066 |
Run | +0.063 |
Too | +0.062 |
Neg logit contributions | |
organ | -0.076 |
nie | -0.075 |
ilda | -0.075 |
ingu | -0.073 |
any | -0.072 |
Token | fun |
Token ID | 1257 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
organ | +0.004 |
cere | +0.004 |
ingu | +0.004 |
Em | +0.004 |
nie | +0.004 |
Neg logit contributions | |
aw | -0.005 |
course | -0.005 |
crow | -0.005 |
Run | -0.004 |
Too | -0.004 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
organ | +0.009 |
ilda | +0.008 |
nie | +0.008 |
any | +0.008 |
Em | +0.008 |
Neg logit contributions | |
aw | -0.010 |
course | -0.009 |
crow | -0.009 |
Run | -0.008 |
Too | -0.008 |
Token | dogs |
Token ID | 6844 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
aw | +0.073 |
course | +0.073 |
crow | +0.060 |
Run | +0.060 |
Too | +0.054 |
Neg logit contributions | |
nie | -0.066 |
ilda | -0.065 |
ingu | -0.064 |
cere | -0.063 |
any | -0.063 |
Token | and |
Token ID | 290 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
aw | +0.091 |
course | +0.088 |
Too | +0.077 |
crow | +0.075 |
Run | +0.074 |
Neg logit contributions | |
ilda | -0.084 |
organ | -0.083 |
any | -0.083 |
nie | -0.081 |
Em | -0.080 |
Token | walk |
Token ID | 2513 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
aw | +0.015 |
course | +0.014 |
crow | +0.012 |
Too | +0.011 |
ican | +0.011 |
Neg logit contributions | |
organ | -0.012 |
nie | -0.012 |
cere | -0.012 |
ilda | -0.012 |
any | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
organ | +0.001 |
to | +0.001 |
nie | +0.001 |
any | +0.001 |
Jackie | +0.001 |
Neg logit contributions | |
course | -0.002 |
aw | -0.002 |
Too | -0.002 |
Run | -0.002 |
hawk | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
Jackie | +0.012 |
ilda | +0.012 |
nie | +0.012 |
organ | +0.012 |
daddy | +0.012 |
Neg logit contributions | |
aw | -0.015 |
course | -0.014 |
Too | -0.012 |
crow | -0.012 |
Run | -0.011 |
Token | middle |
Token ID | 3504 |
Feature activation | +7.33e+00 |
Pos logit contributions | |
aw | +0.018 |
course | +0.017 |
crow | +0.013 |
neither | +0.013 |
Run | +0.013 |
Neg logit contributions | |
ilda | -0.021 |
cere | -0.021 |
ingu | -0.021 |
nie | -0.021 |
die | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
course | +0.321 |
Run | +0.311 |
Too | +0.307 |
hawk | +0.304 |
aw | +0.303 |
Neg logit contributions | |
and | -0.226 |
any | -0.205 |
Em | -0.202 |
to | -0.202 |
nie | -0.202 |
Token | the |
Token ID | 262 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
Jackie | +0.038 |
organ | +0.038 |
Em | +0.038 |
ilda | +0.037 |
any | +0.036 |
Neg logit contributions | |
aw | -0.051 |
course | -0.044 |
Too | -0.040 |
crow | -0.039 |
ar | -0.039 |
Token | park |
Token ID | 3952 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
aw | +0.016 |
course | +0.014 |
neither | +0.012 |
crow | +0.012 |
no | +0.012 |
Neg logit contributions | |
Em | -0.020 |
organ | -0.020 |
ilda | -0.020 |
nie | -0.019 |
cere | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +8.05e-03 |
Pos logit contributions | |
course | +0.165 |
aw | +0.153 |
Run | +0.152 |
Too | +0.149 |
hawk | +0.149 |
Neg logit contributions | |
any | -0.072 |
to | -0.069 |
ilda | -0.067 |
unp | -0.066 |
organ | -0.065 |
Token | They |
Token ID | 1119 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
aw | +0.000 |
course | +0.000 |
crow | +0.000 |
Run | +0.000 |
goose | +0.000 |
Neg logit contributions | |
ilda | -0.000 |
organ | -0.000 |
nie | -0.000 |
Em | -0.000 |
any | -0.000 |
Token | because |
Token ID | 780 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
aw | +0.087 |
course | +0.084 |
crow | +0.070 |
Run | +0.068 |
goose | +0.066 |
Neg logit contributions | |
ilda | -0.079 |
organ | -0.079 |
nie | -0.078 |
Em | -0.077 |
any | -0.076 |
Token | he |
Token ID | 339 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
ilda | +0.039 |
nie | +0.038 |
Jackie | +0.038 |
organ | +0.037 |
Em | +0.037 |
Neg logit contributions | |
aw | -0.036 |
course | -0.034 |
crow | -0.027 |
Run | -0.027 |
Too | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
aw | +0.004 |
course | +0.004 |
crow | +0.003 |
goose | +0.003 |
Too | +0.003 |
Neg logit contributions | |
ilda | -0.004 |
Em | -0.004 |
Jackie | -0.004 |
ingu | -0.004 |
organ | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
aw | +0.035 |
course | +0.032 |
no | +0.028 |
goose | +0.026 |
crow | +0.026 |
Neg logit contributions | |
ilda | -0.054 |
Em | -0.054 |
organ | -0.053 |
ingu | -0.053 |
any | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
organ | +0.047 |
ilda | +0.047 |
nie | +0.046 |
cere | +0.046 |
Em | +0.045 |
Neg logit contributions | |
aw | -0.055 |
course | -0.049 |
crow | -0.043 |
Run | -0.042 |
ican | -0.041 |
Token | middle |
Token ID | 3504 |
Feature activation | +7.33e+00 |
Pos logit contributions | |
aw | +0.014 |
course | +0.013 |
Run | +0.012 |
crow | +0.011 |
aroo | +0.010 |
Neg logit contributions | |
organ | -0.012 |
ilda | -0.011 |
Em | -0.011 |
cere | -0.011 |
ingu | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
course | +0.308 |
aw | +0.307 |
Run | +0.299 |
hawk | +0.287 |
ican | +0.279 |
Neg logit contributions | |
nie | -0.276 |
ilda | -0.270 |
cere | -0.259 |
any | -0.258 |
Em | -0.253 |
Token | his |
Token ID | 465 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
ilda | +0.065 |
organ | +0.064 |
nie | +0.064 |
Em | +0.063 |
any | +0.063 |
Neg logit contributions | |
aw | -0.044 |
course | -0.043 |
crow | -0.033 |
Run | -0.032 |
goose | -0.031 |
Token | book |
Token ID | 1492 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
aw | +0.022 |
course | +0.021 |
crow | +0.018 |
goose | +0.018 |
fountain | +0.018 |
Neg logit contributions | |
organ | -0.017 |
ilda | -0.017 |
nie | -0.017 |
any | -0.017 |
Em | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
aw | +0.122 |
course | +0.119 |
Run | +0.108 |
crow | +0.107 |
Too | +0.103 |
Neg logit contributions | |
ilda | -0.106 |
organ | -0.102 |
Em | -0.102 |
nie | -0.102 |
ingu | -0.098 |
Token | but |
Token ID | 475 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
aw | +0.025 |
course | +0.023 |
crow | +0.020 |
Run | +0.018 |
ar | +0.018 |
Neg logit contributions | |
nie | -0.026 |
Jackie | -0.025 |
ilda | -0.025 |
organ | -0.025 |
any | -0.025 |
Token | They |
Token ID | 1119 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
aw | +0.009 |
course | +0.009 |
crow | +0.007 |
Run | +0.007 |
goose | +0.007 |
Neg logit contributions | |
ilda | -0.010 |
organ | -0.010 |
nie | -0.010 |
Em | -0.010 |
any | -0.010 |
Token | run |
Token ID | 1057 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
aw | +0.079 |
course | +0.076 |
crow | +0.063 |
Run | +0.060 |
Too | +0.058 |
Neg logit contributions | |
organ | -0.091 |
nie | -0.089 |
ilda | -0.089 |
ingu | -0.087 |
any | -0.086 |
Token | to |
Token ID | 284 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
course | +0.194 |
aw | +0.184 |
Too | +0.153 |
hawk | +0.153 |
ican | +0.153 |
Neg logit contributions | |
organ | -0.096 |
to | -0.089 |
ilda | -0.078 |
nie | -0.078 |
any | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
ilda | +0.012 |
organ | +0.012 |
Jackie | +0.012 |
nie | +0.012 |
any | +0.012 |
Neg logit contributions | |
aw | -0.011 |
course | -0.010 |
crow | -0.008 |
Too | -0.008 |
Run | -0.008 |
Token | sees |
Token ID | 7224 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
aw | +0.019 |
course | +0.019 |
ar | +0.016 |
Run | +0.015 |
crow | +0.015 |
Neg logit contributions | |
ilda | -0.024 |
Em | -0.024 |
organ | -0.023 |
any | -0.023 |
daddy | -0.023 |
Token | aw |
Token ID | 707 |
Feature activation | +7.33e+00 |
Pos logit contributions | |
course | +0.107 |
Too | +0.103 |
hawk | +0.101 |
ar | +0.101 |
bye | +0.098 |
Neg logit contributions | |
daddy | -0.092 |
cere | -0.088 |
Jackie | -0.087 |
ingu | -0.086 |
magnets | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
course | +0.345 |
aw | +0.306 |
crow | +0.290 |
Run | +0.285 |
Too | +0.279 |
Neg logit contributions | |
ilda | -0.245 |
to | -0.237 |
organ | -0.236 |
isha | -0.233 |
iddles | -0.232 |
Token | but |
Token ID | 475 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
aw | +0.039 |
course | +0.036 |
crow | +0.033 |
ar | +0.033 |
bye | +0.032 |
Neg logit contributions | |
daddy | -0.024 |
any | -0.023 |
scrub | -0.023 |
nie | -0.022 |
Jackie | -0.021 |
Token | they |
Token ID | 484 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
aw | +0.074 |
course | +0.073 |
crow | +0.059 |
ican | +0.054 |
Run | +0.054 |
Neg logit contributions | |
daddy | -0.073 |
Jackie | -0.072 |
nie | -0.070 |
ilda | -0.069 |
organ | -0.067 |
Token | do |
Token ID | 466 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
aw | +0.044 |
course | +0.042 |
crow | +0.032 |
Run | +0.030 |
Too | +0.028 |
Neg logit contributions | |
organ | -0.076 |
ilda | -0.076 |
nie | -0.075 |
any | -0.074 |
ingu | -0.074 |
Token | not |
Token ID | 407 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
aw | +0.032 |
course | +0.030 |
crow | +0.026 |
Run | +0.024 |
goose | +0.024 |
Neg logit contributions | |
ilda | -0.034 |
organ | -0.034 |
nie | -0.033 |
Em | -0.032 |
any | -0.032 |
Token | she |
Token ID | 673 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
organ | +0.069 |
ilda | +0.069 |
nie | +0.068 |
Em | +0.067 |
any | +0.067 |
Neg logit contributions | |
aw | -0.063 |
course | -0.061 |
crow | -0.050 |
Run | -0.048 |
goose | -0.047 |
Token | was |
Token ID | 373 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
ilda | +0.026 |
organ | +0.026 |
nie | +0.026 |
Em | +0.026 |
any | +0.026 |
Neg logit contributions | |
aw | -0.027 |
course | -0.026 |
crow | -0.022 |
Run | -0.021 |
goose | -0.021 |
Token | inside |
Token ID | 2641 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
aw | +0.020 |
course | +0.020 |
crow | +0.017 |
Run | +0.016 |
Too | +0.016 |
Neg logit contributions | |
ilda | -0.016 |
organ | -0.016 |
nie | -0.016 |
Em | -0.015 |
any | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
Jackie | +0.125 |
ilda | +0.125 |
nie | +0.121 |
Em | +0.121 |
organ | +0.120 |
Neg logit contributions | |
aw | -0.079 |
course | -0.070 |
crow | -0.057 |
Run | -0.055 |
Too | -0.052 |
Token | D |
Token ID | 360 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
Jackie | +0.008 |
ilda | +0.008 |
Em | +0.008 |
organ | +0.008 |
nie | +0.008 |
Neg logit contributions | |
aw | -0.006 |
course | -0.006 |
crow | -0.005 |
Run | -0.005 |
Too | -0.005 |
Token | ott |
Token ID | 1252 |
Feature activation | -9.97e+00 |
Pos logit contributions | |
organ | +0.042 |
ilda | +0.041 |
nie | +0.040 |
Em | +0.040 |
isha | +0.040 |
Neg logit contributions | |
aw | -0.044 |
course | -0.040 |
crow | -0.035 |
Too | -0.032 |
goose | -0.032 |
Token | ie |
Token ID | 494 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
organ | +0.314 |
Em | +0.304 |
cere | +0.295 |
ingu | +0.295 |
Jackie | +0.295 |
Neg logit contributions | |
aw | -0.532 |
course | -0.499 |
crow | -0.450 |
goose | -0.412 |
no | -0.391 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
organ | +0.168 |
ilda | +0.167 |
nie | +0.164 |
Em | +0.163 |
ingu | +0.162 |
Neg logit contributions | |
aw | -0.173 |
course | -0.166 |
crow | -0.138 |
Run | -0.133 |
goose | -0.129 |
Token | lots |
Token ID | 6041 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
aw | +0.060 |
course | +0.057 |
Too | +0.050 |
Run | +0.050 |
crow | +0.049 |
Neg logit contributions | |
ilda | -0.070 |
Jackie | -0.070 |
Em | -0.067 |
organ | -0.067 |
any | -0.066 |
Token | of |
Token ID | 286 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ilda | +0.045 |
Em | +0.045 |
organ | +0.044 |
Jackie | +0.044 |
nie | +0.044 |
Neg logit contributions | |
aw | -0.034 |
course | -0.033 |
Run | -0.027 |
Too | -0.027 |
crow | -0.027 |
Token | colorful |
Token ID | 20239 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
ilda | +0.060 |
organ | +0.059 |
nie | +0.058 |
any | +0.058 |
Em | +0.058 |
Neg logit contributions | |
aw | -0.057 |
course | -0.055 |
crow | -0.045 |
Run | -0.044 |
goose | -0.043 |
Token | box |
Token ID | 3091 |
Feature activation | -6.02e-03 |
Pos logit contributions | |
ilda | +0.001 |
nie | +0.001 |
organ | +0.001 |
Em | +0.001 |
cere | +0.001 |
Neg logit contributions | |
aw | -0.002 |
course | -0.001 |
crow | -0.001 |
Run | -0.001 |
Too | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
ilda | +0.000 |
Jackie | +0.000 |
nie | +0.000 |
to | +0.000 |
any | +0.000 |
Neg logit contributions | |
aw | -0.000 |
course | -0.000 |
Too | -0.000 |
crow | -0.000 |
Run | -0.000 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ilda | +0.012 |
organ | +0.012 |
any | +0.012 |
nie | +0.012 |
ingu | +0.011 |
Neg logit contributions | |
aw | -0.012 |
course | -0.012 |
Run | -0.009 |
crow | -0.009 |
fountain | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
aw | +0.060 |
course | +0.060 |
Too | +0.054 |
crow | +0.052 |
Run | +0.052 |
Neg logit contributions | |
ilda | -0.061 |
Jackie | -0.060 |
ingu | -0.060 |
organ | -0.058 |
cere | -0.058 |
Token | j |
Token ID | 474 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
ilda | +0.029 |
organ | +0.028 |
nie | +0.028 |
Em | +0.028 |
any | +0.028 |
Neg logit contributions | |
aw | -0.033 |
course | -0.032 |
crow | -0.027 |
Run | -0.026 |
Too | -0.025 |
Token | igsaw |
Token ID | 45636 |
Feature activation | -9.97e+00 |
Pos logit contributions | |
ilda | +0.053 |
nie | +0.052 |
ingu | +0.051 |
Jackie | +0.051 |
Em | +0.049 |
Neg logit contributions | |
aw | -0.077 |
course | -0.075 |
Run | -0.067 |
crow | -0.063 |
no | -0.063 |
Token | puzzle |
Token ID | 15027 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
organ | +0.405 |
ilda | +0.404 |
any | +0.395 |
nie | +0.394 |
ingu | +0.393 |
Neg logit contributions | |
course | -0.415 |
aw | -0.413 |
crow | -0.331 |
Run | -0.322 |
fountain | -0.317 |
Token | inside |
Token ID | 2641 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
ilda | +0.088 |
nie | +0.086 |
Em | +0.085 |
Jackie | +0.084 |
organ | +0.083 |
Neg logit contributions | |
aw | -0.101 |
course | -0.094 |
crow | -0.086 |
Too | -0.084 |
Run | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
ilda | +0.083 |
Jackie | +0.082 |
nie | +0.080 |
cere | +0.079 |
any | +0.079 |
Neg logit contributions | |
aw | -0.092 |
course | -0.087 |
crow | -0.079 |
Run | -0.077 |
Too | -0.076 |
Token | He |
Token ID | 679 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
organ | +0.022 |
ilda | +0.022 |
nie | +0.021 |
any | +0.021 |
Em | +0.020 |
Neg logit contributions | |
aw | -0.017 |
course | -0.016 |
crow | -0.013 |
Run | -0.012 |
fountain | -0.012 |
Token | paused |
Token ID | 24487 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
aw | +0.004 |
course | +0.004 |
Run | +0.003 |
no | +0.003 |
fountain | +0.003 |
Neg logit contributions | |
ilda | -0.005 |
organ | -0.004 |
any | -0.004 |
iddles | -0.004 |
nie | -0.004 |
Token | It |
Token ID | 632 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
ilda | +0.002 |
organ | +0.002 |
nie | +0.002 |
any | +0.002 |
Em | +0.002 |
Neg logit contributions | |
aw | -0.002 |
course | -0.002 |
crow | -0.001 |
Run | -0.001 |
goose | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
aw | +0.024 |
course | +0.023 |
crow | +0.020 |
Run | +0.020 |
goose | +0.019 |
Neg logit contributions | |
ilda | -0.019 |
organ | -0.019 |
nie | -0.019 |
any | -0.019 |
Em | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
