Token | � |
Token ID | 40367 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
ingred | +0.034 |
Sect | +0.034 |
� | +0.033 |
ufact | +0.033 |
Voc | +0.032 |
Neg logit contributions | |
ó | -0.036 |
alert | -0.035 |
FB | -0.035 |
umber | -0.034 |
Teddy | -0.034 |
Token | � |
Token ID | 253 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
ó | +0.248 |
alert | +0.237 |
FB | +0.237 |
umber | +0.236 |
ory | +0.234 |
Neg logit contributions | |
ingred | -0.222 |
Sect | -0.218 |
� | -0.214 |
ufact | -0.212 |
Voc | -0.206 |
Token | � |
Token ID | 161 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
ó | +0.041 |
alert | +0.040 |
FB | +0.040 |
umber | +0.040 |
Teddy | +0.039 |
Neg logit contributions | |
ingred | -0.038 |
Sect | -0.037 |
� | -0.036 |
ufact | -0.036 |
Voc | -0.035 |
Token | � |
Token ID | 254 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
ingred | +0.175 |
Sect | +0.172 |
� | +0.168 |
ufact | +0.166 |
Voc | +0.162 |
Neg logit contributions | |
ó | -0.225 |
alert | -0.217 |
FB | -0.217 |
umber | -0.216 |
Teddy | -0.214 |
Token | � |
Token ID | 109 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
ingred | +0.084 |
Sect | +0.083 |
� | +0.080 |
ufact | +0.080 |
Voc | +0.076 |
Neg logit contributions | |
ó | -0.158 |
FB | -0.153 |
alert | -0.153 |
umber | -0.152 |
ory | -0.151 |
Token | � |
Token ID | 27332 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
ingred | +0.010 |
Sect | +0.010 |
� | +0.010 |
ufact | +0.010 |
Voc | +0.010 |
Neg logit contributions | |
ó | -0.011 |
alert | -0.010 |
FB | -0.010 |
umber | -0.010 |
Teddy | -0.010 |
Token | � |
Token ID | 121 |
Feature activation | +3.55e-03 |
Pos logit contributions | |
ingred | +0.354 |
Sect | +0.348 |
� | +0.338 |
ufact | +0.335 |
Voc | +0.323 |
Neg logit contributions | |
ó | -0.622 |
FB | -0.600 |
alert | -0.600 |
umber | -0.596 |
Teddy | -0.592 |
Token | � |
Token ID | 252 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ingred | +0.002 |
Sect | +0.002 |
� | +0.002 |
ufact | +0.002 |
Voc | +0.002 |
Neg logit contributions | |
ó | -0.003 |
FB | -0.003 |
alert | -0.003 |
umber | -0.003 |
ory | -0.003 |
Token | Alternative |
Token ID | 27182 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
ingred | +0.094 |
Sect | +0.092 |
ufact | +0.090 |
� | +0.090 |
Voc | +0.087 |
Neg logit contributions | |
ó | -0.104 |
alert | -0.100 |
FB | -0.100 |
umber | -0.099 |
Teddy | -0.098 |
Token | Facts |
Token ID | 26972 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
ó | +0.019 |
alert | +0.019 |
FB | +0.019 |
umber | +0.019 |
Teddy | +0.018 |
Neg logit contributions | |
ingred | -0.020 |
Sect | -0.019 |
� | -0.019 |
ufact | -0.019 |
Voc | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
ingred | +0.052 |
Sect | +0.051 |
� | +0.050 |
ufact | +0.050 |
Voc | +0.049 |
Neg logit contributions | |
ó | -0.040 |
alert | -0.038 |
FB | -0.038 |
umber | -0.038 |
Teddy | -0.038 |
Token | of |
Token ID | 286 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
ingred | +0.034 |
Sect | +0.034 |
� | +0.033 |
ufact | +0.033 |
Voc | +0.032 |
Neg logit contributions | |
ó | -0.031 |
FB | -0.029 |
alert | -0.029 |
umber | -0.029 |
Teddy | -0.029 |
Token | Sync |
Token ID | 35908 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ingred | +0.030 |
Sect | +0.029 |
� | +0.029 |
ufact | +0.028 |
Voc | +0.028 |
Neg logit contributions | |
ó | -0.025 |
FB | -0.024 |
alert | -0.024 |
umber | -0.024 |
db | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
ó | +0.136 |
alert | +0.130 |
FB | +0.130 |
umber | +0.129 |
Teddy | +0.127 |
Neg logit contributions | |
ingred | -0.161 |
Sect | -0.159 |
� | -0.156 |
ufact | -0.154 |
Voc | -0.151 |
Token |
|
Token ID | 198 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
ingred | +0.026 |
Sect | +0.026 |
� | +0.025 |
ufact | +0.025 |
Voc | +0.024 |
Neg logit contributions | |
ó | -0.023 |
alert | -0.022 |
FB | -0.022 |
umber | -0.022 |
Teddy | -0.021 |
Token | This |
Token ID | 1212 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
ingred | +0.026 |
Sect | +0.025 |
� | +0.025 |
ufact | +0.025 |
Voc | +0.024 |
Neg logit contributions | |
ó | -0.023 |
alert | -0.022 |
FB | -0.022 |
umber | -0.022 |
Teddy | -0.022 |
Token | slideshow |
Token ID | 48828 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
ingred | +0.010 |
Sect | +0.010 |
� | +0.010 |
ufact | +0.010 |
Voc | +0.010 |
Neg logit contributions | |
ó | -0.009 |
FB | -0.009 |
alert | -0.009 |
umber | -0.009 |
db | -0.009 |
Token | requires |
Token ID | 4433 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
ingred | +0.448 |
Sect | +0.441 |
� | +0.440 |
ufact | +0.426 |
Voc | +0.422 |
Neg logit contributions | |
ó | -0.415 |
umber | -0.398 |
FB | -0.397 |
alert | -0.396 |
Teddy | -0.392 |
Token | JavaScript |
Token ID | 11933 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
ó | +0.002 |
umber | +0.002 |
db | +0.002 |
FB | +0.002 |
alert | +0.002 |
Neg logit contributions | |
ingred | -0.005 |
� | -0.005 |
Sect | -0.005 |
Voc | -0.005 |
ufact | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
ó | +0.166 |
FB | +0.160 |
alert | +0.159 |
umber | +0.159 |
Teddy | +0.157 |
Neg logit contributions | |
ingred | -0.185 |
Sect | -0.184 |
� | -0.184 |
Voc | -0.177 |
ufact | -0.175 |
Token |
|
Token ID | 198 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
ingred | +0.026 |
Sect | +0.025 |
� | +0.025 |
ufact | +0.024 |
Voc | +0.024 |
Neg logit contributions | |
ó | -0.021 |
FB | -0.020 |
alert | -0.020 |
umber | -0.020 |
Teddy | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
ingred | +0.021 |
Sect | +0.021 |
� | +0.021 |
ufact | +0.020 |
Voc | +0.020 |
Neg logit contributions | |
ó | -0.018 |
alert | -0.018 |
FB | -0.018 |
umber | -0.018 |
Teddy | -0.017 |
Token | at |
Token ID | 379 |
Feature activation | -2.23e-03 |
Pos logit contributions | |
ingred | +0.050 |
Sect | +0.049 |
� | +0.048 |
ufact | +0.048 |
Voc | +0.047 |
Neg logit contributions | |
ó | -0.042 |
FB | -0.040 |
alert | -0.040 |
umber | -0.040 |
Teddy | -0.039 |
Token | all |
Token ID | 477 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ó | +0.001 |
FB | +0.001 |
alert | +0.001 |
umber | +0.001 |
db | +0.001 |
Neg logit contributions | |
ingred | -0.002 |
Sect | -0.002 |
� | -0.002 |
ufact | -0.002 |
Voc | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
ó | +0.084 |
FB | +0.081 |
alert | +0.081 |
umber | +0.080 |
Teddy | +0.079 |
Neg logit contributions | |
ingred | -0.102 |
Sect | -0.100 |
� | -0.099 |
ufact | -0.098 |
Voc | -0.096 |
Token | It |
Token ID | 632 |
Feature activation | -7.68e-02 |
Pos logit contributions | |
ingred | +0.011 |
Sect | +0.011 |
� | +0.011 |
ufact | +0.011 |
Voc | +0.011 |
Neg logit contributions | |
ó | -0.009 |
alert | -0.009 |
FB | -0.009 |
umber | -0.009 |
Teddy | -0.009 |
Token | plays |
Token ID | 5341 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
ó | +0.055 |
alert | +0.052 |
FB | +0.052 |
umber | +0.052 |
ory | +0.051 |
Neg logit contributions | |
ingred | -0.062 |
Sect | -0.061 |
� | -0.059 |
ufact | -0.059 |
Voc | -0.058 |
Token | compet |
Token ID | 2307 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
ingred | +0.026 |
Sect | +0.025 |
� | +0.025 |
ufact | +0.024 |
Voc | +0.024 |
Neg logit contributions | |
ó | -0.022 |
FB | -0.021 |
alert | -0.021 |
umber | -0.021 |
Teddy | -0.021 |
Token | ently |
Token ID | 1473 |
Feature activation | +7.82e-03 |
Pos logit contributions | |
ingred | +0.463 |
Sect | +0.456 |
� | +0.447 |
ufact | +0.443 |
Voc | +0.434 |
Neg logit contributions | |
ó | -0.401 |
alert | -0.384 |
FB | -0.383 |
umber | -0.381 |
ory | -0.377 |
Token | in |
Token ID | 287 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
ingred | +0.007 |
Sect | +0.006 |
� | +0.006 |
ufact | +0.006 |
Voc | +0.006 |
Neg logit contributions | |
ó | -0.005 |
FB | -0.005 |
alert | -0.005 |
umber | -0.005 |
Teddy | -0.005 |
Token | all |
Token ID | 477 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ó | +0.016 |
FB | +0.015 |
alert | +0.015 |
umber | +0.015 |
db | +0.015 |
Neg logit contributions | |
ingred | -0.019 |
Sect | -0.019 |
� | -0.019 |
ufact | -0.018 |
Voc | -0.018 |
Token | aspects |
Token ID | 7612 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
ó | +0.084 |
alert | +0.080 |
FB | +0.080 |
umber | +0.079 |
Teddy | +0.078 |
Neg logit contributions | |
ingred | -0.101 |
Sect | -0.100 |
� | -0.098 |
ufact | -0.097 |
Voc | -0.095 |
Token | , |
Token ID | 11 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
ó | +0.012 |
alert | +0.011 |
FB | +0.011 |
umber | +0.011 |
Teddy | +0.011 |
Neg logit contributions | |
ingred | -0.013 |
Sect | -0.013 |
� | -0.013 |
ufact | -0.013 |
Voc | -0.012 |
Token | E |
Token ID | 36 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
ingred | +0.010 |
Sect | +0.010 |
� | +0.010 |
ufact | +0.010 |
Voc | +0.010 |
Neg logit contributions | |
ó | -0.009 |
alert | -0.009 |
FB | -0.009 |
umber | -0.009 |
Teddy | -0.009 |
Token | BS |
Token ID | 4462 |
Feature activation | +7.44e-03 |
Pos logit contributions | |
ó | +0.080 |
FB | +0.077 |
alert | +0.076 |
umber | +0.076 |
db | +0.075 |
Neg logit contributions | |
ingred | -0.086 |
Sect | -0.084 |
� | -0.083 |
ufact | -0.082 |
Voc | -0.080 |
Token | CO |
Token ID | 8220 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
ingred | +0.006 |
Sect | +0.006 |
� | +0.006 |
ufact | +0.006 |
Voc | +0.005 |
Neg logit contributions | |
ó | -0.005 |
FB | -0.005 |
alert | -0.005 |
umber | -0.005 |
Teddy | -0.005 |
Token | Information |
Token ID | 6188 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
ingred | +0.027 |
Sect | +0.027 |
� | +0.026 |
ufact | +0.026 |
Voc | +0.025 |
Neg logit contributions | |
ó | -0.024 |
alert | -0.023 |
FB | -0.023 |
umber | -0.023 |
Teddy | -0.022 |
Token | Services |
Token ID | 6168 |
Feature activation | +9.32e-02 |
Pos logit contributions | |
ingred | +0.041 |
Sect | +0.041 |
� | +0.040 |
ufact | +0.039 |
Voc | +0.039 |
Neg logit contributions | |
ó | -0.045 |
alert | -0.043 |
FB | -0.043 |
umber | -0.043 |
Teddy | -0.042 |
Token | compet |
Token ID | 2307 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
ingred | +0.073 |
Sect | +0.072 |
� | +0.071 |
ufact | +0.070 |
Voc | +0.069 |
Neg logit contributions | |
ó | -0.067 |
alert | -0.064 |
FB | -0.064 |
umber | -0.064 |
Teddy | -0.063 |
Token | es |
Token ID | 274 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
ingred | +0.499 |
Sect | +0.493 |
� | +0.486 |
ufact | +0.481 |
Voc | +0.473 |
Neg logit contributions | |
ó | -0.351 |
FB | -0.335 |
alert | -0.335 |
umber | -0.331 |
Teddy | -0.328 |
Token | within |
Token ID | 1626 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
ó | +0.023 |
FB | +0.022 |
alert | +0.022 |
umber | +0.021 |
Teddy | +0.021 |
Neg logit contributions | |
ingred | -0.031 |
Sect | -0.031 |
� | -0.031 |
ufact | -0.030 |
Voc | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +7.45e-03 |
Pos logit contributions | |
ó | +0.046 |
alert | +0.044 |
FB | +0.044 |
umber | +0.043 |
Teddy | +0.043 |
Neg logit contributions | |
ingred | -0.055 |
Sect | -0.054 |
� | -0.053 |
ufact | -0.053 |
Voc | -0.052 |
Token | library |
Token ID | 5888 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
ingred | +0.006 |
Sect | +0.006 |
� | +0.006 |
ufact | +0.006 |
Voc | +0.005 |
Neg logit contributions | |
ó | -0.005 |
FB | -0.005 |
alert | -0.005 |
umber | -0.005 |
Teddy | -0.005 |
Token | technology |
Token ID | 3037 |
Feature activation | -1.64e-03 |
Pos logit contributions | |
ó | +0.168 |
alert | +0.162 |
FB | +0.162 |
umber | +0.161 |
Teddy | +0.159 |
Neg logit contributions | |
ingred | -0.149 |
Sect | -0.146 |
� | -0.143 |
ufact | -0.141 |
Voc | -0.138 |
Token | This |
Token ID | 1212 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
ingred | +0.010 |
Sect | +0.010 |
� | +0.009 |
ufact | +0.009 |
Voc | +0.009 |
Neg logit contributions | |
ó | -0.008 |
FB | -0.008 |
alert | -0.008 |
umber | -0.008 |
Teddy | -0.008 |
Token | is |
Token ID | 318 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
ó | +0.008 |
alert | +0.008 |
FB | +0.008 |
umber | +0.008 |
Teddy | +0.008 |
Neg logit contributions | |
ingred | -0.008 |
Sect | -0.008 |
� | -0.008 |
ufact | -0.008 |
Voc | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
ó | +0.025 |
FB | +0.024 |
alert | +0.024 |
umber | +0.024 |
Teddy | +0.023 |
Neg logit contributions | |
ingred | -0.029 |
Sect | -0.029 |
� | -0.028 |
ufact | -0.028 |
Voc | -0.027 |
Token | true |
Token ID | 2081 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
ó | +0.051 |
alert | +0.049 |
FB | +0.049 |
umber | +0.049 |
Teddy | +0.048 |
Neg logit contributions | |
ingred | -0.056 |
Sect | -0.055 |
� | -0.054 |
ufact | -0.054 |
Voc | -0.053 |
Token | core |
Token ID | 4755 |
Feature activation | -9.06e-02 |
Pos logit contributions | |
ingred | +0.061 |
Sect | +0.060 |
� | +0.059 |
ufact | +0.059 |
Voc | +0.057 |
Neg logit contributions | |
ó | -0.058 |
alert | -0.055 |
FB | -0.055 |
umber | -0.055 |
Teddy | -0.055 |
Token | compet |
Token ID | 2307 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
ó | +0.065 |
alert | +0.063 |
FB | +0.062 |
umber | +0.062 |
Teddy | +0.061 |
Neg logit contributions | |
ingred | -0.071 |
Sect | -0.070 |
� | -0.069 |
ufact | -0.068 |
Voc | -0.067 |
Token | ency |
Token ID | 1387 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
ingred | +0.420 |
Sect | +0.413 |
� | +0.405 |
ufact | +0.402 |
Voc | +0.392 |
Neg logit contributions | |
ó | -0.431 |
alert | -0.413 |
FB | -0.413 |
umber | -0.411 |
ory | -0.406 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
ingred | +0.032 |
Sect | +0.031 |
� | +0.031 |
ufact | +0.030 |
Voc | +0.030 |
Neg logit contributions | |
ó | -0.024 |
alert | -0.023 |
FB | -0.023 |
umber | -0.023 |
Teddy | -0.022 |
Token | He |
Token ID | 679 |
Feature activation | -9.93e-03 |
Pos logit contributions | |
ingred | +0.009 |
Sect | +0.009 |
� | +0.009 |
ufact | +0.008 |
Voc | +0.008 |
Neg logit contributions | |
ó | -0.007 |
alert | -0.007 |
FB | -0.007 |
umber | -0.006 |
Teddy | -0.006 |
Token | is |
Token ID | 318 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
ó | +0.007 |
alert | +0.007 |
FB | +0.007 |
umber | +0.007 |
Teddy | +0.007 |
Neg logit contributions | |
ingred | -0.008 |
Sect | -0.008 |
� | -0.007 |
ufact | -0.007 |
Voc | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
ó | +0.030 |
alert | +0.029 |
FB | +0.029 |
umber | +0.029 |
Teddy | +0.029 |
Neg logit contributions | |
ingred | -0.033 |
Sect | -0.033 |
� | -0.032 |
ufact | -0.032 |
Voc | -0.031 |
Token | in |
Token ID | 287 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
ó | +0.058 |
alert | +0.056 |
FB | +0.056 |
umber | +0.055 |
Teddy | +0.055 |
Neg logit contributions | |
ingred | -0.059 |
Sect | -0.058 |
� | -0.057 |
ufact | -0.057 |
Voc | -0.055 |
Token | writing |
Token ID | 3597 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
ó | +0.020 |
FB | +0.020 |
alert | +0.019 |
umber | +0.019 |
Teddy | +0.019 |
Neg logit contributions | |
ingred | -0.025 |
Sect | -0.024 |
� | -0.024 |
ufact | -0.024 |
Voc | -0.023 |
Token | that |
Token ID | 326 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
ó | +0.098 |
alert | +0.094 |
FB | +0.094 |
umber | +0.093 |
Teddy | +0.092 |
Neg logit contributions | |
ingred | -0.112 |
Sect | -0.110 |
� | -0.108 |
ufact | -0.108 |
Voc | -0.105 |
Token | a |
Token ID | 257 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
ingred | +0.065 |
Sect | +0.064 |
� | +0.063 |
ufact | +0.062 |
Voc | +0.061 |
Neg logit contributions | |
ó | -0.058 |
alert | -0.055 |
FB | -0.055 |
umber | -0.055 |
Teddy | -0.054 |
Token | book |
Token ID | 1492 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ingred | +0.024 |
Sect | +0.023 |
� | +0.023 |
ufact | +0.022 |
Voc | +0.022 |
Neg logit contributions | |
ó | -0.023 |
FB | -0.022 |
alert | -0.022 |
umber | -0.022 |
Teddy | -0.022 |
Token | compet |
Token ID | 2307 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
ó | +0.073 |
alert | +0.070 |
FB | +0.070 |
umber | +0.069 |
Teddy | +0.068 |
Neg logit contributions | |
ingred | -0.079 |
Sect | -0.078 |
� | -0.076 |
ufact | -0.076 |
Voc | -0.074 |
Token | es |
Token ID | 274 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
ingred | +0.509 |
Sect | +0.502 |
� | +0.493 |
ufact | +0.490 |
Voc | +0.480 |
Neg logit contributions | |
ó | -0.341 |
FB | -0.323 |
alert | -0.323 |
umber | -0.321 |
ory | -0.316 |
Token | with |
Token ID | 351 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ó | +0.024 |
FB | +0.023 |
alert | +0.023 |
umber | +0.023 |
Teddy | +0.023 |
Neg logit contributions | |
ingred | -0.034 |
Sect | -0.033 |
� | -0.033 |
ufact | -0.032 |
Voc | -0.032 |
Token | Snapchat |
Token ID | 31546 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ó | +0.083 |
FB | +0.080 |
alert | +0.080 |
umber | +0.079 |
db | +0.078 |
Neg logit contributions | |
ingred | -0.099 |
Sect | -0.098 |
� | -0.096 |
ufact | -0.095 |
Voc | -0.093 |
Token | and |
Token ID | 290 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
ingred | +0.102 |
Sect | +0.101 |
� | +0.099 |
ufact | +0.098 |
Voc | +0.096 |
Neg logit contributions | |
ó | -0.087 |
alert | -0.083 |
FB | -0.083 |
umber | -0.082 |
Teddy | -0.081 |
Token | Instagram |
Token ID | 10767 |
Feature activation | +9.86e-02 |
Pos logit contributions | |
ó | +0.012 |
FB | +0.011 |
alert | +0.011 |
umber | +0.011 |
db | +0.011 |
Neg logit contributions | |
ingred | -0.013 |
Sect | -0.013 |
� | -0.013 |
ufact | -0.012 |
Voc | -0.012 |
Token | A |
Token ID | 317 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
Sect | +0.013 |
ingred | +0.013 |
� | +0.013 |
ufact | +0.013 |
Voc | +0.013 |
Neg logit contributions | |
ó | -0.012 |
alert | -0.011 |
FB | -0.011 |
umber | -0.011 |
ory | -0.011 |
Token | man |
Token ID | 582 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
ó | +0.053 |
FB | +0.051 |
alert | +0.051 |
umber | +0.051 |
Teddy | +0.050 |
Neg logit contributions | |
ingred | -0.064 |
Sect | -0.064 |
� | -0.062 |
ufact | -0.061 |
Voc | -0.060 |
Token | attacked |
Token ID | 7384 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
ingred | +0.023 |
Sect | +0.023 |
� | +0.022 |
ufact | +0.022 |
Voc | +0.022 |
Neg logit contributions | |
ó | -0.019 |
FB | -0.019 |
alert | -0.019 |
umber | -0.018 |
db | -0.018 |
Token | Thomas |
Token ID | 5658 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
ingred | +0.054 |
Sect | +0.053 |
� | +0.053 |
ufact | +0.052 |
Voc | +0.051 |
Neg logit contributions | |
ó | -0.041 |
FB | -0.039 |
alert | -0.039 |
umber | -0.039 |
db | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | +8.22e-03 |
Pos logit contributions | |
ó | +0.009 |
FB | +0.009 |
alert | +0.009 |
umber | +0.009 |
Teddy | +0.009 |
Neg logit contributions | |
ingred | -0.010 |
Sect | -0.010 |
� | -0.010 |
ufact | -0.010 |
Voc | -0.010 |
Token | vide |
Token ID | 18784 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
ingred | +0.007 |
Sect | +0.007 |
� | +0.007 |
ufact | +0.006 |
Voc | +0.006 |
Neg logit contributions | |
ó | -0.006 |
FB | -0.005 |
umber | -0.005 |
alert | -0.005 |
db | -0.005 |
Token | ographer |
Token ID | 18539 |
Feature activation | +2.29e-03 |
Pos logit contributions | |
ingred | +0.441 |
Sect | +0.434 |
� | +0.430 |
ufact | +0.426 |
Voc | +0.415 |
Neg logit contributions | |
ó | -0.394 |
FB | -0.385 |
alert | -0.383 |
umber | -0.381 |
Barney | -0.377 |
Token | Miguel |
Token ID | 29825 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
ingred | +0.002 |
Sect | +0.002 |
� | +0.002 |
ufact | +0.002 |
Voc | +0.002 |
Neg logit contributions | |
ó | -0.002 |
FB | -0.002 |
alert | -0.002 |
umber | -0.002 |
db | -0.002 |
Token | � |
Token ID | 564 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
ingred | +0.036 |
Sect | +0.035 |
� | +0.035 |
ufact | +0.034 |
Voc | +0.033 |
Neg logit contributions | |
ó | -0.032 |
alert | -0.030 |
FB | -0.030 |
umber | -0.030 |
Teddy | -0.030 |
Token | � |
Token ID | 250 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
ingred | +0.018 |
Sect | +0.018 |
� | +0.018 |
ufact | +0.017 |
Voc | +0.017 |
Neg logit contributions | |
ó | -0.021 |
FB | -0.021 |
alert | -0.021 |
umber | -0.021 |
Teddy | -0.020 |
Token | V |
Token ID | 53 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
ingred | +0.035 |
Sect | +0.034 |
� | +0.033 |
ufact | +0.033 |
Voc | +0.032 |
Neg logit contributions | |
ó | -0.031 |
FB | -0.029 |
alert | -0.029 |
umber | -0.029 |
db | -0.029 |
Token | 000 |
Token ID | 830 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ingred | +0.002 |
Sect | +0.002 |
� | +0.002 |
ufact | +0.002 |
Voc | +0.002 |
Neg logit contributions | |
ó | -0.001 |
alert | -0.001 |
FB | -0.001 |
umber | -0.001 |
Teddy | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +7.82e-03 |
Pos logit contributions | |
ó | +0.089 |
FB | +0.086 |
alert | +0.085 |
umber | +0.085 |
Teddy | +0.084 |
Neg logit contributions | |
ingred | -0.109 |
Sect | -0.107 |
� | -0.106 |
ufact | -0.104 |
Voc | -0.102 |
Token | ( |
Token ID | 357 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
ingred | +0.006 |
Sect | +0.006 |
� | +0.006 |
ufact | +0.006 |
Voc | +0.006 |
Neg logit contributions | |
ó | -0.005 |
alert | -0.005 |
FB | -0.005 |
umber | -0.005 |
ory | -0.005 |
Token | See |
Token ID | 6214 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ó | +0.008 |
alert | +0.008 |
FB | +0.008 |
umber | +0.008 |
Teddy | +0.008 |
Neg logit contributions | |
ingred | -0.010 |
Sect | -0.010 |
� | -0.010 |
ufact | -0.010 |
Voc | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
ingred | +0.110 |
Sect | +0.108 |
� | +0.106 |
ufact | +0.105 |
Voc | +0.103 |
Neg logit contributions | |
ó | -0.094 |
alert | -0.090 |
FB | -0.090 |
umber | -0.089 |
Teddy | -0.088 |
Token | slideshow |
Token ID | 48828 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
ingred | +0.012 |
Sect | +0.012 |
� | +0.012 |
ufact | +0.012 |
Voc | +0.012 |
Neg logit contributions | |
ó | -0.011 |
FB | -0.011 |
alert | -0.011 |
umber | -0.011 |
Teddy | -0.010 |
Token | below |
Token ID | 2174 |
Feature activation | -8.93e-02 |
Pos logit contributions | |
ingred | +0.487 |
Sect | +0.481 |
� | +0.473 |
ufact | +0.468 |
Voc | +0.460 |
Neg logit contributions | |
ó | -0.355 |
FB | -0.338 |
alert | -0.338 |
umber | -0.335 |
Teddy | -0.332 |
Token | for |
Token ID | 329 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
ó | +0.054 |
alert | +0.052 |
FB | +0.052 |
umber | +0.051 |
Teddy | +0.051 |
Neg logit contributions | |
ingred | -0.080 |
Sect | -0.079 |
� | -0.078 |
ufact | -0.077 |
Voc | -0.076 |
Token | some |
Token ID | 617 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
ó | +0.022 |
alert | +0.021 |
FB | +0.021 |
umber | +0.021 |
Teddy | +0.021 |
Neg logit contributions | |
ingred | -0.027 |
Sect | -0.027 |
� | -0.026 |
ufact | -0.026 |
Voc | -0.026 |
Token | great |
Token ID | 1049 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
ingred | +0.023 |
Sect | +0.022 |
� | +0.022 |
ufact | +0.022 |
Voc | +0.021 |
Neg logit contributions | |
ó | -0.020 |
FB | -0.020 |
alert | -0.020 |
umber | -0.019 |
Teddy | -0.019 |
Token | Honey |
Token ID | 21788 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
ó | +0.028 |
alert | +0.027 |
FB | +0.027 |
umber | +0.027 |
Teddy | +0.027 |
Neg logit contributions | |
ingred | -0.028 |
Sect | -0.027 |
� | -0.027 |
ufact | -0.026 |
Voc | -0.026 |
Token | Perception |
Token ID | 35802 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
ó | +0.139 |
FB | +0.134 |
alert | +0.133 |
umber | +0.132 |
Teddy | +0.131 |
Neg logit contributions | |
ingred | -0.156 |
Sect | -0.152 |
� | -0.150 |
ufact | -0.149 |
Voc | -0.145 |
Token | . |
Token ID | 13 |
Feature activation | -3.99e-04 |
Pos logit contributions | |
ó | +0.048 |
alert | +0.046 |
FB | +0.046 |
umber | +0.045 |
Teddy | +0.045 |
Neg logit contributions | |
ingred | -0.056 |
Sect | -0.055 |
� | -0.054 |
ufact | -0.054 |
Voc | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | +3.12e-03 |
Pos logit contributions | |
ó | +0.000 |
alert | +0.000 |
FB | +0.000 |
umber | +0.000 |
Teddy | +0.000 |
Neg logit contributions | |
ingred | -0.000 |
Sect | -0.000 |
� | -0.000 |
ufact | -0.000 |
Voc | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -9.20e-04 |
Pos logit contributions | |
ingred | +0.003 |
Sect | +0.002 |
� | +0.002 |
ufact | +0.002 |
Voc | +0.002 |
Neg logit contributions | |
ó | -0.002 |
alert | -0.002 |
FB | -0.002 |
umber | -0.002 |
Teddy | -0.002 |
Token | This |
Token ID | 1212 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
ó | +0.001 |
FB | +0.001 |
alert | +0.001 |
umber | +0.001 |
Teddy | +0.001 |
Neg logit contributions | |
ingred | -0.001 |
Sect | -0.001 |
� | -0.001 |
ufact | -0.001 |
Voc | -0.001 |
Token | slideshow |
Token ID | 48828 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
ó | +0.021 |
alert | +0.020 |
FB | +0.020 |
umber | +0.020 |
Teddy | +0.020 |
Neg logit contributions | |
ingred | -0.003 |
Sect | -0.002 |
ufact | -0.002 |
� | -0.002 |
Voc | -0.002 |
Token | requires |
Token ID | 4433 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
ingred | +0.456 |
Sect | +0.448 |
� | +0.440 |
ufact | +0.438 |
Voc | +0.428 |
Neg logit contributions | |
ó | -0.382 |
alert | -0.366 |
FB | -0.365 |
umber | -0.362 |
db | -0.358 |
Token | JavaScript |
Token ID | 11933 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ó | +0.014 |
umber | +0.013 |
FB | +0.013 |
alert | +0.013 |
db | +0.013 |
Neg logit contributions | |
� | -0.034 |
ingred | -0.034 |
Sect | -0.034 |
Voc | -0.033 |
ufact | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +6.77e-03 |
Pos logit contributions | |
ó | +0.177 |
alert | +0.169 |
FB | +0.169 |
umber | +0.168 |
Teddy | +0.166 |
Neg logit contributions | |
ingred | -0.215 |
Sect | -0.211 |
� | -0.208 |
ufact | -0.206 |
Voc | -0.202 |
Token |
|
Token ID | 198 |
Feature activation | +5.56e-03 |
Pos logit contributions | |
ingred | +0.006 |
Sect | +0.005 |
� | +0.005 |
ufact | +0.005 |
Voc | +0.005 |
Neg logit contributions | |
ó | -0.005 |
alert | -0.004 |
FB | -0.004 |
umber | -0.004 |
Teddy | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +6.22e-03 |
Pos logit contributions | |
ingred | +0.004 |
Sect | +0.004 |
� | +0.004 |
ufact | +0.004 |
Voc | +0.004 |
Neg logit contributions | |
ó | -0.004 |
alert | -0.004 |
FB | -0.004 |
umber | -0.004 |
Teddy | -0.004 |
Token | Minnesota |
Token ID | 8919 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ó | +0.021 |
FB | +0.020 |
alert | +0.020 |
umber | +0.020 |
db | +0.020 |
Neg logit contributions | |
ingred | -0.025 |
Sect | -0.025 |
� | -0.024 |
ufact | -0.024 |
Voc | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +3.79e-03 |
Pos logit contributions | |
ingred | +0.122 |
Sect | +0.120 |
� | +0.119 |
ufact | +0.117 |
Voc | +0.115 |
Neg logit contributions | |
ó | -0.103 |
alert | -0.099 |
FB | -0.099 |
umber | -0.098 |
db | -0.097 |
Token |
|
Token ID | 198 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
ingred | +0.003 |
Sect | +0.003 |
� | +0.003 |
ufact | +0.003 |
Voc | +0.003 |
Neg logit contributions | |
ó | -0.002 |
alert | -0.002 |
FB | -0.002 |
umber | -0.002 |
db | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
ingred | +0.013 |
Sect | +0.013 |
� | +0.013 |
ufact | +0.013 |
Voc | +0.012 |
Neg logit contributions | |
ó | -0.011 |
alert | -0.011 |
FB | -0.011 |
umber | -0.011 |
Teddy | -0.011 |
Token | This |
Token ID | 1212 |
Feature activation | -6.43e-03 |
Pos logit contributions | |
ingred | +0.010 |
Sect | +0.010 |
� | +0.010 |
ufact | +0.010 |
Voc | +0.010 |
Neg logit contributions | |
ó | -0.009 |
alert | -0.008 |
FB | -0.008 |
umber | -0.008 |
Teddy | -0.008 |
Token | slideshow |
Token ID | 48828 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
ó | +0.009 |
alert | +0.009 |
FB | +0.009 |
umber | +0.009 |
Teddy | +0.009 |
Neg logit contributions | |
ingred | -0.001 |
Sect | -0.001 |
� | -0.001 |
ufact | -0.001 |
Voc | -0.001 |
Token | requires |
Token ID | 4433 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
ingred | +0.454 |
Sect | +0.446 |
� | +0.438 |
ufact | +0.435 |
Voc | +0.426 |
Neg logit contributions | |
ó | -0.382 |
alert | -0.366 |
FB | -0.365 |
umber | -0.361 |
Teddy | -0.358 |
Token | JavaScript |
Token ID | 11933 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
ó | +0.008 |
FB | +0.007 |
umber | +0.007 |
alert | +0.007 |
db | +0.007 |
Neg logit contributions | |
Sect | -0.019 |
ingred | -0.019 |
� | -0.019 |
Voc | -0.019 |
ufact | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +9.69e-03 |
Pos logit contributions | |
ó | +0.174 |
alert | +0.166 |
FB | +0.166 |
umber | +0.165 |
Teddy | +0.163 |
Neg logit contributions | |
ingred | -0.212 |
Sect | -0.209 |
� | -0.205 |
ufact | -0.203 |
Voc | -0.199 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ingred | +0.008 |
Sect | +0.008 |
� | +0.008 |
ufact | +0.008 |
Voc | +0.007 |
Neg logit contributions | |
ó | -0.007 |
alert | -0.006 |
FB | -0.006 |
umber | -0.006 |
Teddy | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
ingred | +0.008 |
Sect | +0.008 |
� | +0.008 |
ufact | +0.008 |
Voc | +0.008 |
Neg logit contributions | |
ó | -0.007 |
alert | -0.007 |
FB | -0.007 |
umber | -0.007 |
Teddy | -0.007 |
Token | : |
Token ID | 25 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
ó | +0.034 |
alert | +0.032 |
FB | +0.032 |
umber | +0.032 |
Teddy | +0.032 |
Neg logit contributions | |
ingred | -0.043 |
Sect | -0.042 |
� | -0.041 |
ufact | -0.041 |
Voc | -0.040 |
Token | blended |
Token ID | 32063 |
Feature activation | +7.66e-02 |
Pos logit contributions | |
ó | +0.065 |
alert | +0.062 |
FB | +0.062 |
umber | +0.061 |
Teddy | +0.061 |
Neg logit contributions | |
ingred | -0.062 |
Sect | -0.061 |
� | -0.059 |
ufact | -0.059 |
Voc | -0.057 |
Token | roles |
Token ID | 9176 |
Feature activation | -8.69e-02 |
Pos logit contributions | |
ingred | +0.057 |
Sect | +0.056 |
� | +0.055 |
ufact | +0.055 |
Voc | +0.053 |
Neg logit contributions | |
ó | -0.058 |
alert | -0.056 |
FB | -0.056 |
umber | -0.055 |
ory | -0.055 |
Token | that |
Token ID | 326 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
ó | +0.058 |
alert | +0.055 |
FB | +0.055 |
umber | +0.055 |
Teddy | +0.054 |
Neg logit contributions | |
ingred | -0.073 |
Sect | -0.072 |
� | -0.070 |
ufact | -0.070 |
Voc | -0.068 |
Token | require |
Token ID | 2421 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
ingred | +0.048 |
Sect | +0.047 |
� | +0.046 |
ufact | +0.046 |
Voc | +0.045 |
Neg logit contributions | |
ó | -0.045 |
alert | -0.043 |
FB | -0.043 |
umber | -0.042 |
Teddy | -0.042 |
Token | compet |
Token ID | 2307 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
ó | +0.114 |
alert | +0.111 |
FB | +0.109 |
Teddy | +0.108 |
umber | +0.108 |
Neg logit contributions | |
ingred | -0.114 |
Sect | -0.112 |
ufact | -0.110 |
� | -0.110 |
Voc | -0.106 |
Token | ency |
Token ID | 1387 |
Feature activation | +5.56e-03 |
Pos logit contributions | |
ingred | +0.376 |
Sect | +0.369 |
� | +0.361 |
ufact | +0.357 |
Voc | +0.347 |
Neg logit contributions | |
ó | -0.449 |
alert | -0.433 |
FB | -0.432 |
umber | -0.430 |
db | -0.426 |
Token | in |
Token ID | 287 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
ingred | +0.005 |
Sect | +0.005 |
� | +0.005 |
ufact | +0.004 |
Voc | +0.004 |
Neg logit contributions | |
ó | -0.004 |
alert | -0.004 |
FB | -0.004 |
umber | -0.004 |
Teddy | -0.003 |
Token | both |
Token ID | 1111 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
ó | +0.034 |
alert | +0.033 |
FB | +0.033 |
umber | +0.032 |
Teddy | +0.032 |
Neg logit contributions | |
ingred | -0.038 |
Sect | -0.037 |
� | -0.036 |
ufact | -0.036 |
Voc | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -9.00e-03 |
Pos logit contributions | |
ingred | +0.016 |
Sect | +0.015 |
ufact | +0.015 |
� | +0.015 |
Voc | +0.015 |
Neg logit contributions | |
ó | -0.014 |
alert | -0.014 |
FB | -0.014 |
umber | -0.013 |
Teddy | -0.013 |
Token | � |
Token ID | 447 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
ó | +0.006 |
FB | +0.006 |
alert | +0.006 |
umber | +0.006 |
Teddy | +0.006 |
Neg logit contributions | |
ingred | -0.007 |
Sect | -0.007 |
� | -0.007 |
ufact | -0.007 |