aw | +0.036 |
course | +0.035 |
crow | +0.029 |
Run | +0.029 |
Too | +0.027 |
Neg logit contributions | |
ilda | -0.037 |
organ | -0.036 |
nie | -0.036 |
Em | -0.036 |
any | -0.035 |
Token | big |
Token ID | 1263 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
nie | +0.024 |
Em | +0.024 |
ilda | +0.024 |
organ | +0.024 |
isha | +0.023 |
Neg logit contributions | |
aw | -0.031 |
course | -0.029 |
crow | -0.026 |
Run | -0.025 |
Too | -0.023 |
Token | j |
Token ID | 474 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
aw | +0.038 |
course | +0.031 |
Run | +0.030 |
crow | +0.030 |
Too | +0.028 |
Neg logit contributions | |
nie | -0.036 |
Jackie | -0.034 |
Em | -0.033 |
daddy | -0.033 |
any | -0.033 |
Token | igsaw |
Token ID | 45636 |
Feature activation | -9.96e+00 |
Pos logit contributions | |
ilda | +0.058 |
nie | +0.057 |
Em | +0.056 |
Jackie | +0.055 |
any | +0.055 |
Neg logit contributions | |
aw | -0.074 |
course | -0.072 |
Run | -0.063 |
crow | -0.060 |
no | -0.059 |
Token | puzzle |
Token ID | 15027 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
organ | +0.370 |
ilda | +0.369 |
any | +0.358 |
nie | +0.358 |
ingu | +0.357 |
Neg logit contributions | |
aw | -0.452 |
course | -0.450 |
crow | -0.369 |
Run | -0.357 |
goose | -0.350 |
Token | and |
Token ID | 290 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
ilda | +0.091 |
nie | +0.090 |
Em | +0.090 |
any | +0.086 |
Jackie | +0.086 |
Neg logit contributions | |
aw | -0.089 |
course | -0.081 |
Run | -0.077 |
Too | -0.075 |
crow | -0.074 |
Token | she |
Token ID | 673 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
ilda | +0.007 |
organ | +0.007 |
nie | +0.007 |
Em | +0.007 |
any | +0.007 |
Neg logit contributions | |
aw | -0.005 |
course | -0.005 |
crow | -0.004 |
Run | -0.004 |
goose | -0.004 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ilda | +0.023 |
organ | +0.023 |
ingu | +0.022 |
Em | +0.022 |
Jackie | +0.022 |
Neg logit contributions | |
aw | -0.024 |
course | -0.023 |
crow | -0.019 |
no | -0.018 |
Too | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
organ | +0.006 |
ilda | +0.006 |
nie | +0.006 |
Em | +0.006 |
any | +0.006 |
Neg logit contributions | |
aw | -0.008 |
course | -0.007 |
crow | -0.006 |
Run | -0.006 |
goose | -0.006 |
Token | would |
Token ID | 561 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
Jackie | +0.003 |
obby | +0.003 |
ilda | +0.003 |
ingu | +0.003 |
any | +0.003 |
Neg logit contributions | |
course | -0.002 |
aw | -0.002 |
no | -0.002 |
bars | -0.002 |
dove | -0.002 |
Token | take |
Token ID | 1011 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ilda | +0.021 |
any | +0.020 |
Em | +0.020 |
ingu | +0.020 |
isha | +0.020 |
Neg logit contributions | |
course | -0.020 |
aw | -0.018 |
no | -0.016 |
fountain | -0.015 |
middle | -0.015 |
Token | out |
Token ID | 503 |
Feature activation | -9.91e-02 |
Pos logit contributions | |
any | +0.012 |
ilda | +0.011 |
Em | +0.011 |
isha | +0.011 |
nie | +0.011 |
Neg logit contributions | |
aw | -0.007 |
course | -0.007 |
crow | -0.005 |
no | -0.005 |
middle | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
ilda | +0.005 |
any | +0.005 |
organ | +0.005 |
Em | +0.005 |
nie | +0.005 |
Neg logit contributions | |
aw | -0.004 |
course | -0.004 |
crow | -0.003 |
no | -0.003 |
Run | -0.003 |
Token | j |
Token ID | 474 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
any | +0.033 |
ascal | +0.031 |
ilda | +0.031 |
iddles | +0.030 |
ingu | +0.030 |
Neg logit contributions | |
course | -0.023 |
aw | -0.020 |
fountain | -0.018 |
gate | -0.017 |
middle | -0.017 |
Token | igsaw |
Token ID | 45636 |
Feature activation | -9.96e+00 |
Pos logit contributions | |
ilda | +0.061 |
nie | +0.060 |
organ | +0.060 |
ingu | +0.059 |
Em | +0.059 |
Neg logit contributions | |
aw | -0.071 |
course | -0.069 |
Run | -0.058 |
crow | -0.057 |
goose | -0.054 |
Token | puzzle |
Token ID | 15027 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
any | +0.368 |
organ | +0.363 |
ilda | +0.360 |
ingu | +0.358 |
to | +0.355 |
Neg logit contributions | |
course | -0.462 |
aw | -0.434 |
fountain | -0.350 |
crow | -0.349 |
goose | -0.336 |
Token | and |
Token ID | 290 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
ilda | +0.090 |
organ | +0.090 |
nie | +0.088 |
Em | +0.088 |
any | +0.086 |
Neg logit contributions | |
aw | -0.088 |
course | -0.084 |
crow | -0.071 |
Run | -0.070 |
Too | -0.068 |
Token | try |
Token ID | 1949 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
ilda | +0.013 |
Em | +0.013 |
any | +0.013 |
nie | +0.013 |
ingu | +0.013 |
Neg logit contributions | |
course | -0.014 |
aw | -0.013 |
no | -0.011 |
middle | -0.010 |
crow | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
any | +0.034 |
Em | +0.034 |
nie | +0.033 |
ingu | +0.031 |
Jackie | +0.031 |
Neg logit contributions | |
aw | -0.019 |
course | -0.017 |
that | -0.014 |
more | -0.013 |
no | -0.013 |
Token | solve |
Token ID | 8494 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
any | +0.024 |
ilda | +0.024 |
isha | +0.024 |
ingu | +0.023 |
bie | +0.023 |
Neg logit contributions | |
course | -0.032 |
aw | -0.029 |
no | -0.025 |
middle | -0.025 |
center | -0.024 |
Token | said |
Token ID | 531 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
aw | +0.086 |
course | +0.085 |
Too | +0.075 |
crow | +0.072 |
Run | +0.071 |
Neg logit contributions | |
ilda | -0.077 |
any | -0.075 |
organ | -0.068 |
isha | -0.068 |
Em | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
ilda | +0.006 |
Jackie | +0.006 |
Em | +0.006 |
organ | +0.006 |
nie | +0.006 |
Neg logit contributions | |
aw | -0.004 |
course | -0.004 |
Run | -0.003 |
crow | -0.003 |
Too | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
organ | +0.006 |
ingu | +0.006 |
ilda | +0.006 |
nie | +0.006 |
any | +0.006 |
Neg logit contributions | |
aw | -0.004 |
course | -0.004 |
Run | -0.003 |
crow | -0.003 |
goose | -0.003 |
Token | Hello |
Token ID | 15496 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
ilda | +0.043 |
organ | +0.042 |
ingu | +0.042 |
nie | +0.042 |
isha | +0.041 |
Neg logit contributions | |
aw | -0.036 |
course | -0.035 |
crow | -0.029 |
Run | -0.028 |
Too | -0.027 |
Token | D |
Token ID | 360 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
aw | +0.009 |
course | +0.008 |
crow | +0.006 |
fountain | +0.006 |
goose | +0.006 |
Neg logit contributions | |
organ | -0.016 |
nie | -0.016 |
Em | -0.016 |
any | -0.016 |
ilda | -0.016 |
Token | ott |
Token ID | 1252 |
Feature activation | -9.68e+00 |
Pos logit contributions | |
organ | +0.028 |
nie | +0.027 |
Em | +0.027 |
die | +0.026 |
isha | +0.025 |
Neg logit contributions | |
aw | -0.058 |
course | -0.055 |
crow | -0.051 |
ar | -0.046 |
Too | -0.046 |
Token | ie |
Token ID | 494 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
organ | +0.324 |
Em | +0.318 |
cere | +0.295 |
ingu | +0.293 |
Jackie | +0.292 |
Neg logit contributions | |
aw | -0.491 |
course | -0.467 |
crow | -0.440 |
goose | -0.395 |
ar | -0.370 |
Token | ! |
Token ID | 0 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
ilda | +0.181 |
nie | +0.180 |
any | +0.176 |
organ | +0.175 |
Em | +0.174 |
Neg logit contributions | |
aw | -0.139 |
course | -0.134 |
crow | -0.107 |
Run | -0.105 |
Too | -0.101 |
Token | This |
Token ID | 770 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
aw | +0.002 |
course | +0.002 |
crow | +0.001 |
Run | +0.001 |
Too | +0.001 |
Neg logit contributions | |
organ | -0.003 |
ilda | -0.003 |
nie | -0.003 |
ingu | -0.003 |
Em | -0.003 |
Token | is |
Token ID | 318 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
aw | +0.014 |
course | +0.014 |
crow | +0.011 |
Run | +0.010 |
goose | +0.010 |
Neg logit contributions | |
organ | -0.020 |
ilda | -0.020 |
nie | -0.020 |
Em | -0.020 |
any | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
aw | +0.072 |
course | +0.071 |
crow | +0.055 |
Run | +0.051 |
no | +0.050 |
Neg logit contributions | |
organ | -0.104 |
ilda | -0.103 |
any | -0.101 |
nie | -0.100 |
ingu | -0.100 |
Token | Everyday |
Token ID | 48154 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
course | +0.045 |
aw | +0.044 |
crow | +0.034 |
fountain | +0.034 |
no | +0.034 |
Neg logit contributions | |
organ | -0.045 |
ilda | -0.043 |
cere | -0.043 |
to | -0.043 |
nie | -0.043 |
Token | he |
Token ID | 339 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
aw | +0.014 |
course | +0.012 |
crow | +0.010 |
Run | +0.010 |
Too | +0.010 |
Neg logit contributions | |
nie | -0.018 |
Jackie | -0.018 |
ilda | -0.018 |
Em | -0.018 |
any | -0.018 |
Token | would |
Token ID | 561 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
aw | +0.026 |
course | +0.025 |
crow | +0.021 |
Run | +0.021 |
goose | +0.020 |
Neg logit contributions | |
ilda | -0.020 |
organ | -0.019 |
Em | -0.019 |
nie | -0.019 |
any | -0.019 |
Token | take |
Token ID | 1011 |
Feature activation | -7.21e-02 |
Pos logit contributions | |
ilda | +0.056 |
organ | +0.056 |
nie | +0.055 |
Em | +0.055 |
any | +0.054 |
Neg logit contributions | |
aw | -0.057 |
course | -0.055 |
crow | -0.046 |
Run | -0.044 |
goose | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
ilda | +0.003 |
organ | +0.003 |
nie | +0.003 |
Em | +0.003 |
any | +0.003 |
Neg logit contributions | |
aw | -0.003 |
course | -0.003 |
crow | -0.002 |
Run | -0.002 |
goose | -0.002 |
Token | av |
Token ID | 1196 |
Feature activation | -9.64e+00 |
Pos logit contributions | |
ilda | +0.021 |
organ | +0.021 |
nie | +0.020 |
Em | +0.020 |
any | +0.020 |
Neg logit contributions | |
aw | -0.022 |
course | -0.021 |
crow | -0.018 |
Run | -0.017 |
goose | -0.017 |
Token | oc |
Token ID | 420 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
ilda | +0.530 |
Jackie | +0.513 |
Em | +0.513 |
any | +0.512 |
isha | +0.507 |
Neg logit contributions | |
aw | -0.309 |
course | -0.295 |
crow | -0.206 |
goose | -0.181 |
ar | -0.170 |
Token | ados |
Token ID | 22484 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
aw | +0.015 |
course | +0.015 |
crow | +0.012 |
goose | +0.012 |
Run | +0.012 |
Neg logit contributions | |
organ | -0.012 |
ilda | -0.012 |
Em | -0.012 |
nie | -0.012 |
any | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
organ | +0.160 |
ilda | +0.160 |
Em | +0.157 |
nie | +0.157 |
any | +0.156 |
Neg logit contributions | |
aw | -0.176 |
course | -0.173 |
crow | -0.142 |
Run | -0.133 |
goose | -0.133 |
Token | scatter |
Token ID | 41058 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
ilda | +0.021 |
organ | +0.020 |
Em | +0.020 |
nie | +0.020 |
any | +0.020 |
Neg logit contributions | |
aw | -0.022 |
course | -0.022 |
crow | -0.018 |
Run | -0.018 |
goose | -0.017 |
Token | them |
Token ID | 606 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
organ | +0.035 |
ilda | +0.035 |
nie | +0.035 |
Em | +0.035 |
any | +0.034 |
Neg logit contributions | |
aw | -0.033 |
course | -0.031 |
crow | -0.026 |
Run | -0.025 |
Too | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
aw | +0.035 |
course | +0.034 |
crow | +0.029 |
Run | +0.026 |
Too | +0.026 |
Neg logit contributions | |
organ | -0.042 |
Em | -0.041 |
nie | -0.041 |
ilda | -0.041 |
Jackie | -0.040 |
Token | good |
Token ID | 922 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
ilda | +0.029 |
organ | +0.029 |
any | +0.028 |
nie | +0.027 |
Em | +0.027 |
Neg logit contributions | |
aw | -0.032 |
course | -0.031 |
goose | -0.026 |
crow | -0.026 |
Run | -0.025 |
Token | dog |
Token ID | 3290 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
ilda | +0.011 |
organ | +0.011 |
nie | +0.011 |
Em | +0.011 |
any | +0.011 |
Neg logit contributions | |
aw | -0.006 |
course | -0.006 |
crow | -0.004 |
goose | -0.004 |
Run | -0.004 |
Token | named |
Token ID | 3706 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
aw | +0.148 |
course | +0.142 |
Too | +0.123 |
Run | +0.120 |
crow | +0.115 |
Neg logit contributions | |
Em | -0.182 |
ilda | -0.180 |
any | -0.180 |
nie | -0.180 |
isha | -0.176 |
Token | D |
Token ID | 360 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
aw | +0.104 |
course | +0.100 |
crow | +0.079 |
Run | +0.077 |
goose | +0.074 |
Neg logit contributions | |
ilda | -0.138 |
organ | -0.138 |
nie | -0.136 |
any | -0.134 |
Em | -0.134 |
Token | ott |
Token ID | 1252 |
Feature activation | -9.56e+00 |
Pos logit contributions | |
organ | +0.038 |
ilda | +0.037 |
nie | +0.036 |
any | +0.035 |
Em | +0.035 |
Neg logit contributions | |
aw | -0.039 |
course | -0.038 |
crow | -0.032 |
Run | -0.030 |
goose | -0.029 |
Token | ie |
Token ID | 494 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
organ | +0.313 |
Em | +0.301 |
Jackie | +0.301 |
cere | +0.288 |
ilda | +0.280 |
Neg logit contributions | |
aw | -0.497 |
course | -0.470 |
crow | -0.428 |
goose | -0.396 |
aroo | -0.363 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ilda | +0.161 |
nie | +0.161 |
organ | +0.159 |
any | +0.159 |
Em | +0.157 |
Neg logit contributions | |
aw | -0.148 |
course | -0.144 |
crow | -0.118 |
Run | -0.116 |
Too | -0.113 |
Token | D |
Token ID | 360 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
organ | +0.005 |
ingu | +0.004 |
ilda | +0.004 |
Jackie | +0.004 |
any | +0.004 |
Neg logit contributions | |
aw | -0.005 |
course | -0.005 |
crow | -0.004 |
Run | -0.004 |
goose | -0.004 |
Token | ott |
Token ID | 1252 |
Feature activation | -9.51e+00 |
Pos logit contributions | |
nie | +0.028 |
Em | +0.026 |
isha | +0.025 |
die | +0.025 |
ccoli | +0.024 |
Neg logit contributions | |
aw | -0.052 |
course | -0.049 |
crow | -0.043 |
Too | -0.039 |
fountain | -0.039 |
Token | ie |
Token ID | 494 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
Em | +0.331 |
Jackie | +0.324 |
cere | +0.317 |
epad | +0.315 |
organ | +0.315 |
Neg logit contributions | |
aw | -0.460 |
course | -0.422 |
crow | -0.392 |
goose | -0.331 |
aroo | -0.310 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
ilda | +0.030 |
organ | +0.029 |
Em | +0.029 |
ingu | +0.029 |
any | +0.029 |
Neg logit contributions | |
aw | -0.027 |
course | -0.027 |
crow | -0.021 |
goose | -0.020 |
fountain | -0.020 |
Token | |
Token ID | 220 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
aw | +0.001 |
course | +0.001 |
crow | +0.001 |
Run | +0.001 |
goose | +0.001 |
Neg logit contributions | |
ilda | -0.001 |
organ | -0.001 |
nie | -0.001 |
Em | -0.001 |
any | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
nie | +0.075 |
organ | +0.071 |
any | +0.071 |
ilda | +0.070 |
isha | +0.070 |
Neg logit contributions | |
aw | -0.041 |
course | -0.035 |
crow | -0.030 |
fountain | -0.026 |
no | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
nie | +0.036 |
ilda | +0.036 |
organ | +0.035 |
any | +0.034 |
isha | +0.034 |
Neg logit contributions | |
aw | -0.030 |
course | -0.030 |
crow | -0.024 |
Run | -0.023 |
goose | -0.022 |
Token | D |
Token ID | 35 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
organ | +0.032 |
Em | +0.031 |
ilda | +0.031 |
nie | +0.031 |
any | +0.031 |
Neg logit contributions | |
aw | -0.035 |
course | -0.034 |
crow | -0.028 |
Run | -0.027 |
goose | -0.026 |
Token | ott |
Token ID | 1252 |
Feature activation | -9.54e+00 |
Pos logit contributions | |
Em | +0.069 |
die | +0.068 |
nie | +0.066 |
isha | +0.063 |
Peter | +0.062 |
Neg logit contributions | |
aw | -0.122 |
course | -0.109 |
crow | -0.104 |
ar | -0.095 |
Too | -0.090 |
Token | ie |
Token ID | 494 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
cere | +0.333 |
Em | +0.332 |
organ | +0.323 |
Jackie | +0.322 |
ingu | +0.316 |
Neg logit contributions | |
aw | -0.467 |
course | -0.433 |
crow | -0.404 |
goose | -0.336 |
aroo | -0.318 |
Token | per |
Token ID | 583 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
ilda | +0.158 |
organ | +0.157 |
nie | +0.155 |
Em | +0.154 |
any | +0.153 |
Neg logit contributions | |
aw | -0.151 |
course | -0.146 |
crow | -0.121 |
Run | -0.116 |
goose | -0.113 |
Token | ked |
Token ID | 9091 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
ilda | +0.013 |
organ | +0.013 |
nie | +0.013 |
Em | +0.013 |
any | +0.013 |
Neg logit contributions | |
aw | -0.015 |
course | -0.015 |
crow | -0.013 |
Run | -0.012 |
goose | -0.012 |
Token | up |
Token ID | 510 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
organ | +0.009 |
ilda | +0.009 |
nie | +0.009 |
any | +0.009 |
Em | +0.009 |
Neg logit contributions | |
aw | -0.011 |
course | -0.010 |
crow | -0.009 |
Run | -0.008 |
Too | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
aw | +0.055 |
course | +0.053 |
crow | +0.044 |
Too | +0.044 |
Leave | +0.043 |
Neg logit contributions | |
Jackie | -0.042 |
organ | -0.041 |
Em | -0.038 |
ilda | -0.037 |
to | -0.037 |
Token | After |
Token ID | 2293 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
organ | +0.033 |
nie | +0.033 |
ilda | +0.033 |
isha | +0.031 |
Em | +0.031 |
Neg logit contributions | |
aw | -0.026 |
course | -0.025 |
crow | -0.021 |
Run | -0.019 |
fountain | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
aw | +0.060 |
course | +0.055 |
crow | +0.049 |
Run | +0.045 |
goose | +0.045 |
Neg logit contributions | |
ilda | -0.061 |
organ | -0.060 |
Jackie | -0.060 |
Em | -0.060 |
any | -0.058 |
Token | while |
Token ID | 981 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
organ | +0.036 |
ilda | +0.036 |
any | +0.035 |
nie | +0.035 |
ingu | +0.035 |
Neg logit contributions | |
course | -0.031 |
aw | -0.031 |
crow | -0.025 |
Run | -0.024 |
goose | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
aw | +0.142 |
course | +0.119 |
Too | +0.102 |
goose | +0.097 |
fountain | +0.095 |
Neg logit contributions | |
Jackie | -0.156 |
Grac | -0.143 |
Em | -0.141 |
ilda | -0.139 |
Sad | -0.133 |
Token | D |
Token ID | 360 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
Jackie | +0.002 |
ilda | +0.002 |
Em | +0.002 |
organ | +0.002 |
ingu | +0.002 |
Neg logit contributions | |
aw | -0.002 |
course | -0.002 |
crow | -0.001 |
Run | -0.001 |
Too | -0.001 |
Token | ott |
Token ID | 1252 |
Feature activation | -9.51e+00 |
Pos logit contributions | |
nie | +0.029 |
die | +0.029 |
Em | +0.028 |
isha | +0.028 |
aghetti | +0.027 |
Neg logit contributions | |
aw | -0.051 |
course | -0.048 |
crow | -0.044 |
Too | -0.040 |
ar | -0.040 |
Token | ie |
Token ID | 494 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
Em | +0.310 |
organ | +0.305 |
cere | +0.305 |
Jackie | +0.298 |
ingu | +0.297 |
Neg logit contributions | |
aw | -0.489 |
course | -0.462 |
crow | -0.430 |
goose | -0.366 |
ar | -0.351 |
Token | was |
Token ID | 373 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
ilda | +0.148 |
organ | +0.146 |
nie | +0.145 |
any | +0.144 |
Em | +0.143 |
Neg logit contributions | |
aw | -0.156 |
course | -0.152 |
crow | -0.126 |
Run | -0.122 |
Too | -0.118 |
Token | no |
Token ID | 645 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
aw | +0.031 |
course | +0.030 |
crow | +0.025 |
Run | +0.025 |
Too | +0.024 |
Neg logit contributions | |
ilda | -0.027 |
organ | -0.026 |
nie | -0.026 |
any | -0.026 |
Em | -0.026 |
Token | longer |
Token ID | 2392 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
aw | +0.227 |
course | +0.213 |
crow | +0.175 |
Run | +0.165 |
Too | +0.161 |
Neg logit contributions | |
nie | -0.292 |
organ | -0.288 |
Jackie | -0.287 |
ilda | -0.284 |
Em | -0.280 |
Token | scared |
Token ID | 12008 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
aw | +0.135 |
course | +0.126 |
crow | +0.106 |
Run | +0.100 |
goose | +0.097 |
Neg logit contributions | |
ilda | -0.161 |
organ | -0.160 |
ingu | -0.157 |
nie | -0.157 |
Em | -0.157 |
Token | D |
Token ID | 360 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
aw | +0.104 |
course | +0.100 |
crow | +0.079 |
Run | +0.077 |
goose | +0.074 |
Neg logit contributions | |
ilda | -0.138 |
organ | -0.138 |
nie | -0.136 |
any | -0.134 |
Em | -0.134 |
Token | ott |
Token ID | 1252 |
Feature activation | -9.56e+00 |
Pos logit contributions | |
organ | +0.038 |
ilda | +0.037 |
nie | +0.036 |
any | +0.035 |
Em | +0.035 |
Neg logit contributions | |
aw | -0.039 |
course | -0.038 |
crow | -0.032 |
Run | -0.030 |
goose | -0.029 |
Token | ie |
Token ID | 494 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
organ | +0.313 |
Em | +0.301 |
Jackie | +0.301 |
cere | +0.288 |
ilda | +0.280 |
Neg logit contributions | |
aw | -0.497 |
course | -0.470 |
crow | -0.428 |
goose | -0.396 |
aroo | -0.363 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ilda | +0.161 |
nie | +0.161 |
organ | +0.159 |
any | +0.159 |
Em | +0.157 |
Neg logit contributions | |
aw | -0.148 |
course | -0.144 |
crow | -0.118 |
Run | -0.116 |
Too | -0.113 |
Token | D |
Token ID | 360 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
organ | +0.005 |
ingu | +0.004 |
ilda | +0.004 |
Jackie | +0.004 |
any | +0.004 |
Neg logit contributions | |
aw | -0.005 |
course | -0.005 |
crow | -0.004 |
Run | -0.004 |
goose | -0.004 |
Token | ott |
Token ID | 1252 |
Feature activation | -9.51e+00 |
Pos logit contributions | |
nie | +0.028 |
Em | +0.026 |
isha | +0.025 |
die | +0.025 |
ccoli | +0.024 |
Neg logit contributions | |
aw | -0.052 |
course | -0.049 |
crow | -0.043 |
Too | -0.039 |
fountain | -0.039 |
Token | ie |
Token ID | 494 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
Em | +0.331 |
Jackie | +0.324 |
cere | +0.317 |
epad | +0.315 |
organ | +0.315 |
Neg logit contributions | |
aw | -0.460 |
course | -0.422 |
crow | -0.392 |
goose | -0.331 |
aroo | -0.310 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
ilda | +0.125 |
organ | +0.124 |
nie | +0.121 |
Em | +0.120 |
any | +0.119 |
Neg logit contributions | |
aw | -0.184 |
course | -0.179 |
crow | -0.153 |
Run | -0.148 |
goose | -0.145 |
Token | to |
Token ID | 284 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
ilda | +0.005 |
organ | +0.005 |
nie | +0.005 |
Em | +0.005 |
any | +0.005 |
Neg logit contributions | |
aw | -0.007 |
course | -0.007 |
crow | -0.006 |
Run | -0.006 |
goose | -0.005 |
Token | visit |
Token ID | 3187 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ilda | +0.029 |
organ | +0.028 |
nie | +0.028 |
Em | +0.028 |
any | +0.028 |
Neg logit contributions | |
aw | -0.028 |
course | -0.027 |
crow | -0.023 |
Run | -0.022 |
goose | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
ilda | +0.054 |
organ | +0.054 |
nie | +0.053 |
Em | +0.053 |
any | +0.053 |
Neg logit contributions | |
aw | -0.039 |
course | -0.039 |
crow | -0.030 |
Run | -0.028 |
goose | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ilda | +0.052 |
organ | +0.051 |
nie | +0.051 |
Em | +0.050 |
any | +0.050 |
Neg logit contributions | |
aw | -0.044 |
course | -0.043 |
crow | -0.035 |
Run | -0.033 |
goose | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
ilda | +0.008 |
nie | +0.008 |
organ | +0.008 |
Em | +0.008 |
isha | +0.008 |
Neg logit contributions | |
aw | -0.007 |
course | -0.007 |
crow | -0.006 |
goose | -0.005 |
fountain | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ilda | +0.003 |
nie | +0.003 |
organ | +0.003 |
any | +0.003 |
cere | +0.003 |
Neg logit contributions | |
aw | -0.002 |
course | -0.002 |
crow | -0.002 |
Run | -0.002 |
goose | -0.002 |
Token | When |
Token ID | 2215 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
organ | +0.005 |
Em | +0.005 |
ilda | +0.005 |
nie | +0.005 |
ingu | +0.005 |
Neg logit contributions | |
aw | -0.007 |
course | -0.006 |
crow | -0.005 |
Run | -0.005 |
goose | -0.005 |
Token | D |
Token ID | 360 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
aw | +0.075 |
course | +0.071 |
crow | +0.059 |
Run | +0.056 |
Too | +0.053 |
Neg logit contributions | |
Jackie | -0.080 |
organ | -0.078 |
ilda | -0.077 |
ingu | -0.077 |
Em | -0.077 |
Token | ott |
Token ID | 1252 |
Feature activation | -9.49e+00 |
Pos logit contributions | |
nie | +0.030 |
Em | +0.029 |
die | +0.028 |
isha | +0.028 |
any | +0.026 |
Neg logit contributions | |
aw | -0.053 |
course | -0.051 |
crow | -0.045 |
Too | -0.042 |
ar | -0.042 |
Token | ie |
Token ID | 494 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
Em | +0.345 |
Jackie | +0.327 |
cere | +0.327 |
organ | +0.323 |
ouses | +0.318 |
Neg logit contributions | |
aw | -0.453 |
course | -0.437 |
crow | -0.383 |
goose | -0.322 |
ar | -0.308 |
Token | arrived |
Token ID | 5284 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
ilda | +0.143 |
organ | +0.140 |
nie | +0.139 |
any | +0.138 |
Em | +0.137 |
Neg logit contributions | |
aw | -0.166 |
course | -0.160 |
crow | -0.134 |
Run | -0.132 |
Too | -0.128 |
Token | at |
Token ID | 379 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
Jackie | +0.020 |
ilda | +0.020 |
organ | +0.019 |
to | +0.019 |
ingu | +0.019 |
Neg logit contributions | |
course | -0.021 |
aw | -0.021 |
Run | -0.018 |
Too | -0.017 |
crow | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
course | +0.073 |
aw | +0.071 |
crow | +0.055 |
Run | +0.050 |
goose | +0.050 |
Neg logit contributions | |
nie | -0.121 |
organ | -0.121 |
ilda | -0.121 |
Em | -0.119 |
any | -0.118 |
Token | lab |
Token ID | 2248 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
aw | +0.002 |
course | +0.002 |
crow | +0.001 |
Run | +0.001 |
goose | +0.001 |
Neg logit contributions | |
ilda | -0.001 |
organ | -0.001 |
isha | -0.001 |
nie | -0.001 |
Em | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
aw | +0.013 |
course | +0.012 |
crow | +0.010 |
Too | +0.009 |
Run | +0.009 |
Neg logit contributions | |
Jackie | -0.015 |
ilda | -0.015 |
Em | -0.015 |
nie | -0.015 |
organ | -0.015 |
Token | kind |
Token ID | 1611 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
ilda | +0.026 |
organ | +0.026 |
nie | +0.026 |
Em | +0.026 |
any | +0.025 |
Neg logit contributions | |
aw | -0.031 |
course | -0.030 |
crow | -0.025 |
Run | -0.024 |
Too | -0.023 |
Token | deer |
Token ID | 20096 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
aw | +0.005 |
course | +0.004 |
Run | +0.004 |
Too | +0.004 |
crow | +0.003 |
Neg logit contributions | |
ilda | -0.005 |
nie | -0.005 |
Jackie | -0.005 |
isha | -0.005 |
Em | -0.005 |
Token | named |
Token ID | 3706 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
aw | +0.060 |
course | +0.055 |
Too | +0.052 |
crow | +0.048 |
Run | +0.047 |
Neg logit contributions | |
to | -0.044 |
any | -0.044 |
nie | -0.042 |
ilda | -0.042 |
Jackie | -0.041 |
Token | D |
Token ID | 360 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
aw | +0.132 |
course | +0.128 |
crow | +0.108 |
Run | +0.104 |
goose | +0.102 |
Neg logit contributions | |
organ | -0.110 |
ilda | -0.109 |
nie | -0.108 |
Em | -0.106 |
any | -0.106 |
Token | ott |
Token ID | 1252 |
Feature activation | -9.36e+00 |
Pos logit contributions | |
organ | +0.029 |
ilda | +0.027 |
nie | +0.027 |
cere | +0.026 |
Em | +0.026 |
Neg logit contributions | |
aw | -0.043 |
course | -0.042 |
crow | -0.038 |
goose | -0.034 |
Run | -0.034 |
Token | ie |
Token ID | 494 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
organ | +0.292 |
Em | +0.285 |
ilda | +0.279 |
Jackie | +0.278 |
ingu | +0.273 |
Neg logit contributions | |
aw | -0.498 |
course | -0.481 |
crow | -0.435 |
goose | -0.399 |
Run | -0.381 |
Token | appeared |
Token ID | 4120 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ilda | +0.150 |
any | +0.145 |
nie | +0.144 |
Jackie | +0.141 |
Em | +0.140 |
Neg logit contributions | |
aw | -0.145 |
course | -0.142 |
Run | -0.117 |
Too | -0.116 |
crow | -0.113 |
Token | . |
Token ID | 13 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
aw | +0.006 |
course | +0.006 |
crow | +0.005 |
Run | +0.004 |
goose | +0.004 |
Neg logit contributions | |
ilda | -0.007 |
organ | -0.007 |
nie | -0.006 |
Em | -0.006 |
any | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
organ | +0.021 |
nie | +0.021 |
ilda | +0.021 |
any | +0.020 |
isha | +0.020 |
Neg logit contributions | |
aw | -0.017 |
course | -0.016 |
crow | -0.014 |
Run | -0.013 |
goose | -0.013 |
Token | Leave |
Token ID | 35087 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
Em | +0.035 |
organ | +0.035 |
nie | +0.034 |
any | +0.034 |
ilda | +0.034 |
Neg logit contributions | |
aw | -0.036 |
course | -0.034 |
crow | -0.028 |
fountain | -0.027 |
goose | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
ilda | +0.013 |
nie | +0.012 |
organ | +0.012 |
cere | +0.012 |
any | +0.012 |
Neg logit contributions | |
aw | -0.010 |
course | -0.010 |
crow | -0.008 |
Run | -0.008 |
fountain | -0.007 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
ilda | +0.015 |
organ | +0.014 |
nie | +0.014 |
any | +0.014 |
Em | +0.014 |
Neg logit contributions | |
aw | -0.015 |
course | -0.014 |
crow | -0.012 |
Run | -0.011 |
goose | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
aw | +0.090 |
course | +0.089 |
Too | +0.073 |
crow | +0.070 |
Leave | +0.067 |
Neg logit contributions | |
Jackie | -0.117 |
organ | -0.109 |
daddy | -0.107 |
nie | -0.107 |
isha | -0.106 |
Token | they |
Token ID | 484 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
aw | +0.007 |
course | +0.006 |
crow | +0.005 |
Too | +0.005 |
hy | +0.005 |
Neg logit contributions | |
Jackie | -0.006 |
organ | -0.006 |
daddy | -0.006 |
Em | -0.006 |
isha | -0.006 |
Token | sp |
Token ID | 599 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
aw | +0.043 |
course | +0.042 |
crow | +0.034 |
Run | +0.033 |
goose | +0.032 |
Neg logit contributions | |
ilda | -0.049 |
organ | -0.049 |
nie | -0.048 |
Em | -0.048 |
any | -0.048 |
Token | ott |
Token ID | 1252 |
Feature activation | -9.34e+00 |
Pos logit contributions | |
ilda | +0.142 |
Em | +0.141 |
any | +0.141 |
organ | +0.141 |
Jackie | +0.139 |
Neg logit contributions | |
aw | -0.221 |
course | -0.201 |
crow | -0.173 |
Run | -0.169 |
goose | -0.163 |
Token | led |
Token ID | 992 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
Em | +0.333 |
Jackie | +0.332 |
organ | +0.326 |
ingu | +0.322 |
cere | +0.322 |
Neg logit contributions | |
aw | -0.472 |
course | -0.431 |
crow | -0.389 |
goose | -0.350 |
Run | -0.327 |
Token | a |
Token ID | 257 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
organ | +0.074 |
Jackie | +0.073 |
nie | +0.072 |
ilda | +0.071 |
any | +0.070 |
Neg logit contributions | |
course | -0.091 |
aw | -0.090 |
crow | -0.075 |
Too | -0.073 |
Run | -0.070 |
Token | bicycle |
Token ID | 17026 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
ilda | +0.027 |
nie | +0.027 |
Em | +0.027 |
organ | +0.027 |
isha | +0.026 |
Neg logit contributions | |
aw | -0.030 |
course | -0.029 |
crow | -0.024 |
Run | -0.023 |
Too | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
ilda | +0.030 |
organ | +0.030 |
any | +0.029 |
to | +0.028 |
nie | +0.028 |
Neg logit contributions | |
course | -0.041 |
aw | -0.041 |
crow | -0.038 |
Too | -0.036 |
goose | -0.035 |
Token | It |
Token ID | 632 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
ilda | +0.023 |
organ | +0.023 |
nie | +0.023 |
Em | +0.023 |