Voc | -0.007 |
Token | promoted |
Token ID | 13722 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ó | +0.121 |
FB | +0.116 |
alert | +0.116 |
umber | +0.115 |
Teddy | +0.114 |
Neg logit contributions | |
ingred | -0.137 |
Sect | -0.135 |
� | -0.133 |
ufact | -0.131 |
Voc | -0.129 |
Token | the |
Token ID | 262 |
Feature activation | +5.07e-03 |
Pos logit contributions | |
ingred | +0.086 |
Sect | +0.084 |
� | +0.083 |
ufact | +0.082 |
Voc | +0.080 |
Neg logit contributions | |
ó | -0.071 |
alert | -0.068 |
FB | -0.068 |
umber | -0.067 |
Teddy | -0.067 |
Token | � |
Token ID | 564 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ingred | +0.004 |
Sect | +0.004 |
� | +0.004 |
ufact | +0.004 |
Voc | +0.004 |
Neg logit contributions | |
ó | -0.003 |
FB | -0.003 |
alert | -0.003 |
umber | -0.003 |
db | -0.003 |
Token | � |
Token ID | 250 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
ingred | +0.010 |
Sect | +0.010 |
ufact | +0.010 |
� | +0.009 |
Voc | +0.009 |
Neg logit contributions | |
ó | -0.015 |
alert | -0.014 |
FB | -0.014 |
ory | -0.014 |
umber | -0.014 |
Token | cons |
Token ID | 5936 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
ingred | +0.033 |
Sect | +0.033 |
� | +0.032 |
ufact | +0.032 |
Voc | +0.031 |
Neg logit contributions | |
ó | -0.033 |
FB | -0.031 |
alert | -0.031 |
umber | -0.031 |
Teddy | -0.031 |
Token | cience |
Token ID | 4234 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
ingred | +0.091 |
Sect | +0.089 |
� | +0.086 |
ufact | +0.085 |
Voc | +0.082 |
Neg logit contributions | |
ó | -0.168 |
alert | -0.163 |
FB | -0.162 |
umber | -0.162 |
ory | -0.161 |
Token | clause |
Token ID | 13444 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
ingred | +0.387 |
Sect | +0.380 |
� | +0.371 |
ufact | +0.369 |
Voc | +0.359 |
Neg logit contributions | |
ó | -0.436 |
alert | -0.421 |
FB | -0.419 |
umber | -0.416 |
Teddy | -0.413 |
Token | , |
Token ID | 11 |
Feature activation | +8.64e-03 |
Pos logit contributions | |
ingred | +0.126 |
Sect | +0.124 |
� | +0.121 |
ufact | +0.121 |
Voc | +0.118 |
Neg logit contributions | |
ó | -0.106 |
alert | -0.102 |
FB | -0.101 |
umber | -0.101 |
Teddy | -0.100 |
Token | � |
Token ID | 447 |
Feature activation | -2.92e-04 |
Pos logit contributions | |
ingred | +0.006 |
Sect | +0.006 |
� | +0.006 |
ufact | +0.006 |
Voc | +0.006 |
Neg logit contributions | |
ó | -0.007 |
alert | -0.006 |
FB | -0.006 |
umber | -0.006 |
Teddy | -0.006 |
Token | � |
Token ID | 251 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
ó | +0.000 |
FB | +0.000 |
alert | +0.000 |
umber | +0.000 |
Teddy | +0.000 |
Neg logit contributions | |
ingred | -0.000 |
Sect | -0.000 |
� | -0.000 |
ufact | -0.000 |
Voc | -0.000 |
Token | which |
Token ID | 543 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
ingred | +0.012 |
Sect | +0.012 |
� | +0.012 |
ufact | +0.012 |
Voc | +0.012 |
Neg logit contributions | |
ó | -0.012 |
alert | -0.012 |
FB | -0.012 |
umber | -0.012 |
Teddy | -0.012 |
Token | Miss |
Token ID | 4544 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
ingred | +0.015 |
Sect | +0.014 |
ufact | +0.014 |
� | +0.014 |
Voc | +0.013 |
Neg logit contributions | |
ó | -0.020 |
FB | -0.020 |
alert | -0.020 |
umber | -0.020 |
Teddy | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +4.21e-04 |
Pos logit contributions | |
ingred | +0.139 |
Sect | +0.137 |
� | +0.135 |
ufact | +0.134 |
Voc | +0.131 |
Neg logit contributions | |
ó | -0.116 |
alert | -0.111 |
FB | -0.111 |
umber | -0.110 |
db | -0.109 |
Token |
|
Token ID | 198 |
Feature activation | +1.46e-03 |
Pos logit contributions | |
ingred | +0.000 |
Sect | +0.000 |
� | +0.000 |
ufact | +0.000 |
Voc | +0.000 |
Neg logit contributions | |
ó | -0.000 |
alert | -0.000 |
FB | -0.000 |
umber | -0.000 |
ory | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e-03 |
Pos logit contributions | |
ingred | +0.001 |
Sect | +0.001 |
� | +0.001 |
ufact | +0.001 |
Voc | +0.001 |
Neg logit contributions | |
ó | -0.001 |
alert | -0.001 |
FB | -0.001 |
umber | -0.001 |
Teddy | -0.001 |
Token | This |
Token ID | 1212 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
ó | +0.001 |
alert | +0.001 |
FB | +0.001 |
umber | +0.001 |
Teddy | +0.001 |
Neg logit contributions | |
ingred | -0.001 |
Sect | -0.001 |
� | -0.001 |
ufact | -0.001 |
Voc | -0.001 |
Token | slideshow |
Token ID | 48828 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
ó | +0.024 |
alert | +0.024 |
FB | +0.024 |
umber | +0.024 |
Teddy | +0.024 |
Neg logit contributions | |
ingred | -0.002 |
Sect | -0.002 |
� | -0.002 |
ufact | -0.002 |
Voc | -0.001 |
Token | requires |
Token ID | 4433 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
ingred | +0.442 |
Sect | +0.435 |
� | +0.427 |
ufact | +0.424 |
Voc | +0.415 |
Neg logit contributions | |
ó | -0.376 |
alert | -0.360 |
FB | -0.360 |
umber | -0.357 |
Teddy | -0.353 |
Token | JavaScript |
Token ID | 11933 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
ó | +0.016 |
FB | +0.015 |
umber | +0.015 |
alert | +0.015 |
db | +0.014 |
Neg logit contributions | |
Sect | -0.039 |
ingred | -0.039 |
� | -0.039 |
Voc | -0.038 |
ufact | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ó | +0.187 |
alert | +0.179 |
FB | +0.179 |
umber | +0.177 |
Teddy | +0.175 |
Neg logit contributions | |
ingred | -0.227 |
Sect | -0.224 |
� | -0.220 |
ufact | -0.218 |
Voc | -0.214 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
ó | +0.009 |
alert | +0.009 |
FB | +0.009 |
umber | +0.009 |
Teddy | +0.009 |
Neg logit contributions | |
ingred | -0.011 |
Sect | -0.011 |
� | -0.011 |
ufact | -0.010 |
Voc | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -9.98e-03 |
Pos logit contributions | |
ó | +0.007 |
alert | +0.007 |
FB | +0.007 |
umber | +0.007 |
Teddy | +0.007 |
Neg logit contributions | |
ingred | -0.009 |
Sect | -0.008 |
� | -0.008 |
ufact | -0.008 |
Voc | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
ó | +0.037 |
FB | +0.036 |
alert | +0.036 |
umber | +0.035 |
Teddy | +0.035 |
Neg logit contributions | |
ingred | -0.045 |
Sect | -0.044 |
� | -0.044 |
ufact | -0.043 |
Voc | -0.042 |
Token |
|
Token ID | 198 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
ingred | +0.008 |
Sect | +0.008 |
� | +0.008 |
ufact | +0.008 |
Voc | +0.008 |
Neg logit contributions | |
ó | -0.007 |
alert | -0.007 |
FB | -0.007 |
umber | -0.007 |
Teddy | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +3.11e-03 |
Pos logit contributions | |
ingred | +0.011 |
Sect | +0.011 |
� | +0.011 |
ufact | +0.011 |
Voc | +0.010 |
Neg logit contributions | |
ó | -0.010 |
alert | -0.009 |
FB | -0.009 |
umber | -0.009 |
Teddy | -0.009 |
Token | With |
Token ID | 3152 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
ingred | +0.003 |
Sect | +0.002 |
� | +0.002 |
ufact | +0.002 |
Voc | +0.002 |
Neg logit contributions | |
ó | -0.002 |
alert | -0.002 |
FB | -0.002 |
umber | -0.002 |
Teddy | -0.002 |
Token | Josh |
Token ID | 8518 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
ingred | +0.019 |
Sect | +0.019 |
� | +0.019 |
ufact | +0.018 |
Voc | +0.018 |
Neg logit contributions | |
ó | -0.015 |
alert | -0.015 |
FB | -0.015 |
umber | -0.015 |
Teddy | -0.015 |
Token | Doct |
Token ID | 32155 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
ingred | +0.080 |
Sect | +0.078 |
ufact | +0.077 |
� | +0.077 |
Voc | +0.075 |
Neg logit contributions | |
ó | -0.046 |
alert | -0.044 |
FB | -0.044 |
Teddy | -0.044 |
umber | -0.043 |
Token | son |
Token ID | 1559 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Sect | +0.484 |
ingred | +0.478 |
� | +0.476 |
Voc | +0.463 |
ufact | +0.457 |
Neg logit contributions | |
ó | -0.321 |
FB | -0.309 |
alert | -0.305 |
umber | -0.301 |
Teddy | -0.301 |
Token | finally |
Token ID | 3443 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
ó | +0.095 |
alert | +0.091 |
FB | +0.091 |
umber | +0.090 |
Teddy | +0.090 |
Neg logit contributions | |
ingred | -0.093 |
Sect | -0.092 |
� | -0.090 |
ufact | -0.089 |
Voc | -0.087 |
Token | becoming |
Token ID | 5033 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
ó | +0.097 |
FB | +0.093 |
umber | +0.092 |
alert | +0.091 |
db | +0.091 |
Neg logit contributions | |
ingred | -0.115 |
Sect | -0.113 |
� | -0.112 |
ufact | -0.110 |
Voc | -0.108 |
Token | a |
Token ID | 257 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
ó | +0.011 |
FB | +0.010 |
umber | +0.010 |
alert | +0.010 |
db | +0.010 |
Neg logit contributions | |
ingred | -0.012 |
Sect | -0.012 |
� | -0.011 |
ufact | -0.011 |
Voc | -0.011 |
Token | force |
Token ID | 2700 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
ingred | +0.030 |
Sect | +0.030 |
� | +0.029 |
ufact | +0.029 |
Voc | +0.028 |
Neg logit contributions | |
ó | -0.026 |
FB | -0.024 |
umber | -0.024 |
alert | -0.024 |
db | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -5.76e-03 |
Pos logit contributions | |
ingred | +0.054 |
Sect | +0.053 |
� | +0.052 |
ufact | +0.052 |
Voc | +0.051 |
Neg logit contributions | |
ó | -0.046 |
alert | -0.044 |
FB | -0.044 |
umber | -0.044 |
Teddy | -0.043 |
Token | Football |
Token ID | 9957 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
ó | +0.004 |
FB | +0.004 |
alert | +0.004 |
umber | +0.004 |
db | +0.004 |
Neg logit contributions | |
ingred | -0.005 |
Sect | -0.005 |
� | -0.005 |
ufact | -0.005 |
Voc | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -5.75e-04 |
Pos logit contributions | |
ó | +0.145 |
FB | +0.139 |
alert | +0.139 |
umber | +0.138 |
Teddy | +0.137 |
Neg logit contributions | |
ingred | -0.172 |
Sect | -0.169 |
� | -0.165 |
ufact | -0.165 |
Voc | -0.160 |
Token |
|
Token ID | 198 |
Feature activation | +2.40e-03 |
Pos logit contributions | |
ó | +0.000 |
alert | +0.000 |
FB | +0.000 |
umber | +0.000 |
Teddy | +0.000 |
Neg logit contributions | |
ingred | -0.000 |
Sect | -0.000 |
� | -0.000 |
ufact | -0.000 |
Voc | -0.000 |
Token | This |
Token ID | 1212 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
ingred | +0.002 |
Sect | +0.002 |
� | +0.002 |
ufact | +0.002 |
Voc | +0.002 |
Neg logit contributions | |
ó | -0.002 |
alert | -0.002 |
FB | -0.002 |
umber | -0.002 |
Teddy | -0.002 |
Token | slideshow |
Token ID | 48828 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
ó | +0.024 |
alert | +0.024 |
FB | +0.024 |
umber | +0.024 |
Teddy | +0.024 |
Neg logit contributions | |
ingred | -0.004 |
Sect | -0.004 |
� | -0.004 |
ufact | -0.004 |
Voc | -0.004 |
Token | requires |
Token ID | 4433 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
ingred | +0.449 |
Sect | +0.441 |
� | +0.431 |
ufact | +0.431 |
Voc | +0.420 |
Neg logit contributions | |
ó | -0.369 |
alert | -0.353 |
FB | -0.351 |
umber | -0.348 |
ory | -0.344 |
Token | JavaScript |
Token ID | 11933 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ó | +0.015 |
umber | +0.014 |
FB | +0.014 |
db | +0.014 |
alert | +0.014 |
Neg logit contributions | |
� | -0.036 |
ingred | -0.036 |
Sect | -0.035 |
Voc | -0.034 |
ufact | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-03 |
Pos logit contributions | |
ó | +0.182 |
FB | +0.175 |
alert | +0.175 |
umber | +0.173 |
Teddy | +0.171 |
Neg logit contributions | |
ingred | -0.220 |
Sect | -0.217 |
� | -0.213 |
ufact | -0.211 |
Voc | -0.207 |
Token |
|
Token ID | 198 |
Feature activation | -9.69e-05 |
Pos logit contributions | |
ingred | +0.002 |
Sect | +0.002 |
� | +0.002 |
ufact | +0.002 |
Voc | +0.002 |
Neg logit contributions | |
ó | -0.002 |
alert | -0.002 |
FB | -0.002 |
umber | -0.002 |
Teddy | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +2.58e-03 |
Pos logit contributions | |
ó | +0.000 |
alert | +0.000 |
FB | +0.000 |
umber | +0.000 |
Teddy | +0.000 |
Neg logit contributions | |
ingred | -0.000 |
Sect | -0.000 |
� | -0.000 |
ufact | -0.000 |
Voc | -0.000 |
Token | Scroll |
Token ID | 17428 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ingred | +0.002 |
Sect | +0.002 |
� | +0.002 |
ufact | +0.002 |
Voc | +0.002 |
Neg logit contributions | |
ó | -0.002 |
alert | -0.002 |
FB | -0.002 |
umber | -0.002 |
Teddy | -0.002 |
Token | down |
Token ID | 866 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
ingred | +0.229 |
Sect | +0.226 |
� | +0.222 |
ufact | +0.219 |
Voc | +0.214 |
Neg logit contributions | |
ó | -0.238 |
FB | -0.229 |
alert | -0.229 |
umber | -0.227 |
Teddy | -0.225 |
Token | and |
Token ID | 290 |
Feature activation | -8.22e-03 |
Pos logit contributions | |
ingred | +0.054 |
Sect | +0.053 |
� | +0.052 |
ufact | +0.052 |
Voc | +0.050 |
Neg logit contributions | |
ó | -0.045 |
alert | -0.044 |
FB | -0.043 |
umber | -0.043 |
Teddy | -0.043 |
Token | click |
Token ID | 3904 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
ó | +0.007 |
FB | +0.006 |
alert | +0.006 |
umber | +0.006 |
Teddy | +0.006 |
Neg logit contributions | |
ingred | -0.006 |
Sect | -0.006 |
� | -0.006 |
ufact | -0.005 |
Voc | -0.005 |
Token | on |
Token ID | 319 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
ingred | +0.156 |
Sect | +0.155 |
� | +0.152 |
ufact | +0.150 |
Voc | +0.147 |
Neg logit contributions | |
ó | -0.141 |
FB | -0.136 |
alert | -0.135 |
umber | -0.135 |
Teddy | -0.133 |
Token | Vide |
Token ID | 42551 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
ingred | +0.045 |
Sect | +0.044 |
� | +0.044 |
ufact | +0.043 |
Voc | +0.042 |
Neg logit contributions | |
ó | -0.038 |
FB | -0.037 |
alert | -0.037 |
umber | -0.037 |
db | -0.036 |
Token | opl |
Token ID | 20106 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
ingred | +0.527 |
Sect | +0.521 |
� | +0.515 |
ufact | +0.510 |
Voc | +0.502 |
Neg logit contributions | |
ó | -0.282 |
FB | -0.267 |
alert | -0.267 |
umber | -0.263 |
Teddy | -0.261 |
Token | ayer |
Token ID | 2794 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
ó | +0.027 |
alert | +0.026 |
FB | +0.026 |
umber | +0.026 |
Teddy | +0.026 |
Neg logit contributions | |
ingred | -0.040 |
Sect | -0.039 |
� | -0.039 |
ufact | -0.038 |
Voc | -0.038 |
Token | Input |
Token ID | 23412 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ó | +0.091 |
alert | +0.087 |
FB | +0.087 |
umber | +0.086 |
Teddy | +0.085 |
Neg logit contributions | |
ingred | -0.101 |
Sect | -0.100 |
� | -0.098 |
ufact | -0.097 |
Voc | -0.095 |
Token | Stream |
Token ID | 12124 |
Feature activation | +2.47e-03 |
Pos logit contributions | |
ingred | +0.115 |
Sect | +0.113 |
ufact | +0.110 |
� | +0.110 |
Voc | +0.107 |
Neg logit contributions | |
ó | -0.104 |
alert | -0.100 |
FB | -0.100 |
umber | -0.099 |
ory | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-03 |
Pos logit contributions | |
ingred | +0.002 |
Sect | +0.002 |
� | +0.002 |
ufact | +0.002 |
Voc | +0.002 |
Neg logit contributions | |
ó | -0.002 |
alert | -0.002 |
FB | -0.002 |
umber | -0.002 |
Teddy | -0.002 |
Token | th |
Token ID | 400 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
ingred | +0.151 |
Sect | +0.149 |
� | +0.146 |
ufact | +0.145 |
Voc | +0.142 |
Neg logit contributions | |
ó | -0.108 |
alert | -0.103 |
FB | -0.103 |
umber | -0.102 |
Teddy | -0.100 |
Token | U |
Token ID | 471 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
ó | +0.047 |
alert | +0.046 |
FB | +0.046 |
umber | +0.045 |
Teddy | +0.045 |
Neg logit contributions | |
ingred | -0.040 |
Sect | -0.038 |
ufact | -0.038 |
� | -0.038 |
Voc | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
ingred | +0.027 |
Sect | +0.027 |
ufact | +0.027 |
� | +0.026 |
Voc | +0.025 |
Neg logit contributions | |
ó | -0.021 |
FB | -0.020 |
alert | -0.020 |
umber | -0.020 |
db | -0.019 |
Token | S |
Token ID | 50 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ingred | +0.021 |
ufact | +0.020 |
Sect | +0.020 |
� | +0.019 |
Voc | +0.019 |
Neg logit contributions | |
ó | -0.021 |
FB | -0.021 |
alert | -0.020 |
umber | -0.020 |
Teddy | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
ingred | +0.100 |
Sect | +0.097 |
ufact | +0.096 |
� | +0.096 |
Voc | +0.093 |
Neg logit contributions | |
ó | -0.079 |
alert | -0.076 |
FB | -0.076 |
umber | -0.075 |
Teddy | -0.075 |
Token | Circuit |
Token ID | 13588 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
ingred | +0.007 |