any | +0.023 |
Neg logit contributions | |
aw | -0.019 |
course | -0.018 |
crow | -0.014 |
Run | -0.014 |
goose | -0.013 |
Token | believe |
Token ID | 1975 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
ilda | +0.019 |
organ | +0.019 |
nie | +0.019 |
Em | +0.019 |
any | +0.019 |
Neg logit contributions | |
aw | -0.014 |
course | -0.013 |
crow | -0.010 |
Run | -0.010 |
goose | -0.009 |
Token | it |
Token ID | 340 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
organ | +0.235 |
any | +0.224 |
ingu | +0.223 |
nie | +0.222 |
Em | +0.220 |
Neg logit contributions | |
course | -0.135 |
aw | -0.134 |
crow | -0.096 |
no | -0.092 |
goose | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ilda | +0.037 |
organ | +0.036 |
nie | +0.036 |
Em | +0.035 |
any | +0.035 |
Neg logit contributions | |
aw | -0.032 |
course | -0.031 |
crow | -0.026 |
Run | -0.025 |
goose | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
organ | +0.080 |
nie | +0.078 |
ilda | +0.076 |
aghetti | +0.076 |
iddles | +0.075 |
Neg logit contributions | |
aw | -0.040 |
course | -0.039 |
crow | -0.029 |
Too | -0.027 |
middle | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
organ | +0.069 |
cere | +0.068 |
ccoli | +0.067 |
nie | +0.067 |
ingu | +0.067 |
Neg logit contributions | |
aw | -0.046 |
course | -0.045 |
crow | -0.033 |
Run | -0.032 |
Too | -0.031 |
Token | Em |
Token ID | 10161 |
Feature activation | -9.34e+00 |
Pos logit contributions | |
ingu | +0.060 |
organ | +0.059 |
ilda | +0.059 |
cere | +0.058 |
iddles | +0.058 |
Neg logit contributions | |
aw | -0.054 |
course | -0.052 |
Too | -0.041 |
Run | -0.041 |
crow | -0.040 |
Token | ma |
Token ID | 2611 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
organ | +0.419 |
emo | +0.407 |
ingu | +0.406 |
iddles | +0.403 |
ccoli | +0.397 |
Neg logit contributions | |
course | -0.375 |
aw | -0.335 |
Too | -0.249 |
Run | -0.247 |
crow | -0.241 |
Token | looked |
Token ID | 3114 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
organ | +0.063 |
ilda | +0.061 |
Em | +0.060 |
nie | +0.059 |
ingu | +0.059 |
Neg logit contributions | |
aw | -0.064 |
course | -0.061 |
crow | -0.049 |
Run | -0.048 |
goose | -0.047 |
Token | at |
Token ID | 379 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
organ | +0.109 |
ilda | +0.108 |
any | +0.107 |
Em | +0.106 |
nie | +0.106 |
Neg logit contributions | |
aw | -0.102 |
course | -0.097 |
crow | -0.079 |
Run | -0.076 |
goose | -0.074 |
Token | the |
Token ID | 262 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
aw | +0.071 |
course | +0.070 |
crow | +0.056 |
Run | +0.053 |
goose | +0.052 |
Neg logit contributions | |
organ | -0.082 |
ilda | -0.082 |
nie | -0.080 |
Em | -0.080 |
any | -0.079 |
Token | guitar |
Token ID | 10047 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
ilda | +0.017 |
nie | +0.017 |
Em | +0.016 |
isha | +0.016 |
organ | +0.016 |
Neg logit contributions | |
aw | -0.026 |
course | -0.025 |
crow | -0.023 |
Run | -0.022 |
Too | -0.021 |
Token | loyal |
Token ID | 9112 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ilda | +0.026 |
organ | +0.026 |
any | +0.025 |
nie | +0.024 |
ingu | +0.024 |
Neg logit contributions | |
aw | -0.028 |
course | -0.027 |
goose | -0.023 |
crow | -0.023 |
Run | -0.023 |
Token | little |
Token ID | 1310 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
aw | +0.032 |
course | +0.031 |
Run | +0.022 |
crow | +0.022 |
Too | +0.022 |
Neg logit contributions | |
nie | -0.064 |
ilda | -0.064 |
ingu | -0.064 |
Em | -0.064 |
isha | -0.063 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
nie | +0.052 |
isha | +0.050 |
Jackie | +0.050 |
Em | +0.050 |
daddy | +0.048 |
Neg logit contributions | |
aw | -0.049 |
course | -0.046 |
Too | -0.038 |
roads | -0.037 |
crow | -0.037 |
Token | named |
Token ID | 3706 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
aw | +0.039 |
course | +0.038 |
Too | +0.031 |
Run | +0.031 |
crow | +0.029 |
Neg logit contributions | |
any | -0.056 |
Em | -0.056 |
nie | -0.056 |
ilda | -0.055 |
isha | -0.054 |
Token | L |
Token ID | 406 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
aw | +0.093 |
course | +0.092 |
crow | +0.072 |
no | +0.068 |
Run | +0.068 |
Neg logit contributions | |
organ | -0.146 |
ingu | -0.144 |
ilda | -0.144 |
nie | -0.142 |
isha | -0.141 |
Token | ott |
Token ID | 1252 |
Feature activation | -9.33e+00 |
Pos logit contributions | |
aw | +0.007 |
course | +0.007 |
crow | +0.006 |
fountain | +0.005 |
Too | +0.005 |
Neg logit contributions | |
organ | -0.005 |
nie | -0.005 |
die | -0.005 |
any | -0.005 |
ccoli | -0.005 |
Token | ie |
Token ID | 494 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
organ | +0.325 |
Jackie | +0.324 |
Em | +0.318 |
cere | +0.300 |
ingu | +0.297 |
Neg logit contributions | |
aw | -0.455 |
course | -0.422 |
crow | -0.387 |
goose | -0.358 |
aroo | -0.322 |
Token | . |
Token ID | 13 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
ilda | +0.171 |
organ | +0.171 |
nie | +0.168 |
Em | +0.167 |
any | +0.166 |
Neg logit contributions | |
aw | -0.132 |
course | -0.127 |
crow | -0.102 |
Run | -0.097 |
goose | -0.094 |
Token | Every |
Token ID | 3887 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
aw | +0.001 |
course | +0.001 |
crow | +0.001 |
Run | +0.000 |
fountain | +0.000 |
Neg logit contributions | |
ilda | -0.001 |
nie | -0.001 |
organ | -0.001 |
Em | -0.001 |
any | -0.001 |
Token | day |
Token ID | 1110 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
aw | +0.008 |
course | +0.007 |
crow | +0.006 |
Run | +0.006 |
Too | +0.006 |
Neg logit contributions | |
nie | -0.005 |
organ | -0.005 |
Em | -0.005 |
to | -0.005 |
any | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
aw | +0.005 |
course | +0.005 |
Run | +0.004 |
crow | +0.004 |
goose | +0.004 |
Neg logit contributions | |
ilda | -0.009 |
Em | -0.008 |
Jackie | -0.008 |
organ | -0.008 |
isha | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
nie | +0.016 |
organ | +0.015 |
ilda | +0.015 |
any | +0.015 |
cere | +0.015 |
Neg logit contributions | |
aw | -0.012 |
course | -0.012 |
crow | -0.009 |
Run | -0.009 |
goose | -0.008 |
Token | One |
Token ID | 3198 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ilda | +0.017 |
organ | +0.017 |
nie | +0.017 |
Em | +0.017 |
any | +0.017 |
Neg logit contributions | |
aw | -0.015 |
course | -0.015 |
crow | -0.012 |
Run | -0.012 |
goose | -0.011 |
Token | day |
Token ID | 1110 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
aw | +0.080 |
course | +0.078 |
crow | +0.065 |
Run | +0.063 |
Too | +0.061 |
Neg logit contributions | |
nie | -0.069 |
ilda | -0.069 |
organ | -0.069 |
Em | -0.067 |
any | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
aw | +0.004 |
course | +0.004 |
crow | +0.003 |
Run | +0.003 |
goose | +0.002 |
Neg logit contributions | |
ilda | -0.007 |
organ | -0.007 |
Em | -0.007 |
Jackie | -0.007 |
nie | -0.007 |
Token | L |
Token ID | 406 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
aw | +0.011 |
course | +0.011 |
crow | +0.009 |
hawk | +0.009 |
Run | +0.009 |
Neg logit contributions | |
organ | -0.010 |
ilda | -0.010 |
Jackie | -0.009 |
Em | -0.009 |
isha | -0.009 |
Token | ott |
Token ID | 1252 |
Feature activation | -9.33e+00 |
Pos logit contributions | |
die | +0.004 |
nie | +0.004 |
ccoli | +0.004 |
Em | +0.004 |
any | +0.004 |
Neg logit contributions | |
aw | -0.008 |
course | -0.008 |
crow | -0.006 |
no | -0.006 |
Too | -0.006 |
Token | ie |
Token ID | 494 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
Em | +0.356 |
Jackie | +0.349 |
cere | +0.337 |
organ | +0.333 |
Grac | +0.327 |
Neg logit contributions | |
aw | -0.437 |
course | -0.391 |
crow | -0.362 |
goose | -0.307 |
crow | -0.280 |
Token | 's |
Token ID | 338 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
organ | +0.155 |
ilda | +0.155 |
nie | +0.151 |
Em | +0.151 |
ingu | +0.149 |
Neg logit contributions | |
aw | -0.148 |
course | -0.141 |
crow | -0.117 |
Run | -0.112 |
goose | -0.110 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ilda | +0.032 |
organ | +0.032 |
nie | +0.031 |
Em | +0.031 |
any | +0.031 |
Neg logit contributions | |
aw | -0.034 |
course | -0.033 |
crow | -0.027 |
Run | -0.026 |
goose | -0.025 |
Token | went |
Token ID | 1816 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
aw | +0.006 |
course | +0.006 |
crow | +0.005 |
no | +0.005 |
goose | +0.005 |
Neg logit contributions | |
organ | -0.006 |
cere | -0.006 |
ilda | -0.006 |
ouses | -0.006 |
nie | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
organ | +0.007 |
nie | +0.007 |
ingu | +0.007 |
Em | +0.007 |
ilda | +0.007 |
Neg logit contributions | |
aw | -0.007 |
course | -0.007 |
crow | -0.006 |
fountain | -0.006 |
goose | -0.006 |
Token | very |
Token ID | 845 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
ilda | +0.030 |
organ | +0.030 |
nie | +0.030 |
any | +0.029 |
Em | +0.029 |
Neg logit contributions | |
aw | -0.031 |
course | -0.030 |
crow | -0.025 |
Run | -0.024 |
goose | -0.024 |
Token | special |
Token ID | 2041 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
ilda | +0.062 |
organ | +0.061 |
nie | +0.060 |
Em | +0.060 |
any | +0.059 |
Neg logit contributions | |
aw | -0.086 |
course | -0.084 |
crow | -0.072 |
Run | -0.070 |
goose | -0.068 |
Token | toy |
Token ID | 13373 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
nie | +0.031 |
ilda | +0.031 |
organ | +0.031 |
any | +0.030 |
Jackie | +0.030 |
Neg logit contributions | |
aw | -0.036 |
course | -0.033 |
crow | -0.029 |
Run | -0.028 |
Too | -0.027 |
Token | for |
Token ID | 329 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
aw | +0.078 |
course | +0.074 |
Run | +0.064 |
Too | +0.063 |
crow | +0.061 |
Neg logit contributions | |
ilda | -0.071 |
ingu | -0.067 |
isha | -0.066 |
Jackie | -0.065 |
any | -0.065 |
Token | L |
Token ID | 406 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
aw | +0.071 |
course | +0.068 |
crow | +0.056 |
Run | +0.055 |
goose | +0.053 |
Neg logit contributions | |
ilda | -0.072 |
organ | -0.071 |
nie | -0.070 |
Em | -0.070 |
any | -0.069 |
Token | ott |
Token ID | 1252 |
Feature activation | -9.30e+00 |
Pos logit contributions | |
die | +0.005 |
ccoli | +0.004 |
nie | +0.004 |
organ | +0.004 |
any | +0.004 |
Neg logit contributions | |
aw | -0.007 |
course | -0.007 |
crow | -0.006 |
ila | -0.006 |
Too | -0.006 |
Token | ie |
Token ID | 494 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
organ | +0.299 |
Em | +0.297 |
Jackie | +0.286 |
isha | +0.278 |
ilda | +0.273 |
Neg logit contributions | |
aw | -0.473 |
course | -0.459 |
crow | -0.416 |
goose | -0.375 |
ar | -0.346 |
Token | . |
Token ID | 13 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
ilda | +0.157 |
nie | +0.154 |
organ | +0.154 |
any | +0.153 |
Em | +0.152 |
Neg logit contributions | |
aw | -0.139 |
course | -0.135 |
crow | -0.110 |
Run | -0.108 |
Too | -0.104 |
Token | It |
Token ID | 632 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
ilda | +0.017 |
nie | +0.017 |
organ | +0.017 |
Em | +0.017 |
any | +0.017 |
Neg logit contributions | |
aw | -0.012 |
course | -0.012 |
crow | -0.009 |
Run | -0.009 |
Too | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
aw | +0.022 |
course | +0.021 |
crow | +0.018 |
Run | +0.017 |
goose | +0.017 |
Neg logit contributions | |
ilda | -0.020 |
organ | -0.020 |
nie | -0.020 |
Em | -0.020 |
any | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
aw | +0.031 |
course | +0.030 |
crow | +0.025 |
Run | +0.024 |
goose | +0.023 |
Neg logit contributions | |
ilda | -0.038 |
organ | -0.037 |
nie | -0.037 |
Em | -0.037 |
any | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | -5.48e-03 |
Pos logit contributions | |
aw | +0.067 |
course | +0.065 |
Run | +0.061 |
Too | +0.059 |
crow | +0.057 |
Neg logit contributions | |
any | -0.062 |
nie | -0.061 |
ilda | -0.061 |
Jackie | -0.057 |
ingu | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
Jackie | +0.000 |
ilda | +0.000 |
Em | +0.000 |
nie | +0.000 |
any | +0.000 |
Neg logit contributions | |
aw | -0.000 |
course | -0.000 |
crow | -0.000 |
Run | -0.000 |
Too | -0.000 |
Token | all |
Token ID | 477 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
ilda | +0.006 |
Jackie | +0.006 |
nie | +0.006 |
organ | +0.006 |
any | +0.006 |
Neg logit contributions | |
aw | -0.005 |
course | -0.005 |
crow | -0.004 |
Run | -0.004 |
Too | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
nie | +0.147 |
ilda | +0.146 |
any | +0.145 |
Jackie | +0.143 |
Em | +0.143 |
Neg logit contributions | |
aw | -0.123 |
course | -0.116 |
Run | -0.096 |
crow | -0.094 |
Too | -0.093 |
Token | other |
Token ID | 584 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
organ | +0.001 |
ilda | +0.001 |
Em | +0.000 |
any | +0.000 |
nie | +0.000 |
Neg logit contributions | |
aw | -0.000 |
course | -0.000 |
crow | -0.000 |
goose | -0.000 |
Run | -0.000 |
Token | av |
Token ID | 1196 |
Feature activation | -9.28e+00 |
Pos logit contributions | |
aw | +0.074 |
course | +0.072 |
crow | +0.060 |
Run | +0.058 |
goose | +0.056 |
Neg logit contributions | |
ilda | -0.072 |
organ | -0.072 |
nie | -0.071 |
Em | -0.070 |
any | -0.070 |
Token | oc |
Token ID | 420 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
ilda | +0.435 |
organ | +0.435 |
nie | +0.430 |
Em | +0.425 |
any | +0.424 |
Neg logit contributions | |
aw | -0.333 |
course | -0.321 |
crow | -0.259 |
Run | -0.250 |
goose | -0.239 |
Token | ados |
Token ID | 22484 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
aw | +0.020 |
course | +0.020 |
Run | +0.018 |
crow | +0.017 |
fountain | +0.017 |
Neg logit contributions | |
ilda | -0.012 |
ingu | -0.011 |
organ | -0.011 |
nie | -0.011 |
any | -0.011 |
Token | were |
Token ID | 547 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
ilda | +0.152 |
organ | +0.148 |
any | +0.148 |
nie | +0.147 |
Em | +0.147 |
Neg logit contributions | |
aw | -0.142 |
course | -0.134 |
crow | -0.115 |
Run | -0.113 |
Too | -0.112 |
Token | very |
Token ID | 845 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
aw | +0.019 |
course | +0.019 |
crow | +0.016 |
Run | +0.015 |
Too | +0.015 |
Neg logit contributions | |
ilda | -0.018 |
organ | -0.018 |
nie | -0.018 |
Em | -0.018 |
any | -0.018 |
Token | happy |
Token ID | 3772 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
ilda | +0.072 |
organ | +0.071 |
nie | +0.070 |
Em | +0.069 |
any | +0.069 |
Neg logit contributions | |
aw | -0.097 |
course | -0.094 |
crow | -0.080 |
Run | -0.078 |
goose | -0.075 |
Token | still |
Token ID | 991 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
aw | +0.060 |
course | +0.056 |
crow | +0.044 |
Run | +0.043 |
Too | +0.042 |
Neg logit contributions | |
ilda | -0.077 |
Jackie | -0.077 |
nie | -0.075 |
Em | -0.075 |
organ | -0.074 |
Token | couldn |
Token ID | 3521 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
aw | +0.017 |
course | +0.017 |
crow | +0.014 |
Run | +0.013 |
goose | +0.013 |
Neg logit contributions | |
ilda | -0.018 |
organ | -0.017 |
nie | -0.017 |
Em | -0.017 |
any | -0.017 |
Token | 't |
Token ID | 470 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
ilda | +0.115 |
organ | +0.112 |
Em | +0.110 |
Jackie | +0.109 |
any | +0.108 |
Neg logit contributions | |
aw | -0.136 |
course | -0.126 |
crow | -0.106 |
goose | -0.103 |
Run | -0.103 |
Token | find |
Token ID | 1064 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
aw | +0.011 |
course | +0.010 |
crow | +0.009 |
Run | +0.008 |
Too | +0.008 |
Neg logit contributions | |
ilda | -0.007 |
organ | -0.007 |
nie | -0.007 |
Em | -0.007 |
any | -0.007 |
Token | any |
Token ID | 597 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
ilda | +0.067 |
nie | +0.066 |
Jackie | +0.066 |
organ | +0.064 |
cere | +0.064 |
Neg logit contributions | |
aw | -0.069 |
course | -0.064 |
Run | -0.057 |
Too | -0.056 |
crow | -0.054 |
Token | av |
Token ID | 1196 |
Feature activation | -9.26e+00 |
Pos logit contributions | |
aw | +0.030 |
course | +0.029 |
Too | +0.024 |
crow | +0.024 |
Run | +0.024 |
Neg logit contributions | |
nie | -0.033 |
cere | -0.032 |
organ | -0.032 |
ilda | -0.032 |
Jackie | -0.032 |
Token | oc |
Token ID | 420 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
ilda | +0.481 |
Em | +0.472 |
any | +0.468 |
organ | +0.467 |
Jackie | +0.466 |
Neg logit contributions | |
aw | -0.311 |
course | -0.298 |
crow | -0.221 |
Run | -0.200 |
goose | -0.198 |
Token | ados |
Token ID | 22484 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
aw | +0.028 |
course | +0.028 |
crow | +0.023 |
Run | +0.022 |
goose | +0.022 |
Neg logit contributions | |
ilda | -0.021 |
organ | -0.021 |
nie | -0.020 |
Em | -0.020 |
any | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
ilda | +0.154 |
organ | +0.153 |
nie | +0.150 |
Em | +0.149 |
any | +0.149 |
Neg logit contributions | |
aw | -0.140 |
course | -0.135 |
crow | -0.111 |
Run | -0.107 |
Too | -0.103 |
Token | Finally |
Token ID | 9461 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
ilda | +0.013 |
organ | +0.013 |
nie | +0.013 |
Em | +0.013 |
any | +0.013 |
Neg logit contributions | |
aw | -0.012 |
course | -0.012 |
crow | -0.010 |
Run | -0.010 |
goose | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
aw | +0.052 |
course | +0.041 |
ican | +0.040 |
goose | +0.039 |
Run | +0.039 |
Neg logit contributions | |
Jackie | -0.053 |
ilda | -0.048 |
Grac | -0.047 |
Em | -0.046 |
daddy | -0.045 |
Token | very |
Token ID | 845 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
aw | +0.008 |
course | +0.008 |
crow | +0.007 |
Run | +0.006 |
Too | +0.006 |
Neg logit contributions | |
nie | -0.007 |
organ | -0.007 |
ilda | -0.007 |
any | -0.007 |
Em | -0.006 |
Token | excited |
Token ID | 6568 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
nie | +0.080 |
organ | +0.079 |
ilda | +0.078 |
Jackie | +0.077 |
Em | +0.077 |
Neg logit contributions | |
aw | -0.108 |
course | -0.108 |
crow | -0.089 |
Run | -0.086 |
Too | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ilda | +0.030 |
nie | +0.029 |
Jackie | +0.029 |
any | +0.028 |
Em | +0.028 |
Neg logit contributions | |
aw | -0.033 |
course | -0.032 |
crow | -0.028 |
Run | -0.028 |
Too | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
organ | +0.062 |
nie | +0.060 |
ilda | +0.059 |
aghetti | +0.058 |
ingu | +0.058 |
Neg logit contributions | |
aw | -0.034 |
course | -0.034 |
crow | -0.026 |
Run | -0.023 |
Too | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
organ | +0.063 |
cere | +0.062 |
nie | +0.062 |
ingu | +0.061 |
any | +0.061 |
Neg logit contributions | |
aw | -0.044 |
course | -0.043 |
crow | -0.033 |
Run | -0.031 |
Too | -0.030 |
Token | Em |
Token ID | 10161 |
Feature activation | -9.23e+00 |
Pos logit contributions | |
ilda | +0.056 |
organ | +0.055 |
ingu | +0.055 |
any | +0.054 |
nie | +0.053 |
Neg logit contributions | |
aw | -0.050 |
course | -0.048 |
Run | -0.038 |
crow | -0.038 |
Too | -0.038 |
Token | ma |
Token ID | 2611 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
organ | +0.398 |
ingu | +0.392 |
emo | +0.384 |
iddles | +0.378 |
to | +0.377 |
Neg logit contributions | |
course | -0.383 |
aw | -0.350 |
Run | -0.262 |
crow | -0.261 |
Too | -0.259 |
Token | walked |
Token ID | 6807 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
organ | +0.056 |
ilda | +0.056 |
Em | +0.054 |
nie | +0.054 |
ingu | +0.054 |
Neg logit contributions | |
aw | -0.061 |
course | -0.059 |
crow | -0.049 |
Run | -0.047 |
goose | -0.046 |
Token | around |
Token ID | 1088 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
ilda | +0.024 |
nie | +0.023 |
any | +0.023 |
organ | +0.023 |
Jackie | +0.023 |
Neg logit contributions | |
aw | -0.041 |
course | -0.041 |
Too | -0.034 |
Run | -0.034 |
crow | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
ilda | +0.080 |
organ | +0.079 |
Em | +0.079 |
Jackie | +0.079 |
nie | +0.078 |
Neg logit contributions | |
aw | -0.073 |
course | -0.067 |
crow | -0.056 |
Run | -0.054 |
Too | -0.053 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
organ | +0.039 |
ilda | +0.038 |
ingu | +0.038 |
nie | +0.038 |
cere | +0.038 |
Neg logit contributions | |
aw | -0.035 |
course | -0.034 |
crow | -0.027 |
Run | -0.026 |
goose | -0.026 |
Token | there |
Token ID | 612 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
aw | +0.014 |
course | +0.013 |
Run | +0.011 |
crow | +0.011 |
no | +0.011 |
Neg logit contributions | |
ilda | -0.018 |
any | -0.017 |
organ | -0.017 |
ingu | -0.017 |
cere | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
organ | +0.023 |
ilda | +0.022 |
nie | +0.022 |
Em | +0.022 |
any | +0.022 |
Neg logit contributions | |
aw | -0.029 |
course | -0.027 |
crow | -0.023 |
Run | -0.023 |
Too | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
aw | +0.030 |
course | +0.029 |
crow | +0.022 |
Run | +0.022 |
goose | +0.021 |
Neg logit contributions | |
ilda | -0.043 |
organ | -0.043 |
nie | -0.042 |
any | -0.042 |
Em | -0.042 |
Token | charming |
Token ID | 23332 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
ilda | +0.021 |
organ | +0.021 |
any | +0.021 |
nie | +0.020 |
to | +0.020 |
Neg logit contributions | |
aw | -0.023 |
course | -0.022 |
goose | -0.019 |
crow | -0.018 |
fountain | -0.018 |
Token | little |
Token ID | 1310 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
aw | +0.021 |
course | +0.020 |
crow | +0.016 |
Run | +0.016 |
goose | +0.015 |
Neg logit contributions | |
ilda | -0.021 |
organ | -0.021 |
nie | -0.021 |
Em | -0.021 |
any | -0.021 |
Token | dog |
Token ID | 3290 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
nie | +0.056 |
Jackie | +0.054 |
isha | +0.054 |
Em | +0.053 |
any | +0.052 |
Neg logit contributions | |
aw | -0.059 |
course | -0.056 |
Too | -0.047 |
crow | -0.046 |
Run | -0.046 |
Token | named |
Token ID | 3706 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
aw | +0.143 |
course | +0.137 |
Run | +0.110 |
crow | +0.109 |
Too | +0.107 |
Neg logit contributions | |
ilda | -0.220 |
Em | -0.219 |
nie | -0.217 |
organ | -0.216 |
any | -0.216 |
Token | Spot |
Token ID | 15899 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
aw | +0.103 |
course | +0.099 |
crow | +0.077 |
Run | +0.074 |
goose | +0.073 |
Neg logit contributions | |
organ | -0.146 |
ilda | -0.144 |
any | -0.142 |
nie | -0.142 |
Em | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
aw | +0.041 |
course | +0.038 |
crow | +0.028 |
no | +0.026 |
goose | +0.026 |
Neg logit contributions | |
ilda | -0.073 |
organ | -0.072 |
Em | -0.071 |
nie | -0.070 |
Jackie | -0.070 |
Token | Spot |
Token ID | 15899 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
organ | +0.013 |
Em | +0.013 |
nie | +0.013 |
ingu | +0.013 |
die | +0.013 |
Neg logit contributions | |
aw | -0.008 |
course | -0.008 |
crow | -0.006 |
Too | -0.005 |
Run | -0.005 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
aw | +0.052 |
course | +0.050 |
crow | +0.039 |
no | +0.039 |
goose | +0.039 |
Neg logit contributions | |
ilda | -0.055 |
Em | -0.051 |
organ | -0.051 |
Jackie | -0.051 |
ingu | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
course | +0.048 |
aw | +0.047 |
fountain | +0.041 |
Too | +0.041 |
goose | +0.040 |
Neg logit contributions | |
Jackie | -0.034 |
Em | -0.034 |
nie | -0.033 |
ilda | -0.033 |
any | -0.032 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ilda | +0.005 |
nie | +0.005 |
Jackie | +0.005 |
organ | +0.005 |
any | +0.005 |
Neg logit contributions | |
aw | -0.007 |
course | -0.007 |
crow | -0.006 |
Too | -0.005 |
fountain | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
aw | +0.077 |
course | +0.074 |
Too | +0.060 |
crow | +0.059 |
Run | +0.059 |
Neg logit contributions | |
organ | -0.064 |
ilda | -0.061 |
any | -0.060 |
nie | -0.060 |
Em | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Jackie | +0.021 |
ilda | +0.021 |
organ | +0.020 |
to | +0.020 |
any | +0.020 |
Neg logit contributions | |
aw | -0.023 |
course | -0.020 |
crow | -0.017 |
Too | -0.017 |
goose | -0.016 |
Token | other |
Token ID | 584 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
aw | +0.004 |
course | +0.004 |
crow | +0.003 |
Run | +0.003 |
ar | +0.003 |
Neg logit contributions | |
Em | -0.004 |
ilda | -0.004 |
any | -0.004 |
nie | -0.004 |
organ | -0.004 |
Token | side |
Token ID | 1735 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
aw | +0.087 |
course | +0.078 |
Too | +0.065 |
ar | +0.061 |
Run | +0.061 |
Neg logit contributions | |
any | -0.103 |
nie | -0.103 |
organ | -0.100 |
Em | -0.098 |
cere | -0.098 |
Token | of |
Token ID | 286 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
aw | +0.279 |
Too | +0.248 |
course | +0.246 |
Run | +0.241 |
hawk | +0.233 |
Neg logit contributions | |
any | -0.206 |
Em | -0.202 |
ilda | -0.201 |
nie | -0.200 |
Jackie | -0.200 |
Token | the |
Token ID | 262 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Em | +0.057 |
Jackie | +0.057 |
ilda | +0.056 |
organ | +0.056 |
nie | +0.055 |
Neg logit contributions | |
aw | -0.056 |
course | -0.048 |
crow | -0.042 |
Too | -0.040 |
Run | -0.039 |
Token | yard |
Token ID | 12699 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
aw | +0.004 |
course | +0.004 |
crow | +0.003 |
Run | +0.003 |
goose | +0.003 |
Neg logit contributions | |
ilda | -0.005 |
organ | -0.005 |
nie | -0.005 |
ingu | -0.005 |
Em | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
aw | +0.027 |
course | +0.026 |
Too | +0.024 |
Run | +0.023 |
hawk | +0.022 |
Neg logit contributions | |
any | -0.017 |
ilda | -0.017 |
Jackie | -0.016 |
Em | -0.015 |
to | -0.015 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
ilda | +0.016 |
organ | +0.016 |
Em | +0.015 |
nie | +0.015 |
any | +0.015 |
Neg logit contributions | |
aw | -0.013 |
course | -0.013 |
crow | -0.010 |
Run | -0.010 |
goose | -0.009 |
Token | praise |
Token ID | 13463 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
aw | +0.093 |
course | +0.086 |
crow | +0.078 |
Too | +0.076 |
Run | +0.076 |
Neg logit contributions | |
Jackie | -0.080 |
nie | -0.076 |
ilda | -0.076 |
organ | -0.075 |
cere | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ilda | +0.064 |
nie | +0.063 |
organ | +0.062 |
Em | +0.062 |
any | +0.062 |
Neg logit contributions | |
aw | -0.059 |
course | -0.056 |
crow | -0.047 |
Run | -0.047 |
Too | -0.045 |
Token | Soon |
Token ID | 15894 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
organ | +0.054 |
ilda | +0.052 |
nie | +0.052 |
any | +0.050 |
ingu | +0.050 |
Neg logit contributions | |
aw | -0.044 |
course | -0.043 |
crow | -0.035 |
Run | -0.033 |
Too | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
aw | +0.024 |
course | +0.022 |
Run | +0.018 |
crow | +0.018 |
Too | +0.018 |
Neg logit contributions | |
ilda | -0.038 |
Jackie | -0.037 |
ingu | -0.037 |
organ | -0.037 |
Em | -0.037 |
Token | he |
Token ID | 339 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
ilda | +0.023 |
organ | +0.023 |
nie | +0.023 |
Em | +0.023 |
Jackie | +0.023 |
Neg logit contributions | |
aw | -0.020 |
course | -0.019 |
crow | -0.015 |
Run | -0.015 |
Too | -0.015 |
Token | no |
Token ID | 645 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
organ | +0.018 |
ilda | +0.018 |
nie | +0.018 |
Em | +0.017 |
any | +0.017 |
Neg logit contributions | |
aw | -0.019 |
course | -0.018 |
crow | -0.015 |
Run | -0.014 |
goose | -0.014 |
Token | longer |
Token ID | 2392 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
aw | +0.236 |
course | +0.216 |
crow | +0.198 |
Run | +0.196 |
goose | +0.186 |
Neg logit contributions | |
nie | -0.249 |
ilda | -0.234 |
Em | -0.231 |
any | -0.230 |
Jackie | -0.230 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
aw | +0.149 |
course | +0.145 |
crow | +0.122 |
Run | +0.119 |
goose | +0.116 |
Neg logit contributions | |
ilda | -0.123 |
organ | -0.122 |
nie | -0.120 |
Em | -0.119 |
any | -0.119 |
Token | pain |
Token ID | 2356 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
organ | +0.087 |
ilda | +0.087 |
nie | +0.086 |
Em | +0.085 |
Jackie | +0.085 |
Neg logit contributions | |
aw | -0.077 |
course | -0.074 |
crow | -0.060 |
Run | -0.059 |
goose | -0.056 |
Token | because |
Token ID | 780 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
aw | +0.096 |
course | +0.093 |
crow | +0.077 |
Run | +0.074 |
goose | +0.072 |
Neg logit contributions | |
ilda | -0.097 |
organ | -0.097 |
nie | -0.096 |
Em | -0.095 |
any | -0.094 |
Token | he |
Token ID | 339 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
ilda | +0.080 |
organ | +0.079 |
nie | +0.079 |
Em | +0.078 |
Jackie | +0.077 |
Neg logit contributions | |
aw | -0.061 |
course | -0.058 |
crow | -0.047 |
Run | -0.046 |
goose | -0.044 |
Token | being |
Token ID | 852 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
aw | +0.003 |
course | +0.003 |
crow | +0.002 |
Run | +0.002 |
fountain | +0.002 |
Neg logit contributions | |
ilda | -0.003 |
organ | -0.003 |
nie | -0.003 |
any | -0.003 |
ingu | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
nie | +0.117 |
organ | +0.116 |
ilda | +0.116 |
Em | +0.114 |
any | +0.114 |
Neg logit contributions | |
aw | -0.120 |
course | -0.116 |
crow | -0.097 |
Run | -0.095 |
goose | -0.091 |
Token | big |
Token ID | 1263 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
aw | +0.008 |
course | +0.007 |
crow | +0.006 |
Run | +0.006 |
Too | +0.006 |
Neg logit contributions | |
ilda | -0.007 |
nie | -0.007 |
organ | -0.007 |
Em | -0.007 |
any | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
aw | +0.039 |
course | +0.034 |
Run | +0.030 |
crow | +0.030 |
Too | +0.029 |
Neg logit contributions | |
nie | -0.039 |
Jackie | -0.039 |
ilda | -0.038 |
any | -0.038 |
Em | -0.038 |
Token | fast |
Token ID | 3049 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
aw | +0.009 |
course | +0.008 |
crow | +0.007 |
Run | +0.007 |
goose | +0.007 |
Neg logit contributions | |
ilda | -0.007 |
organ | -0.007 |
nie | -0.007 |
Em | -0.007 |
any | -0.007 |
Token | dog |
Token ID | 3290 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
aw | +0.131 |
course | +0.125 |
Run | +0.104 |
Too | +0.102 |
crow | +0.100 |
Neg logit contributions | |
nie | -0.144 |
any | -0.140 |
ilda | -0.138 |
Jackie | -0.137 |
Em | -0.137 |
Token | who |
Token ID | 508 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
aw | +0.194 |
course | +0.191 |
Run | +0.165 |
Too | +0.161 |
crow | +0.159 |
Neg logit contributions | |
nie | -0.178 |
ilda | -0.177 |
any | -0.177 |
Em | -0.172 |
organ | -0.169 |
Token | could |
Token ID | 714 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
ilda | +0.087 |
nie | +0.087 |
organ | +0.086 |
any | +0.086 |
Em | +0.084 |
Neg logit contributions | |
aw | -0.106 |
course | -0.103 |
crow | -0.087 |
Run | -0.086 |
Too | -0.083 |
Token | win |
Token ID | 1592 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
organ | +0.090 |
nie | +0.089 |
ilda | +0.089 |
any | +0.087 |
Jackie | +0.085 |
Neg logit contributions | |