ufact | +0.006 |
Sect | +0.006 |
� | +0.006 |
Voc | +0.005 |
Neg logit contributions | |
ó | -0.040 |
alert | -0.039 |
FB | -0.039 |
umber | -0.039 |
db | -0.039 |
Token | Court |
Token ID | 3078 |
Feature activation | +7.07e-02 |
Pos logit contributions | |
ingred | +0.387 |
Sect | +0.379 |
� | +0.371 |
ufact | +0.371 |
Voc | +0.359 |
Neg logit contributions | |
ó | -0.403 |
alert | -0.387 |
FB | -0.386 |
umber | -0.382 |
db | -0.380 |
Token | of |
Token ID | 286 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
ingred | +0.056 |
Sect | +0.055 |
� | +0.054 |
ufact | +0.053 |
Voc | +0.052 |
Neg logit contributions | |
ó | -0.051 |
alert | -0.049 |
FB | -0.049 |
umber | -0.048 |
Teddy | -0.048 |
Token | Appeal |
Token ID | 31876 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ingred | +0.020 |
Sect | +0.019 |
� | +0.019 |
ufact | +0.018 |
Voc | +0.018 |
Neg logit contributions | |
ó | -0.033 |
alert | -0.032 |
FB | -0.032 |
umber | -0.032 |
Teddy | -0.032 |
Token | 's |
Token ID | 338 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
ingred | +0.151 |
Sect | +0.149 |
� | +0.147 |
ufact | +0.145 |
Voc | +0.142 |
Neg logit contributions | |
ó | -0.126 |
FB | -0.120 |
alert | -0.120 |
umber | -0.119 |
Teddy | -0.118 |
Token | 3 |
Token ID | 513 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
ingred | +0.016 |
Sect | +0.016 |
� | +0.015 |
ufact | +0.015 |
Voc | +0.015 |
Neg logit contributions | |
ó | -0.015 |
alert | -0.015 |
FB | -0.015 |
umber | -0.014 |
Teddy | -0.014 |
Token | on |
Token ID | 319 |
Feature activation | +5.85e-02 |
Pos logit contributions | |
ingred | +0.015 |
Sect | +0.014 |
� | +0.014 |
ufact | +0.014 |
Voc | +0.014 |
Neg logit contributions | |
ó | -0.013 |
FB | -0.012 |
alert | -0.012 |
umber | -0.012 |
Teddy | -0.012 |
Token | - |
Token ID | 12 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
ingred | +0.047 |
Sect | +0.046 |
� | +0.045 |
ufact | +0.045 |
Voc | +0.044 |
Neg logit contributions | |
ó | -0.041 |
alert | -0.040 |
FB | -0.040 |
umber | -0.039 |
Teddy | -0.039 |
Token | track |
Token ID | 11659 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
ingred | +0.008 |
Sect | +0.008 |
� | +0.008 |
ufact | +0.008 |
Voc | +0.007 |
Neg logit contributions | |
ó | -0.012 |
alert | -0.012 |
FB | -0.012 |
umber | -0.012 |
Teddy | -0.011 |
Token | session |
Token ID | 6246 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ingred | +0.135 |
Sect | +0.133 |
� | +0.131 |
ufact | +0.129 |
Voc | +0.127 |
Neg logit contributions | |
ó | -0.127 |
FB | -0.122 |
alert | -0.122 |
umber | -0.121 |
Teddy | -0.120 |
Token | at |
Token ID | 379 |
Feature activation | -5.75e-03 |
Pos logit contributions | |
ingred | +0.119 |
Sect | +0.117 |
� | +0.115 |
ufact | +0.114 |
Voc | +0.112 |
Neg logit contributions | |
ó | -0.098 |
alert | -0.094 |
FB | -0.094 |
umber | -0.093 |
Teddy | -0.093 |
Token | Circuit |
Token ID | 13588 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
ó | +0.004 |
alert | +0.004 |
FB | +0.004 |
umber | +0.004 |
Teddy | +0.004 |
Neg logit contributions | |
ingred | -0.004 |
Sect | -0.004 |
� | -0.004 |
ufact | -0.004 |
Voc | -0.004 |
Token | Paul |
Token ID | 3362 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
ingred | +0.405 |
Sect | +0.399 |
� | +0.392 |
ufact | +0.388 |
Voc | +0.380 |
Neg logit contributions | |
ó | -0.369 |
FB | -0.355 |
alert | -0.355 |
umber | -0.352 |
Teddy | -0.348 |
Token | Ric |
Token ID | 15868 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ingred | +0.216 |
Sect | +0.212 |
� | +0.208 |
ufact | +0.206 |
Voc | +0.202 |
Neg logit contributions | |
ó | -0.209 |
alert | -0.200 |
FB | -0.200 |
umber | -0.199 |
db | -0.197 |
Token | ard |
Token ID | 446 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
ingred | +0.115 |
Sect | +0.114 |
� | +0.112 |
ufact | +0.111 |
Voc | +0.110 |
Neg logit contributions | |
ó | -0.053 |
alert | -0.051 |
FB | -0.050 |
Teddy | -0.049 |
umber | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
ó | +0.163 |
alert | +0.156 |
FB | +0.155 |
umber | +0.154 |
ory | +0.153 |
Neg logit contributions | |
ingred | -0.197 |
Sect | -0.194 |
� | -0.190 |
ufact | -0.189 |
Voc | -0.185 |
Token |
|
Token ID | 198 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
ingred | +0.014 |
Sect | +0.013 |
� | +0.013 |
ufact | +0.013 |
Voc | +0.013 |
Neg logit contributions | |
ó | -0.012 |
alert | -0.011 |
FB | -0.011 |
umber | -0.011 |
Teddy | -0.011 |
Token | at |
Token ID | 379 |
Feature activation | +2.95e-03 |
Pos logit contributions | |
ó | +0.055 |
FB | +0.053 |
alert | +0.053 |
umber | +0.052 |
Teddy | +0.052 |
Neg logit contributions | |
ingred | -0.064 |
Sect | -0.063 |
� | -0.062 |
ufact | -0.061 |
Voc | -0.060 |
Token | Buck |
Token ID | 13452 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ingred | +0.002 |
Sect | +0.002 |
� | +0.002 |
ufact | +0.002 |
Voc | +0.002 |
Neg logit contributions | |
ó | -0.002 |
alert | -0.002 |
FB | -0.002 |
umber | -0.002 |
Teddy | -0.002 |
Token | more |
Token ID | 3549 |
Feature activation | +4.73e-03 |
Pos logit contributions | |
ó | +0.111 |
FB | +0.107 |
alert | +0.107 |
umber | +0.106 |
Teddy | +0.105 |
Neg logit contributions | |
ingred | -0.122 |
Sect | -0.120 |
� | -0.118 |
ufact | -0.117 |
Voc | -0.115 |
Token | Park |
Token ID | 3250 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ingred | +0.003 |
Sect | +0.003 |
� | +0.003 |
ufact | +0.003 |
Voc | +0.003 |
Neg logit contributions | |
ó | -0.004 |
FB | -0.003 |
alert | -0.003 |
umber | -0.003 |
Teddy | -0.003 |
Token | Kart |
Token ID | 32872 |
Feature activation | +6.67e-02 |
Pos logit contributions | |
ó | +0.116 |
FB | +0.112 |
alert | +0.112 |
umber | +0.111 |
Teddy | +0.110 |
Neg logit contributions | |
ingred | -0.127 |
Sect | -0.126 |
� | -0.123 |
ufact | -0.122 |
Voc | -0.120 |
Token | Circuit |
Token ID | 13588 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
ingred | +0.048 |
Sect | +0.047 |
� | +0.046 |
ufact | +0.046 |
Voc | +0.045 |
Neg logit contributions | |
ó | -0.052 |
alert | -0.050 |
FB | -0.050 |
umber | -0.050 |
Teddy | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
ingred | +0.417 |
Sect | +0.414 |
� | +0.407 |
ufact | +0.400 |
Voc | +0.395 |
Neg logit contributions | |
ó | -0.350 |
FB | -0.336 |
alert | -0.335 |
umber | -0.334 |
Teddy | -0.329 |
Token | where |
Token ID | 810 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
ingred | +0.011 |
Sect | +0.011 |
� | +0.011 |
ufact | +0.011 |
Voc | +0.011 |
Neg logit contributions | |
ó | -0.010 |
alert | -0.010 |
FB | -0.010 |
umber | -0.010 |
Teddy | -0.010 |
Token | Hamilton |
Token ID | 11582 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
ingred | +0.084 |
Sect | +0.084 |
� | +0.082 |
ufact | +0.081 |
Voc | +0.080 |
Neg logit contributions | |
ó | -0.055 |
FB | -0.052 |
alert | -0.052 |
umber | -0.052 |
db | -0.051 |
Token | caught |
Token ID | 4978 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
ó | +0.260 |
FB | +0.250 |
alert | +0.250 |
umber | +0.248 |
Teddy | +0.245 |
Neg logit contributions | |
ingred | -0.265 |
Sect | -0.262 |
� | -0.257 |
ufact | -0.254 |
Voc | -0.249 |
Token | the |
Token ID | 262 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
ó | +0.026 |
alert | +0.025 |
FB | +0.025 |
umber | +0.025 |
Teddy | +0.025 |
Neg logit contributions | |
ingred | -0.032 |
Sect | -0.031 |
� | -0.031 |
ufact | -0.031 |
Voc | -0.030 |
Token | wan |
Token ID | 8149 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
ingred | +0.090 |
Sect | +0.089 |
� | +0.087 |
ufact | +0.086 |
Voc | +0.084 |
Neg logit contributions | |
ó | -0.102 |
alert | -0.098 |
FB | -0.098 |
umber | -0.097 |
Teddy | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
ingred | +0.063 |
Sect | +0.062 |
� | +0.061 |
ufact | +0.060 |
Voc | +0.059 |
Neg logit contributions | |
ó | -0.053 |
FB | -0.051 |
alert | -0.051 |
umber | -0.051 |
Teddy | -0.050 |
Token | BJP |
Token ID | 18317 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
ó | +0.016 |
alert | +0.015 |
FB | +0.015 |
umber | +0.015 |
Teddy | +0.015 |
Neg logit contributions | |
ingred | -0.015 |
Sect | -0.015 |
� | -0.015 |
ufact | -0.015 |
Voc | -0.014 |
Token | Raj |
Token ID | 13308 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
ó | +0.047 |
alert | +0.046 |
FB | +0.046 |
umber | +0.045 |
Teddy | +0.045 |
Neg logit contributions | |
ingred | -0.039 |
Sect | -0.038 |
� | -0.037 |
ufact | -0.037 |
Voc | -0.035 |
Token | ya |
Token ID | 3972 |
Feature activation | +2.28e-03 |
Pos logit contributions | |
ingred | +0.172 |
Sect | +0.170 |
� | +0.167 |
ufact | +0.165 |
Voc | +0.162 |
Neg logit contributions | |
ó | -0.159 |
alert | -0.152 |
FB | -0.152 |
umber | -0.151 |
Teddy | -0.150 |
Token | Sabha |
Token ID | 41941 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
ingred | +0.000 |
ufact | +0.000 |
Sect | +0.000 |
� | +0.000 |
Voc | +0.000 |
Neg logit contributions | |
ó | -0.003 |
alert | -0.003 |
Teddy | -0.003 |
FB | -0.003 |
umber | -0.003 |
Token | member |
Token ID | 2888 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
ingred | +0.322 |
Sect | +0.314 |
� | +0.310 |
ufact | +0.309 |
Voc | +0.295 |
Neg logit contributions | |
ó | -0.433 |
alert | -0.421 |
FB | -0.418 |
umber | -0.416 |
Teddy | -0.415 |
Token | from |
Token ID | 422 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
ingred | +0.031 |
Sect | +0.030 |
� | +0.030 |
ufact | +0.030 |
Voc | +0.029 |
Neg logit contributions | |
ó | -0.030 |
alert | -0.029 |
FB | -0.029 |
umber | -0.029 |
Teddy | -0.028 |
Token | Gujarat |
Token ID | 30311 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
ingred | +0.024 |
Sect | +0.023 |
� | +0.023 |
ufact | +0.023 |
Voc | +0.022 |
Neg logit contributions | |
ó | -0.025 |
alert | -0.024 |
FB | -0.024 |
umber | -0.024 |
Teddy | -0.024 |
Token | Shank |
Token ID | 41595 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
ingred | +0.131 |
Sect | +0.128 |
� | +0.126 |
ufact | +0.126 |
Voc | +0.122 |
Neg logit contributions | |
ó | -0.130 |
alert | -0.126 |
FB | -0.125 |
umber | -0.124 |
Teddy | -0.124 |
Token | ar |
Token ID | 283 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
ingred | +0.011 |
Sect | +0.010 |
� | +0.010 |
ufact | +0.010 |
Voc | +0.010 |
Neg logit contributions | |
ó | -0.015 |
alert | -0.015 |
FB | -0.015 |
umber | -0.015 |
db | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
ó | +0.004 |
alert | +0.003 |
FB | +0.003 |
umber | +0.003 |
Teddy | +0.003 |
Neg logit contributions | |
ingred | -0.004 |
Sect | -0.004 |
� | -0.004 |
ufact | -0.004 |
Voc | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -4.93e-03 |
Pos logit contributions | |
ó | +0.013 |
FB | +0.012 |
alert | +0.012 |
umber | +0.012 |
Teddy | +0.012 |
Neg logit contributions | |
ingred | -0.014 |
Sect | -0.014 |
� | -0.014 |
ufact | -0.014 |
Voc | -0.014 |
Token | Dip |
Token ID | 43945 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
ó | +0.003 |
FB | +0.003 |
alert | +0.003 |
umber | +0.003 |
db | +0.003 |
Neg logit contributions | |
ingred | -0.004 |
Sect | -0.004 |
� | -0.004 |
ufact | -0.004 |
Voc | -0.004 |
Token | ut |
Token ID | 315 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
ingred | +0.057 |
Sect | +0.056 |
� | +0.055 |
ufact | +0.054 |
Voc | +0.053 |
Neg logit contributions | |
ó | -0.052 |
alert | -0.049 |
FB | -0.049 |
umber | -0.049 |
Teddy | -0.049 |
Token | aci |
Token ID | 32009 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
ó | +0.016 |
FB | +0.015 |
alert | +0.015 |
umber | +0.015 |
Teddy | +0.015 |
Neg logit contributions | |
ingred | -0.017 |
Sect | -0.017 |
� | -0.017 |
ufact | -0.017 |
Voc | -0.016 |
Token | ó |
Token ID | 10205 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
ó | +0.088 |
FB | +0.085 |
alert | +0.084 |
umber | +0.083 |
Teddy | +0.083 |
Neg logit contributions | |
ingred | -0.135 |
Sect | -0.134 |
� | -0.131 |
ufact | -0.130 |
Voc | -0.128 |
Token | de |
Token ID | 390 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
ó | +0.413 |
alert | +0.395 |
FB | +0.394 |
umber | +0.391 |
Teddy | +0.388 |
Neg logit contributions | |
ingred | -0.454 |
Sect | -0.446 |
� | -0.439 |
ufact | -0.435 |
Voc | -0.424 |
Token | Barcelona |
Token ID | 15142 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
ó | +0.014 |
alert | +0.013 |
FB | +0.013 |
umber | +0.013 |
Teddy | +0.013 |
Neg logit contributions | |
ingred | -0.013 |
Sect | -0.012 |
� | -0.012 |
ufact | -0.012 |
Voc | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.30e-03 |
Pos logit contributions | |
ó | +0.052 |
FB | +0.050 |
alert | +0.050 |
umber | +0.050 |
Teddy | +0.049 |
Neg logit contributions | |
ingred | -0.062 |
Sect | -0.061 |
� | -0.060 |
ufact | -0.059 |
Voc | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | +1.66e-04 |
Pos logit contributions | |
ó | +0.001 |
alert | +0.001 |
FB | +0.001 |
umber | +0.001 |
Teddy | +0.001 |
Neg logit contributions | |
ingred | -0.001 |
Sect | -0.001 |
� | -0.001 |
ufact | -0.001 |
Voc | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
ingred | +0.000 |
Sect | +0.000 |
� | +0.000 |
ufact | +0.000 |
Voc | +0.000 |
Neg logit contributions | |
ó | -0.000 |
alert | -0.000 |
FB | -0.000 |
umber | -0.000 |
Teddy | -0.000 |
Token | y |
Token ID | 88 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
ó | +0.087 |
alert | +0.083 |
FB | +0.083 |
umber | +0.082 |
Teddy | +0.082 |
Neg logit contributions | |
ingred | -0.094 |
Sect | -0.093 |
� | -0.091 |
ufact | -0.090 |
Voc | -0.089 |
Token | Animation |
Token ID | 23535 |
Feature activation | -2.07e-03 |
Pos logit contributions | |
ó | +0.204 |
FB | +0.196 |
alert | +0.196 |
umber | +0.195 |
Teddy | +0.193 |
Neg logit contributions | |
ingred | -0.225 |
Sect | -0.222 |
� | -0.218 |
ufact | -0.216 |
Voc | -0.211 |
Token | of |
Token ID | 286 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
ó | +0.002 |
FB | +0.001 |
alert | +0.001 |
umber | +0.001 |
Teddy | +0.001 |
Neg logit contributions | |
ingred | -0.002 |
Sect | -0.002 |
� | -0.002 |
ufact | -0.002 |
Voc | -0.002 |
Token | tra |
Token ID | 9535 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
ó | +0.012 |
FB | +0.011 |
alert | +0.011 |
umber | +0.011 |
Teddy | +0.011 |
Neg logit contributions | |
ingred | -0.013 |
Sect | -0.013 |
� | -0.013 |
ufact | -0.013 |
Voc | -0.013 |
Token | ject |
Token ID | 752 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
ingred | +0.039 |
Sect | +0.039 |
� | +0.038 |
ufact | +0.038 |
Voc | +0.037 |
Neg logit contributions | |
ó | -0.039 |
FB | -0.038 |
alert | -0.038 |
umber | -0.038 |
db | -0.037 |
Token | ory |
Token ID | 652 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
ó | +0.010 |
alert | +0.008 |
FB | +0.007 |
umber | +0.007 |
Teddy | +0.006 |
Neg logit contributions | |
ingred | -0.110 |
Sect | -0.109 |
� | -0.108 |
ufact | -0.107 |
Voc | -0.106 |
Token | from |
Token ID | 422 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
ó | +0.400 |
alert | +0.383 |
FB | +0.383 |
umber | +0.380 |
Teddy | +0.376 |
Neg logit contributions | |
ingred | -0.451 |
Sect | -0.444 |
� | -0.436 |
ufact | -0.432 |
Voc | -0.422 |
Token | 24 |
Token ID | 1987 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ingred | +0.010 |
Sect | +0.010 |
� | +0.009 |
ufact | +0.009 |
Voc | +0.009 |
Neg logit contributions | |
ó | -0.009 |
alert | -0.008 |
FB | -0.008 |
umber | -0.008 |
Teddy | -0.008 |
Token | October |
Token ID | 3267 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
ó | +0.069 |
alert | +0.066 |
FB | +0.066 |
umber | +0.065 |
Teddy | +0.065 |
Neg logit contributions | |
ingred | -0.083 |
Sect | -0.082 |
� | -0.080 |
ufact | -0.080 |
Voc | -0.078 |
Token | 1998 |
Token ID | 7795 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
ó | +0.110 |
FB | +0.105 |
alert | +0.105 |
umber | +0.105 |
Teddy | +0.103 |
Neg logit contributions | |
ingred | -0.129 |
Sect | -0.128 |
� | -0.126 |
ufact | -0.124 |
Voc | -0.122 |
Token | to |
Token ID | 284 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
ó | +0.009 |
alert | +0.008 |
FB | +0.008 |
umber | +0.008 |
Teddy | +0.008 |
Neg logit contributions | |
ingred | -0.010 |
Sect | -0.010 |
� | -0.010 |
ufact | -0.009 |
Voc | -0.009 |
Token | Cook |
Token ID | 8261 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
ó | +0.017 |
FB | +0.016 |
alert | +0.016 |
umber | +0.016 |
db | +0.016 |
Neg logit contributions | |
ingred | -0.020 |
Sect | -0.020 |
� | -0.020 |
ufact | -0.019 |
Voc | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
ingred | +0.058 |
Sect | +0.057 |
� | +0.056 |
ufact | +0.055 |
Voc | +0.054 |
Neg logit contributions | |
ó | -0.048 |
FB | -0.046 |
alert | -0.046 |
umber | -0.045 |
Teddy | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
ó | +0.013 |
alert | +0.012 |
FB | +0.012 |
umber | +0.012 |
db | +0.012 |
Neg logit contributions | |
Sect | -0.015 |
ingred | -0.015 |
� | -0.015 |
ufact | -0.015 |
Voc | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
ó | +0.014 |
alert | +0.013 |
FB | +0.013 |
umber | +0.013 |
Teddy | +0.013 |
Neg logit contributions | |
ingred | -0.016 |
Sect | -0.016 |
� | -0.016 |
ufact | -0.016 |
Voc | -0.015 |
Token | Vict |
Token ID | 21944 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ó | +0.014 |
alert | +0.013 |
FB | +0.013 |
umber | +0.013 |
Teddy | +0.013 |
Neg logit contributions | |
ingred | -0.016 |
Sect | -0.016 |
� | -0.016 |
ufact | -0.015 |
Voc | -0.015 |
Token | ory |
Token ID | 652 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
ó | +0.064 |
alert | +0.061 |
FB | +0.061 |
umber | +0.060 |
ory | +0.059 |
Neg logit contributions | |
ingred | -0.118 |
Sect | -0.116 |
� | -0.115 |
ufact | -0.114 |
Voc | -0.112 |
Token | , |
Token ID | 11 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
ó | +0.375 |
FB | +0.358 |
alert | +0.358 |
umber | +0.355 |
Teddy | +0.352 |
Neg logit contributions | |
ingred | -0.461 |
Sect | -0.454 |
� | -0.447 |
ufact | -0.442 |
Voc | -0.434 |
Token | however |
Token ID | 2158 |
Feature activation | +8.67e-02 |
Pos logit contributions | |
ó | +0.012 |
FB | +0.012 |
alert | +0.012 |
umber | +0.012 |
Teddy | +0.011 |
Neg logit contributions | |
ingred | -0.013 |
Sect | -0.012 |
� | -0.012 |
ufact | -0.012 |
Voc | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
ingred | +0.071 |
Sect | +0.070 |
� | +0.069 |
ufact | +0.067 |
Voc | +0.066 |
Neg logit contributions | |
ó | -0.060 |
FB | -0.057 |
alert | -0.057 |
umber | -0.057 |
db | -0.056 |
Token | would |
Token ID | 561 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
ó | +0.016 |
FB | +0.015 |
alert | +0.015 |
umber | +0.015 |
Teddy | +0.015 |
Neg logit contributions | |
ingred | -0.016 |
Sect | -0.016 |
� | -0.015 |
ufact | -0.015 |
Voc | -0.015 |
Token | put |
Token ID | 1234 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ó | +0.049 |
FB | +0.047 |
umber | +0.047 |
alert | +0.047 |
Teddy | +0.046 |
Neg logit contributions | |
ingred | -0.055 |
Sect | -0.055 |
� | -0.054 |
ufact | -0.053 |
Voc | -0.052 |
Token | ojure |
Token ID | 32511 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ingred | +0.043 |
Sect | +0.042 |
� | +0.042 |
ufact | +0.041 |
Voc | +0.040 |
Neg logit contributions | |
ó | -0.064 |
alert | -0.063 |
FB | -0.063 |
umber | -0.062 |
Teddy | -0.062 |
Token | / |
Token ID | 1220 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
ingred | +0.127 |
Sect | +0.126 |
� | +0.124 |
ufact | +0.121 |
Voc | +0.119 |
Neg logit contributions | |
ó | -0.125 |
FB | -0.120 |
alert | -0.120 |
umber | -0.119 |
Teddy | -0.118 |
Token | java |
Token ID | 20129 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
ingred | +0.009 |
Sect | +0.009 |
� | +0.009 |
ufact | +0.008 |
Voc | +0.008 |
Neg logit contributions | |
ó | -0.009 |
FB | -0.009 |
alert | -0.009 |
umber | -0.009 |
Teddy | -0.009 |
Token | . |
Token ID | 764 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
ingred | +0.139 |
Sect | +0.137 |
� | +0.135 |
ufact | +0.133 |
Voc | +0.130 |
Neg logit contributions | |
ó | -0.120 |
FB | -0.115 |
alert | -0.114 |
umber | -0.114 |
Teddy | -0.112 |
Token | j |
Token ID | 474 |
Feature activation | +7.48e-04 |
Pos logit contributions | |
ó | +0.054 |
alert | +0.052 |
FB | +0.052 |
umber | +0.052 |
db | +0.051 |
Neg logit contributions | |
ingred | -0.042 |
Sect | -0.041 |
� | -0.040 |
ufact | -0.040 |
Voc | -0.039 |
Token | db |
Token ID | 9945 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
ingred | +0.001 |
Sect | +0.001 |
ufact | +0.001 |
� | +0.001 |
Voc | +0.000 |
Neg logit contributions | |
ó | -0.001 |
umber | -0.001 |
alert | -0.001 |
db | -0.001 |
FB | -0.001 |
Token | c |
Token ID | 66 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ó | +0.443 |
FB | +0.429 |
umber | +0.426 |
db | +0.426 |
alert | +0.426 |
Neg logit contributions | |
ingred | -0.394 |
Sect | -0.381 |
ufact | -0.373 |
� | -0.371 |
Voc | -0.361 |
Token | | |
Token ID | 930 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ingred | +0.074 |
Sect | +0.073 |
� | +0.071 |
ufact | +0.071 |
Voc | +0.069 |
Neg logit contributions | |
ó | -0.082 |
FB | -0.079 |
alert | -0.079 |
umber | -0.079 |
Teddy | -0.078 |
Token | 10 |
Token ID | 838 |
Feature activation | -3.06e-03 |
Pos logit contributions | |
ingred | +0.082 |
Sect | +0.080 |
ufact | +0.078 |
� | +0.078 |
Voc | +0.076 |
Neg logit contributions | |
ó | -0.093 |
alert | -0.090 |
FB | -0.090 |
umber | -0.089 |
Teddy | -0.089 |
Token | 64 |
Token ID | 2414 |
Feature activation | -6.03e-02 |
Pos logit contributions | |
ó | +0.002 |
alert | +0.002 |
FB | +0.002 |
umber | +0.002 |
Teddy | +0.002 |
Neg logit contributions | |
ingred | -0.003 |
Sect | -0.003 |
� | -0.003 |
ufact | -0.003 |
Voc | -0.003 |
Token | | |
Token ID | 930 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ó | +0.051 |
FB | +0.050 |
alert | +0.049 |
umber | +0.049 |
db | +0.049 |
Neg logit contributions | |
ingred | -0.040 |
Sect | -0.039 |
ufact | -0.038 |
� | -0.038 |
Voc | -0.037 |
Token | him |
Token ID | 683 |
Feature activation | +5.42e-02 |
Pos logit contributions | |
ingred | +0.102 |
Sect | +0.100 |
� | +0.098 |
ufact | +0.097 |
Voc | +0.095 |
Neg logit contributions | |
ó | -0.105 |
FB | -0.101 |
alert | -0.101 |
umber | -0.100 |
Teddy | -0.099 |
Token | some |
Token ID | 617 |
Feature activation | +5.85e-03 |
Pos logit contributions | |
ingred | +0.045 |
Sect | +0.044 |
� | +0.044 |
ufact | +0.043 |
Voc | +0.042 |
Neg logit contributions | |
ó | -0.037 |
alert | -0.035 |
FB | -0.035 |
umber | -0.035 |
Teddy | -0.034 |
Token | not |
Token ID | 407 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
ingred | +0.005 |
Sect | +0.005 |
� | +0.005 |
ufact | +0.004 |
Voc | +0.004 |
Neg logit contributions | |
ó | -0.004 |
FB | -0.004 |
alert | -0.004 |
umber | -0.004 |
Teddy | -0.004 |
Token | so |
Token ID | 523 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
ó | +0.016 |
alert | +0.015 |
FB | +0.015 |
umber | +0.015 |
Teddy | +0.015 |
Neg logit contributions | |
ingred | -0.024 |
Sect | -0.024 |
� | -0.023 |
ufact | -0.023 |
Voc | -0.023 |
Token | sav |
Token ID | 6799 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
ó | +0.188 |
alert | +0.181 |
FB | +0.180 |
Teddy | +0.177 |
umber | +0.177 |
Neg logit contributions | |
ingred | -0.224 |
Sect | -0.220 |
ufact | -0.217 |
� | -0.216 |
Voc | -0.210 |
Token | ory |
Token ID | 652 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
ingred | +0.173 |
Sect | +0.171 |
� | +0.170 |
ufact | +0.169 |
Voc | +0.167 |
Neg logit contributions | |
ó | -0.009 |
FB | -0.006 |
alert | -0.005 |
umber | -0.005 |
Teddy | -0.004 |
Token | words |
Token ID | 2456 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
ó | +0.399 |
alert | +0.383 |
FB | +0.381 |
umber | +0.378 |
Teddy | +0.377 |
Neg logit contributions | |
ingred | -0.424 |
Sect | -0.417 |
� | -0.409 |
ufact | -0.409 |
Voc | -0.396 |
Token | , |
Token ID | 11 |
Feature activation | -9.95e-03 |
Pos logit contributions | |
ingred | +0.068 |
Sect | +0.067 |
� | +0.066 |
ufact | +0.065 |
Voc | +0.064 |
Neg logit contributions | |
ó | -0.055 |
alert | -0.053 |
FB | -0.053 |
umber | -0.052 |
Teddy | -0.052 |
Token | because |
Token ID | 780 |
Feature activation | +8.62e-02 |
Pos logit contributions | |
ó | +0.006 |
FB | +0.006 |
alert | +0.006 |
umber | +0.006 |
Teddy | +0.006 |
Neg logit contributions | |
ingred | -0.008 |
Sect | -0.008 |
� | -0.008 |
ufact | -0.008 |
Voc | -0.008 |
Token | by |
Token ID | 416 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
ingred | +0.067 |
Sect | +0.066 |
� | +0.065 |
ufact | +0.064 |
Voc | +0.063 |
Neg logit contributions | |
ó | -0.062 |
FB | -0.060 |
alert | -0.060 |
umber | -0.059 |
Teddy | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | +4.79e-05 |
Pos logit contributions | |
ingred | +0.049 |
Sect | +0.048 |
� | +0.047 |
ufact | +0.047 |
Voc | +0.046 |
Neg logit contributions | |
ó | -0.043 |
alert | -0.041 |
FB | -0.041 |
umber | -0.041 |
Teddy | -0.041 |
Token | ut |
Token ID | 315 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
ó | +0.057 |
FB | +0.055 |
alert | +0.055 |
umber | +0.054 |
Teddy | +0.054 |
Neg logit contributions | |
ingred | -0.064 |
Sect | -0.063 |
� | -0.062 |
ufact | -0.061 |
Voc | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | -5.18e-03 |
Pos logit contributions | |
ó | +0.019 |
alert | +0.018 |
FB | +0.018 |
umber | +0.018 |
Teddy | +0.018 |
Neg logit contributions | |
ingred | -0.016 |
Sect | -0.016 |
� | -0.016 |
ufact | -0.015 |
Voc | -0.015 |
Token | various |
Token ID | 2972 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
ó | +0.004 |
FB | +0.003 |
alert | +0.003 |
umber | +0.003 |
db | +0.003 |
Neg logit contributions | |
ingred | -0.004 |
Sect | -0.004 |
� | -0.004 |
ufact | -0.004 |
Voc | -0.004 |
Token | h |
Token ID | 289 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
ó | +0.010 |
FB | +0.010 |
alert | +0.010 |
umber | +0.010 |
Teddy | +0.010 |
Neg logit contributions | |
ingred | -0.012 |
Sect | -0.012 |
� | -0.012 |
ufact | -0.012 |
Voc | -0.011 |
Token | ick |
Token ID | 624 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ó | +0.077 |
alert | +0.072 |
FB | +0.072 |
umber | +0.070 |
Teddy | +0.070 |
Neg logit contributions | |
ingred | -0.181 |
Sect | -0.180 |
� | -0.178 |
ufact | -0.176 |
Voc | -0.173 |
Token | ory |
Token ID | 652 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
ó | +0.007 |
alert | +0.002 |
FB | +0.002 |
umber | +0.002 |
Teddy | +0.001 |
Neg logit contributions | |
ingred | -0.212 |
Sect | -0.211 |
� | -0.209 |
ufact | -0.207 |
Voc | -0.205 |
Token | , |
Token ID | 11 |
Feature activation | -3.34e-03 |
Pos logit contributions | |
ó | +0.375 |
alert | +0.360 |
FB | +0.358 |
umber | +0.356 |
Teddy | +0.353 |
Neg logit contributions | |
ingred | -0.446 |
Sect | -0.439 |
� | -0.432 |
ufact | -0.429 |
Voc | -0.419 |
Token | apple |
Token ID | 17180 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
ó | +0.002 |
FB | +0.002 |
alert | +0.002 |
umber | +0.002 |
Teddy | +0.002 |
Neg logit contributions | |
ingred | -0.003 |
Sect | -0.003 |
� | -0.003 |
ufact | -0.003 |
Voc | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -2.85e-03 |
Pos logit contributions | |
ó | +0.047 |
FB | +0.045 |
alert | +0.045 |
umber | +0.045 |
Teddy | +0.044 |
Neg logit contributions | |
ingred | -0.059 |
Sect | -0.058 |
� | -0.057 |
ufact | -0.057 |
Voc | -0.056 |
Token | pear |
Token ID | 25286 |
Feature activation | -9.36e-04 |
Pos logit contributions | |
ó | +0.002 |
FB | +0.002 |
alert | +0.002 |
umber | +0.002 |
Teddy | +0.002 |
Neg logit contributions | |
ingred | -0.002 |
Sect | -0.002 |
� | -0.002 |
ufact | -0.002 |
Voc | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -4.95e-03 |
Pos logit contributions | |
ó | +0.001 |
FB | +0.001 |
alert | +0.001 |
umber | +0.001 |
Teddy | +0.001 |
Neg logit contributions | |
ingred | -0.001 |
Sect | -0.001 |
� | -0.001 |
ufact | -0.001 |
Voc | -0.001 |
Token | forest |
Token ID | 8222 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ó | +0.035 |
alert | +0.034 |
FB | +0.034 |
umber | +0.034 |
Teddy | +0.033 |
Neg logit contributions | |
ingred | -0.042 |
Sect | -0.041 |
� | -0.040 |
ufact | -0.040 |
Voc | -0.039 |
Token | of |
Token ID | 286 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
ó | +0.148 |
alert | +0.142 |
FB | +0.141 |
umber | +0.140 |
Teddy | +0.139 |
Neg logit contributions | |
ingred | -0.177 |
Sect | -0.174 |
� | -0.172 |
ufact | -0.170 |
Voc | -0.166 |
Token | L |
Token ID | 406 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ingred | +0.024 |
Sect | +0.024 |
� | +0.023 |
ufact | +0.023 |
Voc | +0.023 |
Neg logit contributions | |
ó | -0.021 |
FB | -0.020 |
alert | -0.020 |
umber | -0.020 |
db | -0.019 |
Token | oth |
Token ID | 849 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
ingred | +0.107 |
Sect | +0.107 |
� | +0.105 |
ufact | +0.104 |
Voc | +0.103 |
Neg logit contributions | |
ó | -0.049 |
alert | -0.048 |
FB | -0.048 |
Teddy | -0.047 |
Barney | -0.046 |
Token | l |
Token ID | 75 |
Feature activation | +9.70e-02 |
Pos logit contributions | |
ó | +0.244 |
FB | +0.236 |
alert | +0.236 |
umber | +0.234 |
Teddy | +0.232 |
Neg logit contributions | |
ingred | -0.226 |
Sect | -0.223 |
� | -0.219 |
ufact | -0.216 |
Voc | -0.211 |
Token | ó |
Token ID | 10205 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
ingred | +0.142 |
Sect | +0.141 |
� | +0.140 |
ufact | +0.139 |
Voc | +0.137 |
Neg logit contributions | |
FB | -0.001 |
alert | -0.001 |
ó | -0.001 |
Teddy | +0.000 |
Barney | +0.001 |
Token | rien |
Token ID | 15355 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
ó | +0.319 |
FB | +0.299 |
alert | +0.299 |
umber | +0.297 |
db | +0.295 |
Neg logit contributions | |
ingred | -0.507 |
Sect | -0.497 |
� | -0.490 |
ufact | -0.488 |
Voc | -0.477 |
Token | , |
Token ID | 11 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
ó | +0.063 |
alert | +0.060 |
FB | +0.060 |
umber | +0.059 |
Teddy | +0.059 |
Neg logit contributions | |
ingred | -0.077 |
Sect | -0.075 |
� | -0.074 |
ufact | -0.074 |
Voc | -0.072 |
Token | where |
Token ID | 810 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
ingred | +0.018 |
Sect | +0.018 |
� | +0.018 |
ufact | +0.017 |
Voc | +0.017 |
Neg logit contributions | |
ó | -0.018 |
alert | -0.018 |
FB | -0.018 |
umber | -0.017 |
Teddy | -0.017 |
Token | they |
Token ID | 484 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ingred | +0.085 |
Sect | +0.084 |
� | +0.082 |
ufact | +0.081 |
Voc | +0.080 |
Neg logit contributions | |
ó | -0.084 |
FB | -0.081 |
alert | -0.081 |
umber | -0.081 |
db | -0.080 |
Token | are |
Token ID | 389 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
ingred | +0.082 |
Sect | +0.081 |
� | +0.080 |
ufact | +0.078 |
Voc | +0.077 |
Neg logit contributions | |
ó | -0.072 |
FB | -0.070 |
umber | -0.068 |
alert | -0.068 |
db | -0.067 |
Token |
|
Token ID | 198 |
Feature activation | -3.13e-03 |
Pos logit contributions | |
ó | +0.004 |
alert | +0.004 |
FB | +0.004 |
umber | +0.004 |
db | +0.004 |
Neg logit contributions | |
ingred | -0.005 |
Sect | -0.005 |
� | -0.005 |
ufact | -0.005 |
Voc | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -4.21e-03 |
Pos logit contributions | |
ó | +0.002 |
alert | +0.002 |
FB | +0.002 |
umber | +0.002 |
Teddy | +0.002 |
Neg logit contributions | |
ingred | -0.003 |
Sect | -0.002 |
� | -0.002 |
ufact | -0.002 |
Voc | -0.002 |
Token | At |
Token ID | 2953 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
ó | +0.003 |
alert | +0.003 |
FB | +0.003 |
umber | +0.003 |
Teddy | +0.003 |
Neg logit contributions | |
ingred | -0.003 |
Sect | -0.003 |
� | -0.003 |
ufact | -0.003 |
Voc | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
ingred | +0.022 |
Sect | +0.022 |
� | +0.021 |
ufact | +0.021 |
Voc | +0.021 |
Neg logit contributions | |
ó | -0.019 |
FB | -0.018 |
alert | -0.018 |
umber | -0.018 |
Teddy | -0.018 |
Token | curs |
Token ID | 13882 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ingred | +0.015 |
Sect | +0.015 |
� | +0.015 |
ufact | +0.015 |
Voc | +0.015 |
Neg logit contributions | |
ó | -0.013 |
alert | -0.013 |
FB | -0.013 |
umber | -0.013 |
Teddy | -0.013 |
Token | ory |
Token ID | 652 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