aw | -0.110 |
course | -0.098 |
crow | -0.085 |
Run | -0.081 |
Too | -0.079 |
Token | prizes |
Token ID | 21740 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
aw | +0.058 |
course | +0.056 |
crow | +0.045 |
Run | +0.044 |
goose | +0.042 |
Neg logit contributions | |
ilda | -0.072 |
organ | -0.071 |
nie | -0.071 |
Em | -0.070 |
any | -0.070 |
Token | in |
Token ID | 287 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ilda | +0.028 |
nie | +0.028 |
organ | +0.028 |
Em | +0.027 |
any | +0.027 |
Neg logit contributions | |
aw | -0.029 |
course | -0.028 |
Run | -0.024 |
crow | -0.024 |
Too | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
cere | +0.019 |
organ | +0.019 |
nie | +0.019 |
ingu | +0.018 |
designs | +0.018 |
Neg logit contributions | |
aw | -0.024 |
course | -0.024 |
Run | -0.022 |
crow | -0.021 |
Too | -0.021 |
Token | smooth |
Token ID | 7209 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
aw | +0.026 |
course | +0.024 |
crow | +0.022 |
Run | +0.020 |
goose | +0.020 |
Neg logit contributions | |
organ | -0.019 |
nie | -0.019 |
ilda | -0.019 |
Em | -0.018 |
Jackie | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
nie | +0.030 |
organ | +0.030 |
cere | +0.030 |
any | +0.030 |
ilda | +0.029 |
Neg logit contributions | |
aw | -0.035 |
course | -0.035 |
Run | -0.030 |
crow | -0.029 |
Too | -0.029 |
Token | He |
Token ID | 679 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
aw | +0.016 |
course | +0.015 |
crow | +0.013 |
Run | +0.012 |
goose | +0.012 |
Neg logit contributions | |
organ | -0.016 |
ilda | -0.016 |
nie | -0.016 |
Em | -0.016 |
any | -0.016 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
aw | +0.042 |
course | +0.041 |
crow | +0.034 |
Run | +0.033 |
goose | +0.032 |
Neg logit contributions | |
organ | -0.036 |
ilda | -0.036 |
nie | -0.035 |
Em | -0.035 |
ingu | -0.035 |
Token | after |
Token ID | 706 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
aw | +0.098 |
course | +0.097 |
crow | +0.081 |
Run | +0.081 |
Too | +0.080 |
Neg logit contributions | |
organ | -0.053 |
to | -0.051 |
Jackie | -0.048 |
ilda | -0.048 |
nie | -0.047 |
Token | Mia |
Token ID | 32189 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
aw | +0.187 |
course | +0.169 |
crow | +0.145 |
Too | +0.139 |
Run | +0.139 |
Neg logit contributions | |
Jackie | -0.173 |
ilda | -0.166 |
organ | -0.164 |
to | -0.161 |
cere | -0.161 |
Token | and |
Token ID | 290 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
aw | +0.054 |
course | +0.052 |
crow | +0.043 |
Run | +0.043 |
Too | +0.042 |
Neg logit contributions | |
ilda | -0.057 |
organ | -0.057 |
nie | -0.056 |
any | -0.056 |
Em | -0.055 |
Token | gave |
Token ID | 2921 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
aw | +0.026 |
course | +0.024 |
crow | +0.021 |
Too | +0.021 |
Run | +0.020 |
Neg logit contributions | |
ilda | -0.018 |
organ | -0.018 |
Em | -0.018 |
any | -0.017 |
Jackie | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
Jackie | +0.021 |
nie | +0.021 |
to | +0.020 |
ilda | +0.020 |
die | +0.020 |
Neg logit contributions | |
aw | -0.026 |
course | -0.025 |
Run | -0.023 |
Too | -0.022 |
crow | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
cere | +0.018 |
ingu | +0.018 |
organ | +0.018 |
nie | +0.018 |
ilda | +0.017 |
Neg logit contributions | |
aw | -0.017 |
course | -0.017 |
Run | -0.015 |
Too | -0.014 |
crow | -0.014 |
Token | ch |
Token ID | 442 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
course | +0.197 |
aw | +0.193 |
crow | +0.174 |
bye | +0.167 |
hy | +0.164 |
Neg logit contributions | |
cere | -0.156 |
organ | -0.153 |
die | -0.151 |
to | -0.146 |
nie | -0.145 |
Token | ases |
Token ID | 1386 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
ingu | +0.032 |
emo | +0.031 |
iddles | +0.031 |
ascal | +0.030 |
to | +0.030 |
Neg logit contributions | |
course | -0.030 |
aw | -0.026 |
Too | -0.023 |
fountain | -0.023 |
Run | -0.022 |
Token | them |
Token ID | 606 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
course | +0.200 |
aw | +0.197 |
Too | +0.180 |
hawk | +0.173 |
goose | +0.171 |
Neg logit contributions | |
Jackie | -0.127 |
to | -0.122 |
organ | -0.120 |
ilda | -0.118 |
Em | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
aw | +0.014 |
course | +0.014 |
Too | +0.012 |
crow | +0.012 |
Run | +0.012 |
Neg logit contributions | |
organ | -0.010 |
nie | -0.009 |
to | -0.009 |
any | -0.009 |
ilda | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
organ | +0.001 |
Jackie | +0.001 |
Em | +0.001 |
ingu | +0.001 |
to | +0.001 |
Neg logit contributions | |
aw | -0.001 |
course | -0.001 |
crow | -0.001 |
goose | -0.001 |
Run | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
ilda | +0.018 |
nie | +0.018 |
any | +0.017 |
organ | +0.017 |
cere | +0.017 |
Neg logit contributions | |
aw | -0.014 |
course | -0.013 |
crow | -0.011 |
Run | -0.010 |
fountain | -0.010 |
Token | Tim |
Token ID | 14967 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
Em | +0.016 |
organ | +0.016 |
nie | +0.015 |
Jackie | +0.015 |
any | +0.015 |
Neg logit contributions | |
aw | -0.017 |
course | -0.016 |
crow | -0.014 |
hy | -0.013 |
goose | -0.013 |
Token | drops |
Token ID | 10532 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ilda | +0.001 |
nie | +0.001 |
organ | +0.001 |
die | +0.001 |
ingu | +0.001 |
Neg logit contributions | |
course | -0.001 |
aw | -0.001 |
crow | -0.001 |
Too | -0.001 |
Run | -0.001 |
Token | his |
Token ID | 465 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
aw | +0.063 |
course | +0.061 |
Too | +0.055 |
ar | +0.054 |
ishly | +0.053 |
Neg logit contributions | |
Jackie | -0.033 |
to | -0.033 |
organ | -0.033 |
magnets | -0.031 |
cere | -0.030 |
Token | large |
Token ID | 1588 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
aw | +0.029 |
course | +0.028 |
crow | +0.024 |
Run | +0.023 |
Too | +0.022 |
Neg logit contributions | |
ilda | -0.026 |
organ | -0.026 |
nie | -0.026 |
ingu | -0.026 |
Em | -0.025 |
Token | baseball |
Token ID | 9283 |
Feature activation | +5.63e-04 |
Pos logit contributions | |
aw | +0.053 |
course | +0.049 |
crow | +0.044 |
Run | +0.040 |
roads | +0.040 |
Neg logit contributions | |
Jackie | -0.036 |
ingu | -0.036 |
nie | -0.035 |
magnets | -0.035 |
designs | -0.035 |
Token | The |
Token ID | 464 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ilda | +0.028 |
organ | +0.027 |
nie | +0.027 |
any | +0.027 |
ingu | +0.027 |
Neg logit contributions | |
aw | -0.018 |
course | -0.017 |
crow | -0.013 |
Run | -0.013 |
Too | -0.012 |
Token | bee |
Token ID | 20697 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
aw | +0.053 |
course | +0.050 |
crow | +0.039 |
Run | +0.037 |
Too | +0.035 |
Neg logit contributions | |
nie | -0.076 |
organ | -0.076 |
ilda | -0.076 |
Em | -0.074 |
isha | -0.074 |
Token | was |
Token ID | 373 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
aw | +0.064 |
course | +0.062 |
crow | +0.053 |
Too | +0.051 |
Run | +0.050 |
Neg logit contributions | |
nie | -0.062 |
organ | -0.061 |
any | -0.061 |
Em | -0.061 |
ilda | -0.061 |
Token | so |
Token ID | 523 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
aw | +0.031 |
course | +0.031 |
crow | +0.025 |
Run | +0.024 |
Too | +0.024 |
Neg logit contributions | |
ilda | -0.032 |
organ | -0.032 |
nie | -0.032 |
Em | -0.031 |
any | -0.031 |
Token | excited |
Token ID | 6568 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
ilda | +0.077 |
any | +0.073 |
organ | +0.073 |
Em | +0.073 |
nie | +0.073 |
Neg logit contributions | |
aw | -0.067 |
course | -0.063 |
crow | -0.051 |
goose | -0.050 |
Run | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ilda | +0.021 |
Jackie | +0.020 |
nie | +0.020 |
organ | +0.020 |
any | +0.020 |
Neg logit contributions | |
aw | -0.017 |
course | -0.017 |
crow | -0.014 |
Run | -0.014 |
Too | -0.014 |
Token | " |
Token ID | 366 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
aw | +0.005 |
course | +0.005 |
crow | +0.004 |
hy | +0.004 |
Too | +0.004 |
Neg logit contributions | |
Jackie | -0.005 |
ilda | -0.004 |
Em | -0.004 |
nie | -0.004 |
die | -0.004 |
Token | I |
Token ID | 40 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
organ | +0.037 |
ilda | +0.037 |
nie | +0.037 |
Em | +0.037 |
any | +0.036 |
Neg logit contributions | |
aw | -0.032 |
course | -0.031 |
crow | -0.025 |
Run | -0.024 |
goose | -0.023 |
Token | know |
Token ID | 760 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
aw | +0.009 |
course | +0.009 |
crow | +0.008 |
Run | +0.007 |
fountain | +0.007 |
Neg logit contributions | |
ilda | -0.010 |
Em | -0.010 |
ingu | -0.010 |
nie | -0.010 |
organ | -0.010 |
Token | just |
Token ID | 655 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
nie | +0.168 |
ilda | +0.167 |
cere | +0.166 |
Jackie | +0.164 |
isha | +0.161 |
Neg logit contributions | |
aw | -0.134 |
course | -0.131 |
crow | -0.115 |
Too | -0.110 |
Run | -0.108 |
Token | the |
Token ID | 262 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
aw | +0.043 |
course | +0.042 |
crow | +0.035 |
Run | +0.033 |
goose | +0.032 |
Neg logit contributions | |
ilda | -0.042 |
organ | -0.042 |
nie | -0.041 |
Em | -0.041 |
any | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
organ | +0.028 |
ilda | +0.028 |
nie | +0.027 |
Em | +0.027 |
cere | +0.027 |
Neg logit contributions | |
aw | -0.028 |
course | -0.027 |
crow | -0.023 |
Run | -0.023 |
Too | -0.022 |
Token | draw |
Token ID | 3197 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
aw | +0.021 |
course | +0.020 |
crow | +0.017 |
Run | +0.017 |
goose | +0.016 |
Neg logit contributions | |
ilda | -0.017 |
organ | -0.016 |
nie | -0.016 |
Em | -0.016 |
any | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
ilda | +0.125 |
organ | +0.124 |
nie | +0.123 |
Em | +0.121 |
any | +0.121 |
Neg logit contributions | |
aw | -0.107 |
course | -0.103 |
crow | -0.084 |
Run | -0.080 |
goose | -0.077 |
Token | They |
Token ID | 1119 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
aw | +0.011 |
course | +0.010 |
crow | +0.008 |
Run | +0.008 |
goose | +0.008 |
Neg logit contributions | |
ilda | -0.012 |
organ | -0.012 |
nie | -0.012 |
Em | -0.012 |
any | -0.012 |
Token | are |
Token ID | 389 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
aw | +0.068 |
course | +0.068 |
crow | +0.052 |
Run | +0.050 |
fountain | +0.050 |
Neg logit contributions | |
ilda | -0.095 |
nie | -0.092 |
organ | -0.092 |
Em | -0.092 |
any | -0.092 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
aw | +0.097 |
course | +0.088 |
no | +0.079 |
fountain | +0.071 |
goose | +0.069 |
Neg logit contributions | |
ilda | -0.130 |
to | -0.126 |
Em | -0.126 |
any | -0.124 |
organ | -0.124 |
Token | and |
Token ID | 290 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
ilda | +0.005 |
organ | +0.005 |
nie | +0.005 |
Em | +0.005 |
any | +0.005 |
Neg logit contributions | |
aw | -0.004 |
course | -0.003 |
crow | -0.003 |
Run | -0.003 |
goose | -0.002 |
Token | have |
Token ID | 423 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
aw | +0.019 |
course | +0.018 |
crow | +0.015 |
Run | +0.015 |
goose | +0.014 |
Neg logit contributions | |
ilda | -0.015 |
organ | -0.015 |
nie | -0.014 |
Em | -0.014 |
any | -0.014 |
Token | fun |
Token ID | 1257 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
organ | +0.001 |
ilda | +0.001 |
Em | +0.001 |
nie | +0.001 |
ingu | +0.001 |
Neg logit contributions | |
aw | -0.001 |
course | -0.001 |
crow | -0.001 |
Run | -0.001 |
Too | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
ilda | +0.006 |
organ | +0.006 |
nie | +0.006 |
Em | +0.006 |
ingu | +0.006 |
Neg logit contributions | |
aw | -0.005 |
course | -0.004 |
crow | -0.003 |
Run | -0.003 |
fountain | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -9.57e-02 |
Pos logit contributions | |
aw | +0.009 |
course | +0.008 |
crow | +0.007 |
Run | +0.007 |
goose | +0.006 |
Neg logit contributions | |
organ | -0.008 |
ilda | -0.007 |
nie | -0.007 |
Em | -0.007 |
any | -0.007 |
Token | he |
Token ID | 339 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
ilda | +0.053 |
nie | +0.052 |
Jackie | +0.052 |
Em | +0.052 |
organ | +0.051 |
Neg logit contributions | |
aw | -0.045 |
course | -0.042 |
crow | -0.035 |
Run | -0.034 |
Too | -0.032 |
Token | couldn |
Token ID | 3521 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
aw | +0.002 |
course | +0.002 |
no | +0.002 |
Too | +0.002 |
Run | +0.002 |
Neg logit contributions | |
iddles | -0.002 |
ilda | -0.002 |
organ | -0.002 |
aghetti | -0.002 |
cere | -0.002 |
Token | 't |
Token ID | 470 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ilda | +0.130 |
organ | +0.130 |
nie | +0.129 |
Em | +0.127 |
any | +0.127 |
Neg logit contributions | |
aw | -0.107 |
course | -0.104 |
crow | -0.084 |
Run | -0.080 |
goose | -0.077 |
Token | dance |
Token ID | 9280 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
course | +0.006 |
aw | +0.006 |
crow | +0.005 |
no | +0.005 |
fountain | +0.005 |
Neg logit contributions | |
ilda | -0.007 |
isha | -0.007 |
die | -0.007 |
nie | -0.007 |
ingu | -0.007 |
Token | anymore |
Token ID | 7471 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
ilda | +0.005 |
organ | +0.005 |
nie | +0.005 |
Em | +0.005 |
any | +0.005 |
Neg logit contributions | |
aw | -0.003 |
course | -0.003 |
crow | -0.003 |
Run | -0.003 |
goose | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
aw | +0.095 |
course | +0.093 |
crow | +0.069 |
no | +0.065 |
Run | +0.064 |
Neg logit contributions | |
organ | -0.151 |
ilda | -0.150 |
nie | -0.149 |
Em | -0.148 |
ingu | -0.147 |
Token |
|
Token ID | 198 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
ilda | +0.007 |
organ | +0.007 |
nie | +0.007 |
isha | +0.007 |
ingu | +0.007 |
Neg logit contributions | |
aw | -0.005 |
course | -0.005 |
crow | -0.004 |
Run | -0.004 |
Too | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
ilda | +0.002 |
ingu | +0.002 |
cere | +0.002 |
nie | +0.002 |
organ | +0.002 |
Neg logit contributions | |
aw | -0.001 |
course | -0.001 |
crow | -0.001 |
Run | -0.001 |
Zip | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
ilda | +0.007 |
organ | +0.006 |
ingu | +0.006 |
nie | +0.006 |
Jackie | +0.006 |
Neg logit contributions | |
aw | -0.005 |
course | -0.005 |
crow | -0.004 |
Run | -0.004 |
Too | -0.004 |
Token | strong |
Token ID | 1913 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
aw | +0.070 |
course | +0.069 |
crow | +0.058 |
goose | +0.056 |
Run | +0.055 |
Neg logit contributions | |
ilda | -0.079 |
organ | -0.078 |
any | -0.078 |
ingu | -0.076 |
nie | -0.075 |
Token | dancer |
Token ID | 38619 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
aw | +0.021 |
course | +0.021 |
crow | +0.017 |
Run | +0.017 |
Too | +0.016 |
Neg logit contributions | |
nie | -0.016 |
ilda | -0.016 |
organ | -0.015 |
Em | -0.015 |
any | -0.015 |
Token | clothes |
Token ID | 8242 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
aw | +0.023 |
course | +0.022 |
crow | +0.019 |
Run | +0.019 |
Too | +0.018 |
Neg logit contributions | |
ilda | -0.014 |
nie | -0.014 |
any | -0.014 |
organ | -0.014 |
Em | -0.014 |
Token | look |
Token ID | 804 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ilda | +0.082 |
nie | +0.081 |
any | +0.079 |
Jackie | +0.079 |
organ | +0.079 |
Neg logit contributions | |
aw | -0.064 |
course | -0.060 |
crow | -0.051 |
Run | -0.050 |
goose | -0.047 |
Token | incredible |