ingred | +0.185 |
Sect | +0.184 |
� | +0.183 |
ufact | +0.181 |
Voc | +0.180 |
Neg logit contributions | |
ó | -0.007 |
FB | -0.004 |
alert | -0.004 |
umber | -0.003 |
Teddy | -0.002 |
Token | glance |
Token ID | 16086 |
Feature activation | -3.01e-03 |
Pos logit contributions | |
ó | +0.389 |
alert | +0.375 |
FB | +0.373 |
umber | +0.370 |
Teddy | +0.367 |
Neg logit contributions | |
ingred | -0.429 |
Sect | -0.422 |
� | -0.414 |
ufact | -0.412 |
Voc | -0.401 |
Token | , |
Token ID | 11 |
Feature activation | -9.80e-03 |
Pos logit contributions | |
ó | +0.002 |
FB | +0.002 |
alert | +0.002 |
umber | +0.002 |
db | +0.002 |
Neg logit contributions | |
ingred | -0.002 |
Sect | -0.002 |
� | -0.002 |
ufact | -0.002 |
Voc | -0.002 |
Token | this |
Token ID | 428 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
ó | +0.007 |
FB | +0.006 |
alert | +0.006 |
umber | +0.006 |
Teddy | +0.006 |
Neg logit contributions | |
ingred | -0.008 |
Sect | -0.008 |
� | -0.008 |
ufact | -0.008 |
Voc | -0.008 |
Token | makes |
Token ID | 1838 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
ó | +0.008 |
FB | +0.008 |
umber | +0.008 |
alert | +0.008 |
db | +0.008 |
Neg logit contributions | |
ingred | -0.009 |
Sect | -0.009 |
� | -0.009 |
ufact | -0.009 |
Voc | -0.009 |
Token | perfect |
Token ID | 2818 |
Feature activation | +7.63e-02 |
Pos logit contributions | |
ó | +0.038 |
FB | +0.036 |
alert | +0.036 |
umber | +0.036 |
db | +0.035 |
Neg logit contributions | |
ingred | -0.042 |
Sect | -0.041 |
� | -0.041 |
ufact | -0.040 |
Voc | -0.039 |
Token | me |
Token ID | 502 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ó | +0.004 |
FB | +0.004 |
alert | +0.004 |
umber | +0.004 |
Teddy | +0.004 |
Neg logit contributions | |
ingred | -0.004 |
Sect | -0.004 |
� | -0.004 |
ufact | -0.004 |
Voc | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
ingred | +0.082 |
Sect | +0.081 |
� | +0.080 |
ufact | +0.079 |
Voc | +0.077 |
Neg logit contributions | |
ó | -0.068 |
FB | -0.066 |
alert | -0.065 |
umber | -0.065 |
db | -0.064 |
Token | sterile |
Token ID | 38697 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
ingred | +0.019 |
Sect | +0.018 |
� | +0.018 |
ufact | +0.018 |
Voc | +0.018 |
Neg logit contributions | |
ó | -0.017 |
FB | -0.016 |
alert | -0.016 |
umber | -0.016 |
Teddy | -0.016 |
Token | prom |
Token ID | 1552 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
ó | +0.038 |
FB | +0.037 |
alert | +0.037 |
umber | +0.036 |
Teddy | +0.036 |
Neg logit contributions | |
ingred | -0.042 |
Sect | -0.041 |
� | -0.040 |
ufact | -0.040 |
Voc | -0.039 |
Token | ont |
Token ID | 756 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ingred | +0.078 |
Sect | +0.077 |
� | +0.076 |
ufact | +0.075 |
Voc | +0.074 |
Neg logit contributions | |
ó | -0.059 |
FB | -0.057 |
alert | -0.057 |
umber | -0.056 |
Teddy | -0.056 |
Token | ory |
Token ID | 652 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
ó | +0.004 |
ory | +0.000 |
alert | -0.000 |
umber | -0.000 |
FB | -0.000 |
Neg logit contributions | |
ingred | -0.173 |
Sect | -0.172 |
� | -0.170 |
ufact | -0.169 |
Voc | -0.167 |
Token | ; |
Token ID | 26 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
ó | +0.361 |
alert | +0.346 |
FB | +0.345 |
umber | +0.342 |
Teddy | +0.339 |
Neg logit contributions | |
ingred | -0.451 |
Sect | -0.445 |
� | -0.437 |
ufact | -0.433 |
Voc | -0.425 |
Token |
|
Token ID | 198 |
Feature activation | -3.10e-03 |
Pos logit contributions | |
ó | +0.071 |
FB | +0.068 |
alert | +0.068 |
umber | +0.068 |
Teddy | +0.067 |
Neg logit contributions | |
ingred | -0.083 |
Sect | -0.082 |
� | -0.080 |
ufact | -0.079 |
Voc | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | -5.13e-03 |
Pos logit contributions | |
ó | +0.002 |
FB | +0.002 |
alert | +0.002 |
umber | +0.002 |
Teddy | +0.002 |
Neg logit contributions | |
ingred | -0.002 |
Sect | -0.002 |
� | -0.002 |
ufact | -0.002 |
Voc | -0.002 |
Token | this |
Token ID | 5661 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
ó | +0.004 |
alert | +0.004 |
FB | +0.004 |
umber | +0.004 |
Teddy | +0.004 |
Neg logit contributions | |
ingred | -0.004 |
Sect | -0.004 |
� | -0.004 |
ufact | -0.004 |
Voc | -0.004 |
Token | most |
Token ID | 749 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
ingred | +0.081 |
Sect | +0.080 |
� | +0.078 |
ufact | +0.077 |
Voc | +0.076 |
Neg logit contributions | |
ó | -0.070 |
FB | -0.067 |
alert | -0.067 |
umber | -0.066 |
Teddy | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
ó | +0.076 |
FB | +0.073 |
alert | +0.073 |
umber | +0.072 |
Teddy | +0.071 |
Neg logit contributions | |
ingred | -0.090 |
Sect | -0.089 |
� | -0.087 |
ufact | -0.086 |
Voc | -0.085 |
Token | as |
Token ID | 355 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
ó | +0.010 |
FB | +0.010 |
alert | +0.010 |
umber | +0.010 |
Teddy | +0.009 |
Neg logit contributions | |
ingred | -0.010 |
Sect | -0.010 |
� | -0.010 |
ufact | -0.010 |
Voc | -0.010 |
Token | happened |
Token ID | 3022 |
Feature activation | -2.34e-03 |
Pos logit contributions | |
ingred | +0.035 |
Sect | +0.034 |
� | +0.034 |
ufact | +0.033 |
Voc | +0.033 |
Neg logit contributions | |
ó | -0.028 |
FB | -0.027 |
umber | -0.027 |
alert | -0.027 |
Teddy | -0.026 |
Token | around |
Token ID | 1088 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
ó | +0.002 |
FB | +0.002 |
alert | +0.002 |
umber | +0.002 |
Teddy | +0.001 |
Neg logit contributions | |
ingred | -0.002 |
Sect | -0.002 |
� | -0.002 |
ufact | -0.002 |
Voc | -0.002 |
Token | Chern |
Token ID | 37243 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
ingred | +0.017 |
Sect | +0.017 |
� | +0.017 |
ufact | +0.017 |
Voc | +0.016 |
Neg logit contributions | |
ó | -0.009 |
FB | -0.009 |
alert | -0.009 |
umber | -0.008 |
db | -0.008 |
Token | obyl |
Token ID | 46666 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
ó | +0.025 |
FB | +0.023 |
alert | +0.022 |
Teddy | +0.020 |
Barney | +0.020 |
Neg logit contributions | |
Sect | -0.270 |
ingred | -0.269 |
� | -0.268 |
ufact | -0.265 |
Voc | -0.263 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
ó | +0.367 |
FB | +0.351 |
alert | +0.351 |
umber | +0.348 |
Teddy | +0.345 |
Neg logit contributions | |
ingred | -0.443 |
Sect | -0.437 |
� | -0.430 |
ufact | -0.425 |
Voc | -0.417 |
Token | P |
Token ID | 350 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
ó | +0.008 |
FB | +0.008 |
alert | +0.008 |
umber | +0.008 |
ory | +0.008 |
Neg logit contributions | |
ingred | -0.009 |
Sect | -0.009 |
� | -0.009 |
ufact | -0.009 |
Voc | -0.009 |
Token | fl |
Token ID | 2704 |
Feature activation | +9.42e-02 |
Pos logit contributions | |
ó | +0.064 |
alert | +0.061 |
FB | +0.061 |
umber | +0.061 |
Teddy | +0.061 |
Neg logit contributions | |
ingred | -0.056 |
Sect | -0.055 |
� | -0.054 |
ufact | -0.054 |
Voc | -0.052 |
Token | ug |
Token ID | 1018 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ingred | +0.082 |
Sect | +0.082 |
� | +0.081 |
ufact | +0.080 |
Voc | +0.079 |
Neg logit contributions | |
ó | -0.057 |
FB | -0.055 |
alert | -0.055 |
Teddy | -0.054 |
umber | -0.054 |
Token | be |
Token ID | 1350 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
ó | +0.084 |
alert | +0.081 |
FB | +0.081 |
umber | +0.080 |
Teddy | +0.080 |
Neg logit contributions | |
ingred | -0.098 |
Sect | -0.098 |
� | -0.097 |
ufact | -0.095 |
Voc | -0.094 |
Token | to |
Token ID | 284 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
ó | +0.064 |
alert | +0.061 |
FB | +0.061 |
umber | +0.060 |
Teddy | +0.060 |
Neg logit contributions | |
ingred | -0.074 |
Sect | -0.073 |
� | -0.071 |
ufact | -0.071 |
Voc | -0.069 |
Token | invest |
Token ID | 1325 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ó | +0.014 |
FB | +0.013 |
alert | +0.013 |
umber | +0.013 |
Teddy | +0.013 |
Neg logit contributions | |
ingred | -0.013 |
Sect | -0.012 |
� | -0.012 |
ufact | -0.012 |
Voc | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
ingred | +0.103 |
Sect | +0.102 |
� | +0.100 |
ufact | +0.098 |
Voc | +0.097 |
Neg logit contributions | |
ó | -0.093 |
FB | -0.090 |
alert | -0.089 |
umber | -0.089 |
Barney | -0.088 |
Token | the |
Token ID | 262 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
ó | +0.025 |
FB | +0.024 |
alert | +0.024 |
umber | +0.024 |
Teddy | +0.023 |
Neg logit contributions | |
ingred | -0.027 |
Sect | -0.026 |
� | -0.026 |
ufact | -0.026 |
Voc | -0.025 |
Token | government |
Token ID | 1230 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
ó | +0.015 |
FB | +0.014 |
alert | +0.014 |
umber | +0.014 |
db | +0.014 |
Neg logit contributions | |
ingred | -0.016 |
Sect | -0.015 |
� | -0.015 |
ufact | -0.015 |
Voc | -0.015 |
Token | bonds |
Token ID | 13100 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
ingred | +0.033 |
Sect | +0.033 |
� | +0.032 |
ufact | +0.032 |
Voc | +0.031 |
Neg logit contributions | |
ó | -0.026 |
FB | -0.025 |
alert | -0.025 |
umber | -0.025 |
Teddy | -0.025 |
Token | of |
Token ID | 286 |
Feature activation | -9.79e-03 |
Pos logit contributions | |
ó | +0.383 |
alert | +0.368 |
FB | +0.366 |
umber | +0.362 |
Teddy | +0.360 |
Neg logit contributions | |
ingred | -0.429 |
Sect | -0.419 |
ufact | -0.412 |
� | -0.411 |
Voc | -0.401 |
Token | those |
Token ID | 883 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
ó | +0.007 |
FB | +0.007 |
alert | +0.007 |
umber | +0.006 |
Teddy | +0.006 |
Neg logit contributions | |
ingred | -0.008 |
Sect | -0.008 |
� | -0.008 |
ufact | -0.008 |
Voc | -0.007 |
Token | countries |
Token ID | 2678 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ó | +0.033 |
FB | +0.032 |
alert | +0.032 |
umber | +0.032 |
Teddy | +0.031 |
Neg logit contributions | |
ingred | -0.026 |
Sect | -0.025 |
� | -0.025 |
ufact | -0.024 |
Voc | -0.024 |
Token | are |
Token ID | 389 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
ingred | +0.085 |
Sect | +0.083 |
� | +0.082 |
ufact | +0.081 |
Voc | +0.079 |
Neg logit contributions | |
ó | -0.070 |
alert | -0.067 |
FB | -0.067 |
umber | -0.066 |
Teddy | -0.066 |
Token | always |
Token ID | 1464 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
ó | +0.052 |
FB | +0.050 |
alert | +0.050 |
umber | +0.050 |
Teddy | +0.049 |
Neg logit contributions | |
ingred | -0.053 |
Sect | -0.052 |
� | -0.051 |
ufact | -0.050 |
Voc | -0.049 |
Token | Enlightenment |
Token ID | 39057 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
ó | +0.107 |
alert | +0.102 |
umber | +0.101 |
FB | +0.101 |
ory | +0.101 |
Neg logit contributions | |
ingred | -0.120 |
Sect | -0.117 |
� | -0.115 |
ufact | -0.115 |
Voc | -0.112 |
Token | � |
Token ID | 447 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
ó | +0.136 |
FB | +0.131 |
alert | +0.130 |
umber | +0.129 |
Teddy | +0.128 |
Neg logit contributions | |
ingred | -0.166 |
Sect | -0.165 |
� | -0.162 |
ufact | -0.160 |
Voc | -0.157 |
Token | � |
Token ID | 251 |
Feature activation | +5.00e-03 |
Pos logit contributions | |
ó | +0.012 |
alert | +0.012 |
FB | +0.012 |
umber | +0.011 |
Teddy | +0.011 |
Neg logit contributions | |
ingred | -0.010 |
Sect | -0.010 |
� | -0.010 |
ufact | -0.010 |
Voc | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -6.16e-03 |
Pos logit contributions | |
ingred | +0.004 |
Sect | +0.004 |
� | +0.004 |
ufact | +0.004 |
Voc | +0.004 |
Neg logit contributions | |
ó | -0.003 |
FB | -0.003 |
alert | -0.003 |
umber | -0.003 |
Teddy | -0.003 |
Token | alleg |
Token ID | 2868 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ó | +0.004 |
FB | +0.004 |
alert | +0.004 |
umber | +0.004 |
db | +0.004 |
Neg logit contributions | |
ingred | -0.005 |
Sect | -0.005 |
� | -0.005 |
ufact | -0.005 |
Voc | -0.005 |
Token | ory |
Token ID | 652 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
ó | +0.075 |
FB | +0.069 |
alert | +0.069 |
umber | +0.067 |
Teddy | +0.066 |
Neg logit contributions | |
ingred | -0.305 |
Sect | -0.304 |
� | -0.300 |
ufact | -0.298 |
Voc | -0.294 |
Token | ( |
Token ID | 357 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
ó | +0.362 |
FB | +0.347 |
alert | +0.347 |
umber | +0.344 |
Teddy | +0.340 |
Neg logit contributions | |
ingred | -0.445 |
Sect | -0.439 |
� | -0.432 |
ufact | -0.428 |
Voc | -0.419 |
Token | in |
Token ID | 259 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ó | +0.011 |
FB | +0.010 |
alert | +0.010 |
umber | +0.010 |
Teddy | +0.010 |
Neg logit contributions | |
ingred | -0.009 |
Sect | -0.008 |
� | -0.008 |
ufact | -0.008 |
Voc | -0.008 |
Token | Greek |
Token ID | 8312 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Sect | +0.225 |
ingred | +0.224 |
� | +0.220 |
ufact | +0.217 |
Voc | +0.215 |
Neg logit contributions | |
ó | -0.152 |
FB | -0.146 |
alert | -0.146 |
umber | -0.144 |
db | -0.143 |
Token | h |
Token ID | 289 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ó | +0.173 |
FB | +0.168 |
alert | +0.167 |
umber | +0.165 |
Teddy | +0.164 |
Neg logit contributions | |
ingred | -0.217 |
Sect | -0.215 |
� | -0.211 |
ufact | -0.207 |
Voc | -0.205 |
Token | upon |
Token ID | 27287 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
ó | +0.102 |
alert | +0.100 |
FB | +0.099 |
Teddy | +0.098 |
umber | +0.097 |
Neg logit contributions | |
ingred | -0.147 |
Sect | -0.145 |
� | -0.144 |
ufact | -0.141 |
Voc | -0.139 |
Token | , |
Token ID | 11 |
Feature activation | +6.92e-03 |
Pos logit contributions | |
ó | +0.148 |
FB | +0.142 |
alert | +0.142 |
umber | +0.141 |
Teddy | +0.139 |
Neg logit contributions | |
ingred | -0.183 |
Sect | -0.180 |
� | -0.178 |
ufact | -0.176 |
Voc | -0.172 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
ingred | +0.005 |
Sect | +0.005 |
� | +0.005 |
ufact | +0.005 |
Voc | +0.005 |
Neg logit contributions | |
ó | -0.005 |
FB | -0.005 |
alert | -0.005 |
umber | -0.005 |
Teddy | -0.005 |
Token | even |
Token ID | 772 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
ó | +0.008 |
FB | +0.008 |
alert | +0.008 |
umber | +0.008 |
db | +0.008 |
Neg logit contributions | |
ingred | -0.010 |
Sect | -0.010 |
� | -0.009 |
ufact | -0.009 |
Voc | -0.009 |
Token | then |
Token ID | 788 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
ingred | +0.076 |
Sect | +0.075 |
� | +0.074 |
ufact | +0.073 |
Voc | +0.072 |
Neg logit contributions | |
ó | -0.063 |
FB | -0.060 |
alert | -0.060 |
umber | -0.060 |
db | -0.059 |
Token | alleg |
Token ID | 2868 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
ingred | +0.036 |
Sect | +0.035 |
� | +0.035 |
ufact | +0.034 |
Voc | +0.034 |
Neg logit contributions | |
ó | -0.030 |
FB | -0.029 |
alert | -0.029 |
umber | -0.029 |
db | -0.028 |
Token | ory |
Token ID | 652 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
ó | +0.089 |
FB | +0.085 |
alert | +0.085 |
umber | +0.083 |
Teddy | +0.082 |
Neg logit contributions | |
ingred | -0.282 |
Sect | -0.280 |
� | -0.276 |
ufact | -0.274 |
Voc | -0.270 |
Token | was |
Token ID | 373 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
ó | +0.382 |
alert | +0.366 |
FB | +0.366 |
umber | +0.363 |
Teddy | +0.360 |
Neg logit contributions | |
ingred | -0.426 |
Sect | -0.420 |
� | -0.412 |
ufact | -0.408 |
Voc | -0.400 |
Token | a |
Token ID | 257 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
ingred | +0.008 |
Sect | +0.008 |
� | +0.008 |
ufact | +0.008 |
Voc | +0.008 |
Neg logit contributions | |
ó | -0.008 |
FB | -0.007 |
alert | -0.007 |
umber | -0.007 |
Teddy | -0.007 |
Token | weapon |
Token ID | 4282 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ingred | +0.019 |
Sect | +0.019 |
� | +0.018 |
ufact | +0.018 |
Voc | +0.018 |
Neg logit contributions | |
ó | -0.017 |
FB | -0.016 |
alert | -0.016 |
umber | -0.016 |
Teddy | -0.016 |
Token | in |
Token ID | 287 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
ingred | +0.109 |
Sect | +0.107 |
� | +0.105 |
ufact | +0.104 |
Voc | +0.102 |
Neg logit contributions | |
ó | -0.095 |
FB | -0.092 |
alert | -0.091 |
umber | -0.091 |
Teddy | -0.090 |
Token | a |
Token ID | 257 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
ó | +0.024 |
FB | +0.023 |
alert | +0.023 |
umber | +0.023 |
db | +0.023 |
Neg logit contributions | |
ingred | -0.032 |
Sect | -0.032 |
� | -0.031 |
ufact | -0.031 |
Voc | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -3.76e-03 |
Pos logit contributions | |
ó | +0.002 |
FB | +0.002 |
alert | +0.002 |
umber | +0.002 |
Teddy | +0.002 |
Neg logit contributions | |
ingred | -0.003 |
Sect | -0.003 |
� | -0.003 |
ufact | -0.003 |
Voc | -0.003 |
Token | � |
Token ID | 447 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
ó | +0.003 |
alert | +0.003 |
FB | +0.003 |
umber | +0.002 |
Teddy | +0.002 |
Neg logit contributions | |
ingred | -0.003 |
Sect | -0.003 |
� | -0.003 |
ufact | -0.003 |
Voc | -0.003 |
Token | � |
Token ID | 250 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
ó | +0.012 |
alert | +0.011 |
FB | +0.011 |
umber | +0.011 |
Teddy | +0.011 |
Neg logit contributions | |
ingred | -0.010 |
Sect | -0.009 |
� | -0.009 |
ufact | -0.009 |
Voc | -0.009 |
Token | In |
Token ID | 818 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
ingred | +0.022 |
Sect | +0.022 |
� | +0.022 |
ufact | +0.021 |
Voc | +0.021 |
Neg logit contributions | |
ó | -0.020 |
alert | -0.019 |
FB | -0.019 |
umber | -0.019 |
Teddy | -0.019 |
Token | Chern |
Token ID | 37243 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
ingred | +0.058 |
Sect | +0.058 |
� | +0.056 |
ufact | +0.056 |
Voc | +0.055 |
Neg logit contributions | |
ó | -0.050 |
FB | -0.049 |
alert | -0.048 |
umber | -0.048 |
Teddy | -0.048 |
Token | obyl |
Token ID | 46666 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
ó | +0.024 |
FB | +0.021 |
alert | +0.020 |
Teddy | +0.018 |
umber | +0.018 |
Neg logit contributions | |
Sect | -0.273 |
ingred | -0.273 |
� | -0.271 |
ufact | -0.268 |
Voc | -0.266 |
Token | the |
Token ID | 262 |
Feature activation | -2.20e-03 |
Pos logit contributions | |
ó | +0.362 |
alert | +0.346 |
FB | +0.345 |
umber | +0.343 |
db | +0.339 |
Neg logit contributions | |
ingred | -0.446 |
Sect | -0.440 |
� | -0.432 |
ufact | -0.428 |
Voc | -0.420 |
Token | whole |
Token ID | 2187 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
ó | +0.001 |
FB | +0.001 |
alert | +0.001 |
umber | +0.001 |
Teddy | +0.001 |
Neg logit contributions | |
ingred | -0.002 |
Sect | -0.002 |
� | -0.002 |
ufact | -0.002 |
Voc | -0.002 |
Token | plant |
Token ID | 4618 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
ó | +0.067 |
FB | +0.065 |
alert | +0.064 |
umber | +0.064 |
Teddy | +0.063 |
Neg logit contributions | |
ingred | -0.076 |
Sect | -0.075 |
� | -0.074 |
ufact | -0.073 |
Voc | -0.072 |
Token | core |
Token ID | 4755 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
ingred | +0.021 |
Sect | +0.020 |
� | +0.020 |
ufact | +0.020 |
Voc | +0.019 |
Neg logit contributions | |
ó | -0.019 |
FB | -0.018 |
alert | -0.018 |
umber | -0.018 |
Teddy | -0.018 |
Token | exploded |
Token ID | 18750 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
ó | +0.080 |
FB | +0.077 |
alert | +0.076 |
umber | +0.076 |
Teddy | +0.075 |
Neg logit contributions | |
ingred | -0.088 |
Sect | -0.087 |
� | -0.086 |
ufact | -0.084 |
Voc | -0.083 |
Token | but |
Token ID | 475 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
ó | +0.001 |
FB | +0.001 |
alert | +0.001 |
umber | +0.001 |
Teddy | +0.001 |
Neg logit contributions | |
ingred | -0.001 |
Sect | -0.001 |
� | -0.001 |
ufact | -0.001 |
Voc | -0.001 |
Token | less |
Token ID | 1342 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
ingred | +0.038 |
Sect | +0.038 |
� | +0.037 |
ufact | +0.037 |
Voc | +0.036 |
Neg logit contributions | |
ó | -0.033 |
FB | -0.032 |
alert | -0.032 |
umber | -0.032 |
Teddy | -0.031 |
Token | severe |
Token ID | 6049 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
ó | +0.120 |
FB | +0.115 |
alert | +0.114 |
umber | +0.113 |
Teddy | +0.112 |
Neg logit contributions | |
ingred | -0.178 |
Sect | -0.175 |
� | -0.173 |
ufact | -0.171 |
Voc | -0.168 |
Token | than |
Token ID | 621 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
ó | +0.024 |
FB | +0.023 |
umber | +0.023 |
alert | +0.023 |
Teddy | +0.022 |
Neg logit contributions | |
ingred | -0.029 |
Sect | -0.029 |
� | -0.028 |
ufact | -0.028 |
Voc | -0.027 |
Token | Chern |
Token ID | 37243 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
ó | +0.083 |
FB | +0.080 |
alert | +0.079 |
umber | +0.079 |
Teddy | +0.078 |
Neg logit contributions | |
ingred | -0.101 |
Sect | -0.099 |
� | -0.098 |
ufact | -0.096 |
Voc | -0.095 |
Token | obyl |
Token ID | 46666 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
ó | +0.022 |
FB | +0.018 |
alert | +0.017 |
umber | +0.015 |
Teddy | +0.015 |
Neg logit contributions | |
ingred | -0.265 |
Sect | -0.264 |
� | -0.261 |
ufact | -0.259 |
Voc | -0.257 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-03 |
Pos logit contributions | |
ó | +0.362 |
FB | +0.346 |
alert | +0.346 |
umber | +0.343 |
Teddy | +0.340 |
Neg logit contributions | |
ingred | -0.443 |
Sect | -0.437 |
� | -0.430 |
ufact | -0.425 |
Voc | -0.417 |
Token |
|
Token ID | 198 |
Feature activation | +3.46e-03 |
Pos logit contributions | |
ó | +0.001 |
FB | +0.001 |
alert | +0.001 |
umber | +0.001 |
Teddy | +0.001 |
Neg logit contributions | |
ingred | -0.002 |
Sect | -0.002 |
� | -0.002 |
ufact | -0.002 |
Voc | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +7.73e-03 |
Pos logit contributions | |
ingred | +0.003 |
Sect | +0.003 |
� | +0.003 |
ufact | +0.003 |
Voc | +0.003 |
Neg logit contributions | |
ó | -0.002 |
alert | -0.002 |
FB | -0.002 |
umber | -0.002 |
Teddy | -0.002 |
Token | A |
Token ID | 32 |
Feature activation | -9.71e-02 |
Pos logit contributions | |
ingred | +0.006 |
Sect | +0.006 |
� | +0.006 |
ufact | +0.006 |
Voc | +0.006 |
Neg logit contributions | |
ó | -0.005 |
alert | -0.005 |
FB | -0.005 |
umber | -0.005 |
Teddy | -0.005 |
Token | U |
Token ID | 471 |
Feature activation | -1.06e-04 |
Pos logit contributions | |
ó | +0.067 |
FB | +0.065 |
alert | +0.065 |
umber | +0.064 |
Teddy | +0.064 |
Neg logit contributions | |
ingred | -0.078 |
Sect | -0.077 |
� | -0.076 |
ufact | -0.075 |
Voc | -0.074 |
Token | us |
Token ID | 514 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ó | +0.126 |
alert | +0.121 |
FB | +0.121 |
umber | +0.120 |
ory | +0.119 |
Neg logit contributions | |
ingred | -0.127 |
Sect | -0.124 |
� | -0.122 |
ufact | -0.121 |
Voc | -0.118 |
Token | admit |
Token ID | 9159 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ingred | +0.115 |
Sect | +0.114 |
� | +0.112 |
ufact | +0.110 |
Voc | +0.108 |
Neg logit contributions | |
ó | -0.101 |
FB | -0.097 |
alert | -0.097 |
umber | -0.096 |
Teddy | -0.095 |
Token | that |
Token ID | 326 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
ó | +0.082 |
FB | +0.079 |
alert | +0.079 |
umber | +0.078 |
Teddy | +0.077 |
Neg logit contributions | |
ingred | -0.088 |
Sect | -0.087 |
� | -0.085 |
ufact | -0.084 |
Voc | -0.082 |
Token | the |
Token ID | 262 |
Feature activation | -5.31e-04 |
Pos logit contributions | |
ingred | +0.061 |
Sect | +0.061 |
� | +0.060 |
ufact | +0.059 |
Voc | +0.058 |
Neg logit contributions | |
ó | -0.052 |
alert | -0.050 |
FB | -0.050 |
umber | -0.050 |
Teddy | -0.049 |
Token | transit |
Token ID | 11168 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
ó | +0.000 |
alert | +0.000 |
FB | +0.000 |
umber | +0.000 |
ory | +0.000 |
Neg logit contributions | |
ingred | -0.000 |
Sect | -0.000 |
� | -0.000 |
ufact | -0.000 |
Voc | -0.000 |
Token | ory |
Token ID | 652 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
ó | +0.025 |
FB | +0.019 |
alert | +0.019 |
umber | +0.018 |
Teddy | +0.016 |
Neg logit contributions | |
ingred | -0.302 |
Sect | -0.299 |
� | -0.296 |
ufact | -0.294 |
Voc | -0.291 |
Token | force |
Token ID | 2700 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
ó | +0.378 |
alert | +0.363 |
FB | +0.363 |
umber | +0.360 |
Teddy | +0.356 |
Neg logit contributions | |
ingred | -0.426 |
Sect | -0.420 |
� | -0.413 |
ufact | -0.409 |
Voc | -0.400 |
Token | of |
Token ID | 286 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
ó | +0.068 |
alert | +0.065 |
FB | +0.065 |
umber | +0.065 |
Teddy | +0.064 |
Neg logit contributions | |
ingred | -0.075 |
Sect | -0.074 |
� | -0.072 |
ufact | -0.072 |
Voc | -0.070 |
Token | this |
Token ID | 428 |
Feature activation | +9.66e-05 |
Pos logit contributions | |
ingred | +0.014 |
Sect | +0.014 |
� | +0.014 |
ufact | +0.014 |
Voc | +0.014 |
Neg logit contributions | |
ó | -0.012 |
alert | -0.012 |
FB | -0.012 |
umber | -0.011 |
Teddy | -0.011 |
Token | fren |
Token ID | 22832 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
ingred | +0.000 |
Sect | +0.000 |
� | +0.000 |
ufact | +0.000 |
Voc | +0.000 |
Neg logit contributions | |
ó | -0.000 |
alert | -0.000 |
FB | -0.000 |
umber | -0.000 |
Teddy | -0.000 |
Token | z |
Token ID | 89 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ingred | +0.067 |
Sect | +0.066 |
� | +0.065 |
ufact | +0.065 |
Voc | +0.064 |
Neg logit contributions | |
ó | -0.038 |
alert | -0.036 |
FB | -0.036 |
umber | -0.036 |
Teddy | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
ó | +0.057 |
alert | +0.054 |
FB | +0.054 |
umber | +0.054 |
Teddy | +0.053 |
Neg logit contributions | |
ingred | -0.065 |
Sect | -0.064 |
� | -0.063 |
ufact | -0.062 |
Voc | -0.061 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
ó | +0.008 |
FB | +0.007 |
alert | +0.007 |
umber | +0.007 |
Teddy | +0.007 |
Neg logit contributions | |
ingred | -0.009 |
Sect | -0.009 |
� | -0.009 |
ufact | -0.008 |
Voc | -0.008 |
Token | 1 |
Token ID | 16 |
Feature activation | +6.48e-03 |
Pos logit contributions | |
ó | +0.008 |
alert | +0.007 |
FB | +0.007 |
umber | +0.007 |
Teddy | +0.007 |
Neg logit contributions | |
ingred | -0.008 |
Sect | -0.008 |
� | -0.008 |
ufact | -0.008 |
Voc | -0.008 |
Token | $ |
Token ID | 720 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
ingred | +0.004 |
Sect | +0.004 |
� | +0.004 |
ufact | +0.004 |
Voc | +0.004 |
Neg logit contributions | |
ó | -0.005 |
alert | -0.005 |
FB | -0.005 |
umber | -0.005 |
db | -0.005 |
Token | g |
Token ID | 308 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
ingred | +0.036 |
Sect | +0.035 |
� | +0.035 |
ufact | +0.034 |
Voc | +0.033 |
Neg logit contributions | |
ó | -0.030 |
alert | -0.029 |
FB | -0.029 |
umber | -0.029 |
Teddy | -0.029 |
Token | db |
Token ID | 9945 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
ó | +0.079 |
FB | +0.073 |
alert | +0.072 |
umber | +0.071 |
Teddy | +0.070 |
Neg logit contributions | |
ingred | -0.236 |
Sect | -0.233 |
� | -0.231 |
ufact | -0.229 |
Voc | -0.226 |
Token | -- |
Token ID | 1377 |
Feature activation | -9.87e-02 |
Pos logit contributions | |
ó | +0.343 |
alert | +0.328 |
FB | +0.328 |
umber | +0.325 |
db | +0.323 |
Neg logit contributions | |
ingred | -0.461 |
Sect | -0.455 |
� | -0.445 |
ufact | -0.444 |
Voc | -0.434 |
Token | quiet |
Token ID | 39624 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
ó | +0.071 |
FB | +0.069 |
alert | +0.068 |
umber | +0.068 |
Teddy | +0.067 |
Neg logit contributions | |
ingred | -0.077 |
Sect | -0.076 |
� | -0.075 |
ufact | -0.074 |
Voc | -0.072 |
Token | ./ |
Token ID | 24457 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
ó | +0.152 |
FB | +0.145 |
alert | +0.145 |
umber | +0.144 |
Teddy | +0.143 |
Neg logit contributions | |
ingred | -0.181 |
Sect | -0.179 |
� | -0.176 |
ufact | -0.174 |
Voc | -0.171 |
Token | rop |
Token ID | 1773 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
ó | +0.091 |
alert | +0.087 |
FB | +0.087 |
umber | +0.087 |
Teddy | +0.086 |
Neg logit contributions | |
ingred | -0.107 |
Sect | -0.106 |
� | -0.104 |
ufact | -0.103 |
Voc | -0.101 |
Token | as |
Token ID | 292 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
ó | +0.163 |
alert | +0.156 |
FB | +0.156 |
umber | +0.156 |
db | +0.155 |
Neg logit contributions | |
ingred | -0.168 |
Sect | -0.164 |
� | -0.161 |
ufact | -0.161 |
Voc | -0.157 |
Token | hole |
Token ID | 13207 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ingred | +0.160 |
Sect | +0.158 |
� | +0.156 |
ufact | +0.155 |
Voc | +0.152 |
Neg logit contributions | |
ó | -0.091 |
alert | -0.086 |
FB | -0.086 |
umber | -0.085 |
Teddy | -0.084 |
Token | is |
Token ID | 318 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
ó | +0.085 |
alert | +0.082 |
FB | +0.082 |
umber | +0.081 |
Teddy | +0.081 |
Neg logit contributions | |
ingred | -0.090 |
Sect | -0.089 |
� | -0.087 |
ufact | -0.087 |
Voc | -0.084 |
Token | never |
Token ID | 1239 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
ó | +0.028 |
FB | +0.027 |
alert | +0.026 |
umber | +0.026 |
Teddy | +0.026 |
Neg logit contributions | |
ingred | -0.030 |
Sect | -0.029 |
� | -0.029 |
ufact | -0.029 |
Voc | -0.028 |
Token | off |
Token ID | 572 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
ingred | +0.029 |
Sect | +0.028 |
� | +0.028 |
ufact | +0.027 |
Voc | +0.027 |
Neg logit contributions | |
ó | -0.025 |
FB | -0.024 |
umber | -0.023 |
alert | -0.023 |
db | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +8.53e-03 |
Pos logit contributions | |
ingred | +0.163 |
Sect | +0.161 |
� | +0.158 |
ufact | +0.156 |
Voc | +0.154 |
Neg logit contributions | |
ó | -0.134 |
FB | -0.128 |
alert | -0.127 |
umber | -0.127 |
Teddy | -0.125 |
Token | alert |
Token ID | 7995 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
ingred | +0.007 |
Sect | +0.007 |
� | +0.007 |
ufact | +0.007 |
Voc | +0.007 |
Neg logit contributions | |
ó | -0.006 |
FB | -0.005 |
alert | -0.005 |
umber | -0.005 |
Teddy | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +8.13e-03 |
Pos logit contributions | |
ó | +0.373 |
alert | +0.360 |
FB | +0.357 |
umber | +0.354 |
Teddy | +0.351 |
Neg logit contributions | |
ingred | -0.430 |
Sect | -0.424 |
� | -0.416 |
ufact | -0.414 |
Voc | -0.404 |
Token | He |
Token ID | 679 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
ingred | +0.007 |
Sect | +0.007 |
� | +0.007 |
ufact | +0.007 |
Voc | +0.007 |
Neg logit contributions | |
ó | -0.005 |
FB | -0.005 |
alert | -0.005 |
umber | -0.005 |
Teddy | -0.005 |
Token | doesn |
Token ID | 1595 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
ó | +0.018 |
alert | +0.017 |
FB | +0.017 |
umber | +0.017 |
Teddy | +0.017 |
Neg logit contributions | |
ingred | -0.018 |
Sect | -0.018 |
� | -0.017 |
ufact | -0.017 |
Voc | -0.017 |
Token | 't |
Token ID | 470 |
Feature activation | +8.46e-02 |
Pos logit contributions | |
Sect | +0.048 |
ingred | +0.048 |
� | +0.047 |
ufact | +0.046 |
Voc | +0.046 |
Neg logit contributions | |
ó | -0.055 |
alert | -0.053 |
FB | -0.053 |
umber | -0.053 |
Teddy | -0.052 |
Token | sleep |
Token ID | 3993 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
ingred | +0.065 |
Sect | +0.064 |
� | +0.063 |
ufact | +0.062 |
Voc | +0.061 |
Neg logit contributions | |
ó | -0.062 |
FB | -0.060 |
alert | -0.059 |
umber | -0.059 |
Teddy | -0.058 |
Token | system |
Token ID | 1080 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
ó | +0.071 |
FB | +0.068 |
alert | +0.067 |
umber | +0.067 |
Teddy | +0.066 |
Neg logit contributions | |
ingred | -0.107 |
Sect | -0.105 |
� | -0.104 |
ufact | -0.102 |
Voc | -0.101 |
Token | tone |
Token ID | 8216 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
ó | +0.052 |
FB | +0.050 |
alert | +0.050 |
umber | +0.049 |
Teddy | +0.049 |
Neg logit contributions | |
ingred | -0.065 |
Sect | -0.064 |
� | -0.063 |
ufact | -0.062 |
Voc | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | -2.96e-04 |
Pos logit contributions | |
ó | +0.089 |
FB | +0.085 |
alert | +0.085 |
umber | +0.084 |
Teddy | +0.083 |
Neg logit contributions | |
ingred | -0.107 |
Sect | -0.105 |
� | -0.104 |
ufact | -0.102 |
Voc | -0.100 |
Token | with |
Token ID | 351 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ó | +0.000 |
FB | +0.000 |
umber | +0.000 |
alert | +0.000 |
db | +0.000 |
Neg logit contributions | |
ingred | -0.000 |
Sect | -0.000 |
� | -0.000 |
ufact | -0.000 |
Voc | -0.000 |
Token | higher |
Token ID | 2440 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
ó | +0.078 |
FB | +0.075 |
alert | +0.075 |
umber | +0.074 |
db | +0.074 |
Neg logit contributions | |
ingred | -0.095 |