Token ID | 8082 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ilda | +0.042 |
nie | +0.042 |
organ | +0.042 |
Em | +0.041 |
Jackie | +0.040 |
Neg logit contributions | |
aw | -0.045 |
course | -0.043 |
crow | -0.037 |
Run | -0.036 |
goose | -0.035 |
Token | on |
Token ID | 319 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
organ | +0.012 |
ilda | +0.012 |
nie | +0.012 |
Em | +0.012 |
any | +0.012 |
Neg logit contributions | |
aw | -0.011 |
course | -0.010 |
crow | -0.008 |
Run | -0.008 |
goose | -0.008 |
Token | you |
Token ID | 345 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
ilda | +0.002 |
organ | +0.002 |
nie | +0.002 |
Em | +0.002 |
any | +0.002 |
Neg logit contributions | |
aw | -0.001 |
course | -0.001 |
crow | -0.001 |
Run | -0.001 |
goose | -0.001 |
Token | .' |
Token ID | 2637 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
organ | +0.019 |
ilda | +0.019 |
nie | +0.019 |
Em | +0.019 |
any | +0.019 |
Neg logit contributions | |
aw | -0.019 |
course | -0.018 |
crow | -0.015 |
Run | -0.015 |
goose | -0.014 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
organ | +0.003 |
nie | +0.003 |
ilda | +0.003 |
any | +0.003 |
ingu | +0.003 |
Neg logit contributions | |
aw | -0.003 |
course | -0.003 |
crow | -0.002 |
Run | -0.002 |
Too | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
aw | +0.039 |
course | +0.037 |
crow | +0.028 |
Run | +0.027 |
goose | +0.026 |
Neg logit contributions | |
ilda | -0.069 |
Jackie | -0.068 |
Em | -0.068 |
organ | -0.066 |
nie | -0.066 |
Token | it |
Token ID | 340 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
ilda | +0.008 |
organ | +0.008 |
Em | +0.008 |
nie | +0.008 |
any | +0.008 |
Neg logit contributions | |
aw | -0.009 |
course | -0.009 |
crow | -0.007 |
Run | -0.007 |
goose | -0.007 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ilda | +0.018 |
organ | +0.017 |
nie | +0.017 |
Em | +0.017 |
any | +0.017 |
Neg logit contributions | |
aw | -0.020 |
course | -0.020 |
crow | -0.017 |
Run | -0.016 |
goose | -0.016 |
Token | like |
Token ID | 588 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
organ | +0.077 |
Jackie | +0.077 |
Em | +0.075 |
ilda | +0.075 |
nie | +0.074 |
Neg logit contributions | |
aw | -0.083 |
course | -0.081 |
crow | -0.069 |
Run | -0.067 |
goose | -0.066 |
Token | 't |
Token ID | 470 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
ilda | +0.061 |
organ | +0.061 |
nie | +0.059 |
any | +0.058 |
Em | +0.058 |
Neg logit contributions | |
aw | -0.069 |
course | -0.063 |
crow | -0.053 |
Run | -0.052 |
Too | -0.050 |
Token | fly |
Token ID | 6129 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
aw | +0.007 |
course | +0.007 |
crow | +0.005 |
Run | +0.005 |
goose | +0.005 |
Neg logit contributions | |
ilda | -0.009 |
organ | -0.009 |
nie | -0.009 |
Em | -0.009 |
any | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
aw | +0.056 |
course | +0.055 |
crow | +0.044 |
Run | +0.043 |
goose | +0.042 |
Neg logit contributions | |
organ | -0.066 |
ilda | -0.065 |
nie | -0.065 |
Em | -0.064 |
any | -0.063 |
Token | Can |
Token ID | 1680 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
nie | +0.020 |
ilda | +0.020 |
organ | +0.020 |
Em | +0.020 |
any | +0.020 |
Neg logit contributions | |
aw | -0.018 |
course | -0.017 |
crow | -0.014 |
Run | -0.013 |
goose | -0.013 |
Token | we |
Token ID | 356 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
aw | +0.051 |
course | +0.043 |
crow | +0.037 |
Run | +0.034 |
fountain | +0.034 |
Neg logit contributions | |
ilda | -0.059 |
Em | -0.057 |
Jackie | -0.057 |
nie | -0.057 |
organ | -0.056 |
Token | help |
Token ID | 1037 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
aw | +0.055 |
course | +0.052 |
crow | +0.043 |
Run | +0.042 |
Too | +0.040 |
Neg logit contributions | |
ilda | -0.057 |
organ | -0.057 |
nie | -0.055 |
Em | -0.055 |
ingu | -0.054 |
Token | it |
Token ID | 340 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
organ | +0.062 |
any | +0.061 |
ilda | +0.061 |
Em | +0.060 |
nie | +0.060 |
Neg logit contributions | |
course | -0.031 |
aw | -0.031 |
crow | -0.022 |
goose | -0.021 |
no | -0.021 |
Token | ?" |
Token ID | 1701 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
course | +0.002 |
aw | +0.002 |
crow | +0.001 |
fountain | +0.001 |
no | +0.001 |
Neg logit contributions | |
nie | -0.002 |
ilda | -0.002 |
Em | -0.002 |
any | -0.002 |
isha | -0.002 |
Token | |
Token ID | 220 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
aw | +0.016 |
course | +0.015 |
crow | +0.013 |
Run | +0.013 |
Too | +0.013 |
Neg logit contributions | |
ilda | -0.013 |
Em | -0.013 |
any | -0.013 |
Jackie | -0.013 |
organ | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
nie | +0.063 |
organ | +0.062 |
any | +0.062 |
ilda | +0.061 |
isha | +0.060 |
Neg logit contributions | |
aw | -0.045 |
course | -0.041 |
crow | -0.033 |
no | -0.031 |
Run | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
ilda | +0.026 |
organ | +0.026 |
nie | +0.026 |
any | +0.026 |
isha | +0.025 |
Neg logit contributions | |
aw | -0.022 |
course | -0.022 |
crow | -0.017 |
Run | -0.017 |
goose | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
nie | +0.002 |
any | +0.002 |
ilda | +0.002 |
organ | +0.002 |
Em | +0.002 |
Neg logit contributions | |
aw | -0.002 |
course | -0.002 |
crow | -0.001 |
Too | -0.001 |
Run | -0.001 |
Token | slide |
Token ID | 10649 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
aw | +0.001 |
course | +0.001 |
crow | +0.001 |
ar | +0.000 |
Run | +0.000 |
Neg logit contributions | |
nie | -0.001 |
Em | -0.001 |
any | -0.001 |
ilda | -0.001 |
cere | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
course | +0.131 |
Run | +0.126 |
hawk | +0.123 |
aw | +0.122 |
crow | +0.119 |
Neg logit contributions | |
nie | -0.086 |
organ | -0.084 |
any | -0.083 |
ilda | -0.082 |
to | -0.079 |
Token | but |
Token ID | 475 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
aw | +0.015 |
course | +0.013 |
crow | +0.012 |
Run | +0.011 |
Too | +0.011 |
Neg logit contributions | |
nie | -0.015 |
ilda | -0.015 |
any | -0.015 |
Jackie | -0.015 |
organ | -0.015 |
Token | he |
Token ID | 339 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
aw | +0.055 |
course | +0.051 |
crow | +0.042 |
Run | +0.040 |
goose | +0.039 |
Neg logit contributions | |
ilda | -0.065 |
nie | -0.065 |
organ | -0.065 |
Jackie | -0.064 |
Em | -0.064 |
Token | couldn |
Token ID | 3521 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
aw | +0.010 |
course | +0.010 |
crow | +0.008 |
Run | +0.008 |
goose | +0.008 |
Neg logit contributions | |
ilda | -0.007 |
organ | -0.007 |
nie | -0.006 |
Em | -0.006 |
any | -0.006 |
Token | 't |
Token ID | 470 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
ilda | +0.123 |
organ | +0.123 |
Em | +0.119 |
nie | +0.118 |
any | +0.118 |
Neg logit contributions | |
aw | -0.126 |
course | -0.119 |
crow | -0.099 |
Run | -0.095 |
goose | -0.094 |
Token | see |
Token ID | 766 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
aw | +0.001 |
course | +0.001 |
crow | +0.001 |
Run | +0.001 |
goose | +0.001 |
Neg logit contributions | |
organ | -0.001 |
ilda | -0.001 |
nie | -0.001 |
Em | -0.001 |
any | -0.001 |
Token | very |
Token ID | 845 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
aw | +0.056 |
course | +0.053 |
Run | +0.047 |
Too | +0.046 |
crow | +0.046 |
Neg logit contributions | |
ilda | -0.055 |
organ | -0.055 |
nie | -0.055 |
any | -0.054 |
ingu | -0.054 |
Token | well |
Token ID | 880 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
organ | +0.075 |
ilda | +0.074 |
nie | +0.074 |
Em | +0.072 |
ingu | +0.072 |
Neg logit contributions | |
aw | -0.062 |
course | -0.062 |
crow | -0.049 |
Run | -0.047 |
Too | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
ilda | +0.052 |
organ | +0.051 |
nie | +0.051 |
any | +0.049 |
Em | +0.049 |
Neg logit contributions | |
aw | -0.049 |
course | -0.048 |
crow | -0.040 |
Run | -0.039 |
Too | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
aw | +0.013 |
course | +0.012 |
crow | +0.010 |
no | +0.009 |
Run | +0.009 |
Neg logit contributions | |
organ | -0.016 |
ilda | -0.016 |
Em | -0.016 |
any | -0.015 |
nie | -0.015 |
Token | deliver |
Token ID | 5203 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
ilda | +0.022 |
organ | +0.022 |
nie | +0.022 |
Em | +0.021 |
any | +0.021 |
Neg logit contributions | |
aw | -0.022 |
course | -0.022 |
crow | -0.018 |
Run | -0.017 |
goose | -0.017 |
Token | them |
Token ID | 606 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ilda | +0.015 |
nie | +0.015 |
organ | +0.015 |
ingu | +0.015 |
isha | +0.015 |
Neg logit contributions | |
aw | -0.014 |
course | -0.013 |
Run | -0.011 |
crow | -0.011 |
Too | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
aw | +0.005 |
course | +0.005 |
crow | +0.004 |
goose | +0.004 |
no | +0.004 |
Neg logit contributions | |
ilda | -0.006 |
Em | -0.006 |
organ | -0.006 |
any | -0.006 |
nie | -0.006 |
Token | my |
Token ID | 616 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ilda | +0.025 |
organ | +0.024 |
nie | +0.024 |
Em | +0.024 |
ingu | +0.024 |
Neg logit contributions | |
aw | -0.022 |
course | -0.021 |
crow | -0.017 |
Run | -0.017 |
Too | -0.016 |
Token | family |
Token ID | 1641 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
aw | +0.060 |
course | +0.058 |
Run | +0.050 |
crow | +0.050 |
Too | +0.048 |
Neg logit contributions | |
ilda | -0.048 |
nie | -0.046 |
organ | -0.046 |
isha | -0.046 |
ingu | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
organ | +0.120 |
ilda | +0.120 |
Em | +0.117 |
nie | +0.116 |
any | +0.116 |
Neg logit contributions | |
aw | -0.091 |
course | -0.089 |
crow | -0.070 |
goose | -0.065 |
Run | -0.064 |
Token | That |
Token ID | 1320 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
ilda | +0.001 |
organ | +0.001 |
nie | +0.001 |
Em | +0.001 |
any | +0.001 |
Neg logit contributions | |
aw | -0.000 |
course | -0.000 |
crow | -0.000 |
Run | -0.000 |
goose | -0.000 |
Token | 's |
Token ID | 338 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
ilda | +0.011 |
nie | +0.011 |
organ | +0.011 |
isha | +0.010 |
any | +0.010 |
Neg logit contributions | |
aw | -0.011 |
course | -0.010 |
Run | -0.009 |
Too | -0.008 |
crow | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ilda | +0.035 |
any | +0.035 |
Em | +0.035 |
organ | +0.034 |
to | +0.034 |
Neg logit contributions | |
aw | -0.026 |
course | -0.026 |
no | -0.020 |
crow | -0.020 |
goose | -0.019 |
Token | best |
Token ID | 1266 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
aw | +0.009 |
course | +0.008 |
Run | +0.007 |
crow | +0.007 |
Too | +0.007 |
Neg logit contributions | |
ilda | -0.009 |
nie | -0.009 |
organ | -0.009 |
isha | -0.008 |
Em | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -9.58e-01 |
Pos logit contributions | |
aw | +0.052 |
Run | +0.048 |
goose | +0.045 |
course | +0.045 |
Too | +0.045 |
Neg logit contributions | |
ilda | -0.045 |
Em | -0.044 |
nie | -0.043 |
any | -0.043 |
Jackie | -0.042 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
organ | +0.043 |
ilda | +0.043 |
nie | +0.042 |
ingu | +0.041 |
any | +0.041 |
Neg logit contributions | |
aw | -0.037 |
course | -0.037 |
crow | -0.030 |
Run | -0.027 |
Too | -0.026 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
nie | +0.030 |
ilda | +0.030 |
organ | +0.029 |
ingu | +0.029 |
any | +0.029 |
Neg logit contributions | |
aw | -0.024 |
course | -0.024 |
crow | -0.019 |
fountain | -0.018 |
Run | -0.018 |
Token | there |
Token ID | 612 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
organ | +0.030 |
any | +0.028 |
ilda | +0.027 |
nie | +0.027 |
Em | +0.026 |
Neg logit contributions | |
aw | -0.066 |
course | -0.066 |
crow | -0.057 |
no | -0.056 |
goose | -0.055 |
Token | was |
Token ID | 373 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
organ | +0.032 |
Jackie | +0.032 |
ilda | +0.031 |
nie | +0.031 |
Em | +0.031 |
Neg logit contributions | |
aw | -0.046 |
course | -0.042 |
Run | -0.038 |
crow | -0.037 |
Too | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
aw | +0.026 |
course | +0.025 |
crow | +0.021 |
Run | +0.020 |
Too | +0.020 |
Neg logit contributions | |
organ | -0.031 |
nie | -0.031 |
Em | -0.031 |
ilda | -0.031 |
Jackie | -0.030 |
Token | little |
Token ID | 1310 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ilda | +0.031 |
organ | +0.030 |
any | +0.030 |
ingu | +0.028 |
nie | +0.028 |
Neg logit contributions | |
aw | -0.033 |
course | -0.031 |
goose | -0.027 |
fountain | -0.026 |
Run | -0.026 |
Token | girl |
Token ID | 2576 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
nie | +0.056 |
isha | +0.053 |
Em | +0.053 |
Jackie | +0.053 |
ilda | +0.052 |
Neg logit contributions | |
aw | -0.057 |
course | -0.055 |
crow | -0.045 |
Too | -0.045 |
Run | -0.044 |
Token | named |
Token ID | 3706 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
aw | +0.030 |
course | +0.029 |
Run | +0.024 |
Too | +0.024 |
crow | +0.023 |
Neg logit contributions | |
nie | -0.045 |
Em | -0.045 |
any | -0.045 |
ilda | -0.045 |
organ | -0.044 |
Token | Sophie |
Token ID | 35331 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
course | +0.093 |
aw | +0.092 |
crow | +0.071 |
no | +0.070 |
fountain | +0.069 |
Neg logit contributions | |
organ | -0.157 |
ingu | -0.155 |
ilda | -0.155 |
isha | -0.152 |
nie | -0.152 |
Token | . |
Token ID | 13 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
organ | +0.100 |
ingu | +0.098 |
ilda | +0.097 |
iddles | +0.096 |
cere | +0.094 |
Neg logit contributions | |
aw | -0.040 |
course | -0.035 |
no | -0.024 |
crow | -0.024 |
goose | -0.022 |
Token | made |
Token ID | 925 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
aw | +0.062 |
course | +0.060 |
crow | +0.047 |
Run | +0.047 |
no | +0.046 |
Neg logit contributions | |
ilda | -0.061 |
nie | -0.059 |
any | -0.059 |
Em | -0.059 |
organ | -0.059 |
Token | a |
Token ID | 257 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
aw | +0.033 |
course | +0.032 |
crow | +0.026 |
Run | +0.025 |
Too | +0.024 |
Neg logit contributions | |
organ | -0.041 |
ilda | -0.041 |
nie | -0.040 |
Em | -0.040 |
ingu | -0.040 |
Token | swing |
Token ID | 9628 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
organ | +0.021 |
ilda | +0.021 |
nie | +0.021 |
Em | +0.021 |
ingu | +0.020 |
Neg logit contributions | |
aw | -0.028 |
course | -0.027 |
crow | -0.024 |
Run | -0.023 |
Too | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Run | +0.127 |
Too | +0.123 |
course | +0.122 |
aw | +0.122 |
crow | +0.119 |
Neg logit contributions | |
organ | -0.081 |
ilda | -0.077 |
designs | -0.074 |
neatly | -0.074 |
ingu | -0.073 |
Token | played |
Token ID | 2826 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
organ | +0.005 |
ilda | +0.005 |
Em | +0.004 |
any | +0.004 |
Jackie | +0.004 |
Neg logit contributions | |
aw | -0.005 |
course | -0.004 |
crow | -0.004 |
Too | -0.004 |
Run | -0.004 |
Token | all |
Token ID | 477 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
organ | +0.037 |
Em | +0.034 |
ilda | +0.034 |
to | +0.033 |
iddles | +0.033 |
Neg logit contributions | |
aw | -0.044 |
course | -0.042 |
crow | -0.039 |
Run | -0.036 |
Too | -0.036 |
Token | day |
Token ID | 1110 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
nie | +0.091 |
organ | +0.087 |
any | +0.087 |
Em | +0.085 |
ilda | +0.083 |
Neg logit contributions | |
aw | -0.125 |
course | -0.118 |
Run | -0.104 |
crow | -0.101 |
Too | -0.099 |
Token | long |
Token ID | 890 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
aw | +0.004 |
course | +0.004 |
crow | +0.003 |
Run | +0.003 |
fountain | +0.003 |
Neg logit contributions | |
organ | -0.005 |
ilda | -0.005 |
any | -0.005 |
nie | -0.005 |
ingu | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
aw | +0.020 |
course | +0.019 |
crow | +0.017 |
Run | +0.017 |
Too | +0.016 |
Neg logit contributions | |
ilda | -0.018 |
organ | -0.018 |
Em | -0.018 |
nie | -0.018 |
any | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
ilda | +0.007 |
nie | +0.007 |
organ | +0.007 |
isha | +0.007 |
Em | +0.007 |
Neg logit contributions | |
aw | -0.006 |
course | -0.006 |
crow | -0.005 |
Run | -0.005 |
fountain | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
nie | +0.021 |
ilda | +0.021 |
any | +0.021 |
organ | +0.021 |
cere | +0.021 |
Neg logit contributions | |
aw | -0.016 |
course | -0.016 |
crow | -0.012 |
Run | -0.011 |
fountain | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
organ | +0.065 |
nie | +0.065 |
ilda | +0.063 |
any | +0.062 |
cere | +0.062 |
Neg logit contributions | |
aw | -0.048 |
course | -0.044 |
crow | -0.036 |
Zip | -0.032 |
no | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
organ | +0.032 |
ilda | +0.031 |
nie | +0.031 |
any | +0.030 |
ingu | +0.030 |
Neg logit contributions | |
aw | -0.031 |
course | -0.030 |
crow | -0.024 |
Run | -0.023 |
goose | -0.023 |
Token | B |
Token ID | 33 |
Feature activation | -6.48e+00 |
Pos logit contributions | |
Em | +0.032 |
ilda | +0.031 |
nie | +0.031 |
organ | +0.030 |
any | +0.030 |
Neg logit contributions | |
aw | -0.028 |
course | -0.027 |
crow | -0.022 |
Run | -0.021 |
fountain | -0.021 |
Token | un |
Token ID | 403 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
organ | +0.149 |
ilda | +0.147 |
nie | +0.140 |
Em | +0.138 |
isha | +0.137 |
Neg logit contributions | |
aw | -0.391 |
course | -0.380 |
crow | -0.339 |
Run | -0.329 |
Too | -0.323 |
Token | - |
Token ID | 12 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ilda | +0.203 |
nie | +0.200 |
any | +0.199 |
Em | +0.197 |
organ | +0.196 |
Neg logit contributions | |
aw | -0.235 |
course | -0.229 |
crow | -0.190 |
Run | -0.187 |
goose | -0.182 |
Token | B |
Token ID | 33 |
Feature activation | -6.60e+00 |
Pos logit contributions | |
ilda | +0.040 |
organ | +0.039 |
nie | +0.039 |
Em | +0.038 |
any | +0.038 |
Neg logit contributions | |
aw | -0.070 |
course | -0.068 |
crow | -0.059 |
Run | -0.057 |
goose | -0.056 |
Token | un |
Token ID | 403 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
organ | +0.135 |
ilda | +0.129 |
nie | +0.125 |
cere | +0.124 |
Em | +0.123 |
Neg logit contributions | |
aw | -0.414 |
course | -0.401 |
crow | -0.364 |
Run | -0.350 |
Too | -0.346 |
Token | had |
Token ID | 550 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ilda | +0.201 |
nie | +0.198 |
any | +0.198 |
Em | +0.194 |
organ | +0.192 |
Neg logit contributions | |
aw | -0.237 |
course | -0.232 |
crow | -0.191 |
Run | -0.190 |
fountain | -0.185 |
Token | an |
Token ID | 281 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
organ | +0.068 |
ilda | +0.067 |
Em | +0.066 |
nie | +0.065 |
any | +0.065 |
Neg logit contributions | |
aw | -0.067 |
course | -0.065 |
crow | -0.055 |
Run | -0.053 |
goose | -0.052 |
Token | idea |
Token ID | 2126 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
nie | +0.049 |
organ | +0.049 |
ilda | +0.048 |
any | +0.046 |
ingu | +0.046 |
Neg logit contributions | |
aw | -0.071 |
course | -0.067 |
crow | -0.058 |
Run | -0.058 |
Too | -0.056 |
Token | ! |
Token ID | 0 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ilda | +0.031 |
any | +0.029 |
to | +0.029 |
Jackie | +0.029 |
nie | +0.029 |
Neg logit contributions | |
aw | -0.037 |
course | -0.033 |
Too | -0.030 |
crow | -0.029 |
Run | -0.028 |
Token | that |
Token ID | 326 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
ilda | +0.031 |
nie | +0.030 |
Jackie | +0.030 |
organ | +0.030 |
Em | +0.029 |
Neg logit contributions | |
aw | -0.013 |
course | -0.012 |
crow | -0.010 |
Too | -0.009 |
Run | -0.008 |
Token | day |
Token ID | 1110 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
organ | +0.038 |
ilda | +0.038 |
ingu | +0.037 |
iddles | +0.036 |
cere | +0.036 |
Neg logit contributions | |
course | -0.032 |
aw | -0.030 |
crow | -0.025 |
no | -0.024 |
Run | -0.024 |
Token | on |
Token ID | 319 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ilda | +0.008 |
organ | +0.008 |
nie | +0.008 |
Em | +0.008 |
any | +0.008 |
Neg logit contributions | |
aw | -0.007 |
course | -0.007 |
crow | -0.006 |
Run | -0.006 |
goose | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
aw | +0.005 |
course | +0.004 |
crow | +0.003 |
Run | +0.003 |
goose | +0.003 |
Neg logit contributions | |
ilda | -0.009 |
Em | -0.009 |
organ | -0.009 |
nie | -0.009 |
Jackie | -0.009 |
Token | Tim |
Token ID | 5045 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
organ | +0.001 |
ilda | +0.001 |
nie | +0.001 |
Em | +0.001 |
any | +0.001 |
Neg logit contributions | |
aw | -0.001 |
course | -0.001 |
crow | -0.001 |
Run | -0.001 |
goose | -0.001 |
Token | my |
Token ID | 1820 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
ouses | +0.025 |
organ | +0.025 |
to | +0.024 |
cere | +0.024 |
Em | +0.023 |
Neg logit contributions | |
course | -0.023 |
aw | -0.021 |
no | -0.017 |
end | -0.017 |
crow | -0.016 |
Token | loved |
Token ID | 6151 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Em | +0.268 |
ilda | +0.262 |
nie | +0.258 |
cere | +0.255 |
Jackie | +0.255 |
Neg logit contributions | |
aw | -0.190 |
course | -0.186 |
no | -0.146 |
crow | -0.138 |
dove | -0.129 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
nie | +0.116 |
any | +0.113 |
Em | +0.113 |
ilda | +0.112 |
isha | +0.110 |
Neg logit contributions | |
course | -0.074 |
aw | -0.069 |
that | -0.062 |
no | -0.057 |
goose | -0.056 |
Token | burying |
Token ID | 48360 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
organ | +0.118 |
ilda | +0.115 |
Em | +0.114 |
nie | +0.112 |
ingu | +0.111 |
Neg logit contributions | |
aw | -0.111 |
course | -0.106 |
crow | -0.089 |
Run | -0.087 |
goose | -0.084 |
Token | games |
Token ID | 1830 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ilda | +0.123 |
nie | +0.121 |
any | +0.121 |
organ | +0.121 |
Em | +0.120 |
Neg logit contributions | |
aw | -0.106 |
course | -0.102 |
crow | -0.081 |
Run | -0.078 |
goose | -0.076 |
Token | with |
Token ID | 351 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
aw | +0.049 |
course | +0.045 |
crow | +0.041 |
Run | +0.041 |
Too | +0.040 |
Neg logit contributions | |
organ | -0.048 |
ilda | -0.047 |
Em | -0.046 |
nie | -0.046 |
Jackie | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
nie | +0.028 |
ilda | +0.027 |
Jackie | +0.027 |
Em | +0.027 |
any | +0.027 |
Neg logit contributions | |
aw | -0.029 |
course | -0.027 |
crow | -0.023 |
Run | -0.022 |
Too | -0.022 |
Token | I |
Token ID | 314 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
ilda | +0.034 |
nie | +0.034 |
organ | +0.034 |
Em | +0.034 |
any | +0.034 |
Neg logit contributions | |
aw | -0.023 |
course | -0.022 |
crow | -0.017 |
Run | -0.016 |
goose | -0.016 |
Token | don |
Token ID | 836 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
aw | +0.015 |
course | +0.015 |
crow | +0.012 |
Run | +0.012 |
goose | +0.011 |
Neg logit contributions | |
ilda | -0.014 |
organ | -0.014 |
nie | -0.013 |
Em | -0.013 |
ingu | -0.013 |
Token | 't |
Token ID | 470 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
nie | +0.029 |
ingu | +0.029 |
organ | +0.029 |
cere | +0.028 |
ilda | +0.028 |
Neg logit contributions | |
aw | -0.018 |
course | -0.018 |
crow | -0.014 |
Run | -0.014 |
Too | -0.013 |
Token | know |
Token ID | 760 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
aw | +0.009 |
course | +0.009 |
crow | +0.008 |
Run | +0.007 |
goose | +0.007 |
Neg logit contributions | |
ilda | -0.007 |
organ | -0.007 |
ingu | -0.007 |
Em | -0.007 |
nie | -0.007 |
Token | how |
Token ID | 703 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
ilda | +0.135 |
nie | +0.133 |
organ | +0.131 |
Em | +0.129 |
any | +0.129 |
Neg logit contributions | |
aw | -0.151 |
course | -0.146 |
crow | -0.125 |
Run | -0.122 |
Too | -0.119 |
Token | to |
Token ID | 284 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
organ | +0.259 |
ingu | +0.254 |
ilda | +0.251 |
iddles | +0.242 |
isha | +0.241 |
Neg logit contributions | |
aw | -0.229 |
course | -0.219 |
crow | -0.188 |
no | -0.184 |
Run | -0.178 |
Token | get |
Token ID | 651 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
ilda | +0.023 |
organ | +0.022 |
nie | +0.022 |
Em | +0.022 |
any | +0.022 |
Neg logit contributions | |
aw | -0.028 |
course | -0.027 |
crow | -0.023 |
Run | -0.022 |
goose | -0.022 |
Token | back |
Token ID | 736 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
aw | +0.012 |
course | +0.012 |
crow | +0.010 |
Run | +0.009 |
Too | +0.009 |
Neg logit contributions | |
ilda | -0.012 |
nie | -0.011 |
organ | -0.011 |
any | -0.011 |
Em | -0.011 |
Token | home |
Token ID | 1363 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
aw | +0.068 |
course | +0.066 |
crow | +0.055 |
Run | +0.053 |
goose | +0.052 |
Neg logit contributions | |
ilda | -0.061 |
organ | -0.061 |
nie | -0.060 |
Em | -0.060 |
ingu | -0.059 |
Token | ." |
Token ID | 526 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
aw | +0.013 |
course | +0.012 |
crow | +0.010 |
Run | +0.010 |
goose | +0.010 |
Neg logit contributions | |
ilda | -0.011 |
organ | -0.011 |
nie | -0.011 |
any | -0.011 |
Em | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
nie | +0.017 |
ilda | +0.017 |
any | +0.016 |
cere | +0.016 |
organ | +0.016 |
Neg logit contributions | |
aw | -0.011 |
course | -0.011 |
crow | -0.008 |
Run | -0.007 |
goose | -0.007 |
Token | But |
Token ID | 1537 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
ilda | +0.018 |
organ | +0.017 |
nie | +0.017 |
isha | +0.017 |
ingu | +0.017 |
Neg logit contributions | |
aw | -0.015 |
course | -0.015 |
crow | -0.012 |
Run | -0.012 |
Too | -0.011 |
Token | then |
Token ID | 788 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
aw | +0.134 |
course | +0.122 |
crow | +0.104 |
Too | +0.093 |
Run | +0.093 |
Neg logit contributions | |
organ | -0.186 |
nie | -0.184 |
Jackie | -0.182 |
ilda | -0.182 |
any | -0.180 |
Token | , |
Token ID | 11 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
aw | +0.032 |
course | +0.030 |
crow | +0.025 |
Too | +0.022 |
fountain | +0.022 |
Neg logit contributions | |
organ | -0.050 |
Jackie | -0.050 |
ilda | -0.049 |
nie | -0.049 |
Em | -0.048 |
Token | Tim |
Token ID | 5045 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
aw | +0.017 |
course | +0.016 |
crow | +0.015 |
Too | +0.013 |
goose | +0.013 |
Neg logit contributions | |
organ | -0.014 |
Jackie | -0.014 |
Em | -0.013 |
ilda | -0.013 |
cere | -0.013 |
Token | my |
Token ID | 1820 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
ouses | +0.013 |
organ | +0.013 |
cere | +0.013 |
Em | +0.013 |
isha | +0.012 |
Neg logit contributions | |
aw | -0.018 |
course | -0.017 |
no | -0.014 |
crow | -0.014 |
dog | -0.013 |
Token | accidentally |
Token ID | 14716 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
organ | +0.219 |
ilda | +0.218 |
nie | +0.215 |
Em | +0.214 |
any | +0.212 |
Neg logit contributions | |
aw | -0.227 |
course | -0.212 |
crow | -0.177 |
Run | -0.172 |
goose | -0.167 |
Token | hurt |
Token ID | 5938 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
nie | +0.054 |
Em | +0.053 |
ilda | +0.053 |
isha | +0.052 |
ingu | +0.052 |
Neg logit contributions | |
aw | -0.046 |
course | -0.044 |
no | -0.037 |
Run | -0.036 |
crow | -0.035 |
Token | himself |
Token ID | 2241 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
aw | +0.022 |
course | +0.021 |
crow | +0.018 |
Run | +0.017 |
goose | +0.017 |
Neg logit contributions | |
ilda | -0.021 |
organ | -0.021 |
nie | -0.020 |
Em | -0.020 |
any | -0.020 |
Token | while |
Token ID | 981 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
organ | +0.088 |
ilda | +0.088 |
Em | +0.088 |
nie | +0.086 |
isha | +0.086 |
Neg logit contributions | |
aw | -0.064 |
course | -0.062 |
crow | -0.048 |
Run | -0.046 |
goose | -0.045 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
aw | +0.138 |
course | +0.133 |
crow | +0.106 |
Run | +0.104 |
no | +0.102 |
Neg logit contributions | |
organ | -0.163 |
ilda | -0.160 |
nie | -0.160 |
Em | -0.158 |
any | -0.157 |
Token | cookies |
Token ID | 14746 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
aw | +0.006 |
course | +0.006 |
crow | +0.005 |
Run | +0.005 |
Too | +0.005 |
Neg logit contributions | |
organ | -0.007 |
ilda | -0.007 |
nie | -0.007 |
Em | -0.007 |
any | -0.007 |
Token | were |
Token ID | 547 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
ilda | +0.001 |
organ | +0.001 |
any | +0.001 |
Em | +0.001 |
Jackie | +0.001 |
Neg logit contributions | |
aw | -0.001 |
course | -0.001 |
crow | -0.001 |
Run | -0.001 |
Too | -0.001 |
Token | hidden |
Token ID | 7104 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
aw | +0.021 |
course | +0.021 |
crow | +0.016 |
fountain | +0.016 |
no | +0.016 |
Neg logit contributions | |
organ | -0.025 |
ilda | -0.025 |
nie | -0.025 |
Em | -0.025 |
any | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
aw | +0.035 |
course | +0.034 |
crow | +0.028 |
Run | +0.028 |
Too | +0.027 |
Neg logit contributions | |
ilda | -0.034 |
organ | -0.034 |
nie | -0.033 |
any | -0.033 |
Em | -0.033 |
Token | Tim |
Token ID | 5045 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
ilda | +0.025 |
organ | +0.025 |
nie | +0.025 |
isha | +0.024 |
any | +0.024 |
Neg logit contributions | |
aw | -0.018 |
course | -0.018 |
crow | -0.014 |
Run | -0.013 |
fountain | -0.013 |
Token | my |
Token ID | 1820 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
organ | +0.016 |
ilda | +0.015 |
Em | +0.015 |
cere | +0.015 |
to | +0.014 |
Neg logit contributions | |
aw | -0.027 |
course | -0.027 |
crow | -0.022 |
goose | -0.021 |
no | -0.021 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ilda | +0.235 |
organ | +0.233 |
nie | +0.230 |
Em | +0.229 |
any | +0.226 |
Neg logit contributions | |
aw | -0.218 |
course | -0.211 |
crow | -0.170 |
Run | -0.164 |
goose | -0.162 |
Token | that |
Token ID | 326 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
nie | +0.068 |
organ | +0.067 |
ilda | +0.067 |
any | +0.067 |
Em | +0.066 |
Neg logit contributions | |
aw | -0.021 |
course | -0.020 |
crow | -0.011 |
Run | -0.010 |
goose | -0.009 |
Token | it |
Token ID | 340 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
ilda | +0.030 |
nie | +0.029 |
any | +0.029 |
organ | +0.029 |
Em | +0.029 |
Neg logit contributions | |
course | -0.021 |
aw | -0.020 |
no | -0.016 |
crow | -0.016 |
Run | -0.016 |
Token | 's |
Token ID | 338 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
Em | +0.003 |
cere | +0.003 |
isha | +0.003 |
ingu | +0.003 |
bie | +0.003 |
Neg logit contributions | |
course | -0.001 |
aw | -0.001 |
no | -0.001 |
crow | -0.001 |
neither | -0.001 |
Token | always |
Token ID | 1464 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
ilda | +0.035 |
isha | +0.034 |
Em | +0.033 |
cere | +0.032 |
to | +0.032 |
Neg logit contributions | |
course | -0.034 |
aw | -0.032 |
no | -0.031 |
that | -0.027 |
neither | -0.027 |