Sect | -0.094 |
� | -0.093 |
ufact | -0.091 |
Voc | -0.090 |
Token | alert |
Token ID | 7995 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
ingred | +0.065 |
Sect | +0.064 |
� | +0.064 |
Voc | +0.062 |
ufact | +0.062 |
Neg logit contributions | |
ó | -0.042 |
FB | -0.041 |
umber | -0.040 |
db | -0.040 |
Barney | -0.039 |
Token | ness |
Token ID | 1108 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
ó | +0.329 |
FB | +0.316 |
alert | +0.311 |
umber | +0.311 |
db | +0.307 |
Neg logit contributions | |
ingred | -0.471 |
Sect | -0.464 |
� | -0.458 |
ufact | -0.452 |
Voc | -0.445 |
Token | and |
Token ID | 290 |
Feature activation | -6.30e-03 |
Pos logit contributions | |
ó | +0.042 |
FB | +0.041 |
umber | +0.040 |
alert | +0.040 |
db | +0.040 |
Neg logit contributions | |
ingred | -0.048 |
Sect | -0.048 |
� | -0.047 |
ufact | -0.046 |
Voc | -0.046 |
Token | activation |
Token ID | 14916 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
ó | +0.004 |
FB | +0.004 |
umber | +0.004 |
db | +0.004 |
Barney | +0.004 |
Neg logit contributions | |
ingred | -0.005 |
Sect | -0.005 |
� | -0.005 |
ufact | -0.005 |
Voc | -0.005 |
Token | from |
Token ID | 422 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
ó | +0.064 |
FB | +0.062 |
umber | +0.061 |
alert | +0.061 |
Teddy | +0.061 |
Neg logit contributions | |
ingred | -0.074 |
Sect | -0.073 |
� | -0.072 |
ufact | -0.071 |
Voc | -0.070 |
Token | sympathetic |
Token ID | 22335 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ingred | +0.039 |
Sect | +0.038 |
� | +0.038 |
ufact | +0.037 |
Voc | +0.037 |
Neg logit contributions | |
ó | -0.030 |
FB | -0.029 |
umber | -0.029 |
alert | -0.028 |
db | -0.028 |
Token | but |
Token ID | 475 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
ingred | +0.001 |
Sect | +0.001 |
� | +0.001 |
ufact | +0.001 |
Voc | +0.001 |
Neg logit contributions | |
ó | -0.001 |
FB | -0.001 |
alert | -0.001 |
umber | -0.001 |
Teddy | -0.001 |
Token | don |
Token ID | 836 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ingred | +0.041 |
Sect | +0.041 |
� | +0.040 |
ufact | +0.039 |
Voc | +0.039 |
Neg logit contributions | |
ó | -0.037 |
FB | -0.035 |
umber | -0.035 |
alert | -0.035 |
Teddy | -0.035 |
Token | � |
Token ID | 447 |
Feature activation | -5.53e-03 |
Pos logit contributions | |
ingred | +0.009 |
Sect | +0.009 |
� | +0.009 |
ufact | +0.009 |
Voc | +0.009 |
Neg logit contributions | |
ó | -0.008 |
alert | -0.007 |
FB | -0.007 |
umber | -0.007 |
Teddy | -0.007 |
Token | � |
Token ID | 247 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
ó | +0.004 |
FB | +0.004 |
alert | +0.004 |
umber | +0.004 |
db | +0.004 |
Neg logit contributions | |
ingred | -0.004 |
Sect | -0.004 |
� | -0.004 |
ufact | -0.004 |
Voc | -0.004 |
Token | t |
Token ID | 83 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ó | +0.011 |
FB | +0.010 |
alert | +0.010 |
umber | +0.010 |
ory | +0.010 |
Neg logit contributions | |
ingred | -0.012 |
Sect | -0.012 |
� | -0.011 |
ufact | -0.011 |
Voc | -0.011 |
Token | alert |
Token ID | 7995 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
ingred | +0.010 |
Sect | +0.010 |
� | +0.010 |
ufact | +0.009 |
Voc | +0.009 |
Neg logit contributions | |
ó | -0.008 |
FB | -0.008 |
umber | -0.008 |
alert | -0.008 |
Teddy | -0.008 |
Token | on |
Token ID | 319 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
ó | +0.407 |
alert | +0.393 |
FB | +0.390 |
umber | +0.387 |
Teddy | +0.385 |
Neg logit contributions | |
ingred | -0.395 |
Sect | -0.388 |
� | -0.379 |
ufact | -0.378 |
Voc | -0.368 |
Token | a |
Token ID | 257 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
ingred | +0.041 |
Sect | +0.040 |
� | +0.040 |
ufact | +0.039 |
Voc | +0.038 |
Neg logit contributions | |
ó | -0.040 |
alert | -0.038 |
FB | -0.038 |
umber | -0.038 |
Teddy | -0.038 |
Token | file |
Token ID | 2393 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
ingred | +0.030 |
Sect | +0.029 |
� | +0.029 |
ufact | +0.028 |
Voc | +0.028 |
Neg logit contributions | |
ó | -0.026 |
FB | -0.025 |
umber | -0.025 |
alert | -0.025 |
Teddy | -0.025 |
Token | that |
Token ID | 326 |
Feature activation | +8.49e-02 |
Pos logit contributions | |
ó | +0.041 |
FB | +0.040 |
alert | +0.040 |
umber | +0.039 |
Teddy | +0.039 |
Neg logit contributions | |
ingred | -0.043 |
Sect | -0.043 |
� | -0.042 |
ufact | -0.041 |
Voc | -0.040 |
Token | doesn |
Token ID | 1595 |
Feature activation | +7.11e-02 |
Pos logit contributions | |
ingred | +0.066 |
Sect | +0.065 |
� | +0.064 |
ufact | +0.064 |
Voc | +0.062 |
Neg logit contributions | |
ó | -0.061 |
alert | -0.059 |
FB | -0.059 |
umber | -0.058 |
Teddy | -0.058 |
Token | JR |
Token ID | 44817 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
ó | +0.059 |
alert | +0.057 |
FB | +0.056 |
umber | +0.056 |
Teddy | +0.056 |
Neg logit contributions | |
ingred | -0.055 |
Sect | -0.054 |
� | -0.054 |
ufact | -0.053 |
Voc | -0.052 |
Token | � |
Token ID | 8582 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
ingred | +0.188 |
Sect | +0.186 |
� | +0.183 |
ufact | +0.179 |
Voc | +0.176 |
Neg logit contributions | |
ó | -0.200 |
alert | -0.192 |
FB | -0.192 |
umber | -0.191 |
Teddy | -0.189 |
Token | � |
Token ID | 229 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
ingred | +0.035 |
Sect | +0.033 |
� | +0.031 |
ufact | +0.031 |
Voc | +0.028 |
Neg logit contributions | |
ó | -0.177 |
FB | -0.173 |
alert | -0.173 |
umber | -0.172 |
db | -0.171 |
Token | � |
Token ID | 118 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ingred | +0.192 |
Sect | +0.187 |
� | +0.181 |
ufact | +0.178 |
Voc | +0.171 |
Neg logit contributions | |
ó | -0.454 |
FB | -0.441 |
alert | -0.441 |
umber | -0.438 |
db | -0.436 |
Token | � |
Token ID | 8582 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
ingred | +0.220 |
Sect | +0.216 |
� | +0.212 |
ufact | +0.209 |
Voc | +0.204 |
Neg logit contributions | |
ó | -0.274 |
alert | -0.264 |
FB | -0.264 |
umber | -0.263 |
Teddy | -0.260 |
Token | � |
Token ID | 229 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
ingred | +0.034 |
Sect | +0.032 |
ufact | +0.030 |
� | +0.030 |
Voc | +0.027 |
Neg logit contributions | |
ó | -0.178 |
alert | -0.174 |
FB | -0.174 |
umber | -0.173 |
ory | -0.172 |
Token | � |
Token ID | 116 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
ingred | +0.198 |
Sect | +0.192 |
� | +0.186 |
ufact | +0.184 |
Voc | +0.176 |
Neg logit contributions | |
ó | -0.455 |
FB | -0.442 |
alert | -0.441 |
umber | -0.439 |
db | -0.437 |
Token | (@ |
Token ID | 4275 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ingred | +0.212 |
Sect | +0.209 |
� | +0.205 |
ufact | +0.202 |
Voc | +0.198 |
Neg logit contributions | |
ó | -0.243 |
alert | -0.234 |
FB | -0.234 |
umber | -0.233 |
Teddy | -0.231 |
Token | m |
Token ID | 76 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
ingred | +0.109 |
Sect | +0.108 |
� | +0.106 |
ufact | +0.105 |
Voc | +0.103 |
Neg logit contributions | |
ó | -0.097 |
alert | -0.094 |
FB | -0.093 |
umber | -0.092 |
Teddy | -0.092 |
Token | f |
Token ID | 69 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
ó | +0.013 |
alert | +0.012 |
FB | +0.012 |
umber | +0.012 |
Teddy | +0.012 |
Neg logit contributions | |
ingred | -0.012 |
Sect | -0.012 |
� | -0.012 |
ufact | -0.012 |
Voc | -0.012 |
Token | lynn |
Token ID | 12935 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
ó | +0.121 |
alert | +0.116 |
FB | +0.116 |
umber | +0.115 |
Teddy | +0.115 |
Neg logit contributions | |
ingred | -0.117 |
Sect | -0.115 |
� | -0.113 |
ufact | -0.112 |
Voc | -0.109 |
Token | the |
Token ID | 262 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
ingred | +0.056 |
Sect | +0.055 |
� | +0.054 |
ufact | +0.054 |
Voc | +0.053 |
Neg logit contributions | |
ó | -0.046 |
FB | -0.044 |
alert | -0.044 |
umber | -0.044 |
db | -0.043 |
Token | arms |
Token ID | 5101 |
Feature activation | -9.71e-02 |
Pos logit contributions | |
ingred | +0.013 |
Sect | +0.013 |
� | +0.013 |
ufact | +0.013 |
Voc | +0.012 |
Neg logit contributions | |
ó | -0.011 |
FB | -0.011 |
alert | -0.010 |
umber | -0.010 |
Teddy | -0.010 |
Token | trade |
Token ID | 3292 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ó | +0.061 |
alert | +0.059 |
FB | +0.058 |
umber | +0.057 |
ory | +0.057 |
Neg logit contributions | |
ingred | -0.085 |
Sect | -0.084 |
� | -0.082 |
ufact | -0.082 |
Voc | -0.080 |
Token | agreement |
Token ID | 4381 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
ingred | +0.093 |
Sect | +0.092 |
� | +0.091 |
ufact | +0.089 |
Voc | +0.088 |
Neg logit contributions | |
ó | -0.064 |
FB | -0.061 |
umber | -0.061 |
alert | -0.060 |
Teddy | -0.059 |
Token | � |
Token ID | 564 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
ó | +0.198 |
FB | +0.190 |
alert | +0.189 |
umber | +0.189 |
Teddy | +0.186 |
Neg logit contributions | |
ingred | -0.246 |
Sect | -0.244 |
� | -0.242 |
ufact | -0.236 |
Voc | -0.233 |
Token | � |
Token ID | 246 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
ingred | +0.015 |
Sect | +0.015 |
ufact | +0.014 |
� | +0.014 |
Voc | +0.014 |
Neg logit contributions | |
ó | -0.024 |
FB | -0.023 |
alert | -0.023 |
umber | -0.023 |
ory | -0.022 |
Token | would |
Token ID | 19188 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
ingred | +0.245 |
Sect | +0.240 |
� | +0.235 |
ufact | +0.233 |
Voc | +0.227 |
Neg logit contributions | |
ó | -0.295 |
FB | -0.284 |
alert | -0.284 |
umber | -0.282 |
db | -0.280 |
Token | jeopard |
Token ID | 22451 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
ó | +0.008 |
FB | +0.008 |
alert | +0.008 |
umber | +0.008 |
Teddy | +0.008 |
Neg logit contributions | |
ingred | -0.009 |
Sect | -0.009 |
� | -0.009 |
ufact | -0.008 |
Voc | -0.008 |
Token | ise |
Token ID | 786 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
ingred | +0.059 |
Sect | +0.058 |
� | +0.057 |
ufact | +0.056 |
Voc | +0.055 |
Neg logit contributions | |
ó | -0.056 |
FB | -0.054 |
alert | -0.054 |
umber | -0.053 |
Teddy | -0.053 |
Token | Sweden |
Token ID | 10710 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
ingred | +0.024 |
Sect | +0.023 |
� | +0.023 |
ufact | +0.023 |
Voc | +0.022 |
Neg logit contributions | |
ó | -0.018 |
FB | -0.018 |
alert | -0.018 |
umber | -0.017 |
Teddy | -0.017 |
Token | � |
Token ID | 447 |
Feature activation | +1.49e-03 |
Pos logit contributions | |
ingred | +0.028 |
Sect | +0.027 |
� | +0.027 |
ufact | +0.027 |
Voc | +0.026 |
Neg logit contributions | |
ó | -0.024 |
alert | -0.023 |
FB | -0.023 |
umber | -0.023 |
db | -0.022 |
Token | life |
Token ID | 1204 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
ingred | +0.013 |
Sect | +0.013 |
ufact | +0.013 |
� | +0.013 |
Voc | +0.012 |
Neg logit contributions | |
ó | -0.012 |
alert | -0.012 |
FB | -0.012 |
umber | -0.012 |
Teddy | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
ó | +0.015 |
alert | +0.015 |
FB | +0.015 |
umber | +0.014 |
Teddy | +0.014 |
Neg logit contributions | |
ingred | -0.017 |
Sect | -0.016 |
� | -0.016 |
ufact | -0.016 |
Voc | -0.016 |
Token | me |
Token ID | 502 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ingred | +0.019 |
Sect | +0.019 |
� | +0.019 |
ufact | +0.019 |
Voc | +0.018 |
Neg logit contributions | |
ó | -0.023 |
alert | -0.023 |
FB | -0.023 |
umber | -0.022 |
Teddy | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
ingred | +0.101 |
Sect | +0.099 |
� | +0.097 |
ufact | +0.096 |
Voc | +0.095 |
Neg logit contributions | |
ó | -0.083 |
alert | -0.079 |
FB | -0.079 |
umber | -0.078 |
Teddy | -0.078 |
Token | figure |
Token ID | 3785 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
ingred | +0.014 |
Sect | +0.013 |
� | +0.013 |
ufact | +0.013 |
Voc | +0.013 |
Neg logit contributions | |
ó | -0.013 |
alert | -0.013 |
FB | -0.013 |
umber | -0.013 |
Teddy | -0.013 |
Token | out |
Token ID | 503 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
ó | +0.037 |
alert | +0.036 |
FB | +0.036 |
umber | +0.036 |
Teddy | +0.036 |
Neg logit contributions | |
ingred | -0.018 |
Sect | -0.017 |
ufact | -0.017 |
� | -0.017 |
Voc | -0.016 |
Token | how |
Token ID | 703 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
ingred | +0.288 |
Sect | +0.284 |
� | +0.279 |
ufact | +0.276 |
Voc | +0.271 |
Neg logit contributions | |
ó | -0.234 |
alert | -0.224 |
FB | -0.224 |
umber | -0.222 |
Teddy | -0.220 |
Token | to |
Token ID | 284 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
ó | +0.014 |
alert | +0.013 |
FB | +0.013 |
umber | +0.013 |
Teddy | +0.013 |
Neg logit contributions | |
ingred | -0.016 |
Sect | -0.015 |
� | -0.015 |
ufact | -0.015 |
Voc | -0.015 |
Token | do |
Token ID | 466 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
ingred | +0.014 |
Sect | +0.014 |
� | +0.013 |
ufact | +0.013 |
Voc | +0.013 |
Neg logit contributions | |
ó | -0.013 |
alert | -0.013 |
FB | -0.013 |
umber | -0.013 |
Teddy | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | -2.40e-03 |
Pos logit contributions | |
ingred | +0.065 |
Sect | +0.064 |
� | +0.063 |
ufact | +0.062 |
Voc | +0.061 |
Neg logit contributions | |
ó | -0.054 |
FB | -0.051 |
alert | -0.051 |
umber | -0.051 |
Teddy | -0.050 |
Token | myself |
Token ID | 3589 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ó | +0.002 |
alert | +0.002 |
FB | +0.002 |
umber | +0.002 |
Teddy | +0.002 |
Neg logit contributions | |
ingred | -0.002 |
Sect | -0.002 |
� | -0.002 |
ufact | -0.002 |
Voc | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +6.80e-03 |
Pos logit contributions | |
ó | +0.033 |
alert | +0.032 |
FB | +0.032 |
umber | +0.032 |
Teddy | +0.031 |
Neg logit contributions | |
ingred | -0.036 |
Sect | -0.036 |
� | -0.035 |
ufact | -0.035 |
Voc | -0.034 |
Token | power |
Token ID | 1176 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
ingred | +0.005 |
Sect | +0.005 |
� | +0.005 |
ufact | +0.005 |
Voc | +0.005 |
Neg logit contributions | |
ó | -0.005 |
FB | -0.005 |
alert | -0.005 |
umber | -0.005 |
Teddy | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +4.01e-03 |
Pos logit contributions | |
ó | +0.051 |
alert | +0.049 |
FB | +0.049 |
umber | +0.048 |
Teddy | +0.048 |
Neg logit contributions | |
ingred | -0.068 |
Sect | -0.067 |
� | -0.066 |
ufact | -0.066 |
Voc | -0.064 |
Token | say |
Token ID | 910 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
ingred | +0.003 |
Sect | +0.003 |
� | +0.003 |
ufact | +0.003 |
Voc | +0.003 |
Neg logit contributions | |
ó | -0.003 |
alert | -0.003 |
FB | -0.003 |
umber | -0.003 |
Teddy | -0.003 |
Token | � |
Token ID | 564 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
ingred | +0.027 |
Sect | +0.027 |
� | +0.027 |
ufact | +0.026 |
Voc | +0.026 |
Neg logit contributions | |
ó | -0.024 |
FB | -0.023 |
alert | -0.023 |
umber | -0.023 |
Teddy | -0.023 |
Token | � |
Token ID | 246 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
ingred | +0.007 |
Sect | +0.007 |
� | +0.007 |
ufact | +0.007 |
Voc | +0.006 |
Neg logit contributions | |
ó | -0.023 |
FB | -0.022 |
alert | -0.022 |
umber | -0.022 |
ory | -0.022 |
Token | Yes |
Token ID | 5297 |
Feature activation | -6.27e-03 |
Pos logit contributions | |
ingred | +0.314 |
Sect | +0.310 |
� | +0.306 |
ufact | +0.302 |
Voc | +0.297 |
Neg logit contributions | |
ó | -0.211 |
alert | -0.202 |
FB | -0.202 |
umber | -0.200 |
Teddy | -0.198 |
Token | � |
Token ID | 447 |
Feature activation | -2.41e-03 |
Pos logit contributions | |
ó | +0.004 |
alert | +0.004 |
FB | +0.004 |
umber | +0.004 |
Teddy | +0.004 |
Neg logit contributions | |
ingred | -0.005 |
Sect | -0.005 |
� | -0.005 |
ufact | -0.005 |
Voc | -0.005 |
Token | � |
Token ID | 247 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
ó | +0.002 |
alert | +0.002 |
FB | +0.002 |
umber | +0.002 |
Teddy | +0.002 |
Neg logit contributions | |
ingred | -0.002 |
Sect | -0.002 |
� | -0.002 |
ufact | -0.002 |
Voc | -0.002 |
Token | that |
Token ID | 326 |
Feature activation | +8.49e-02 |
Pos logit contributions | |
ó | +0.009 |
alert | +0.008 |
FB | +0.008 |
umber | +0.008 |
Teddy | +0.008 |
Neg logit contributions | |
ingred | -0.010 |
Sect | -0.010 |
� | -0.010 |
ufact | -0.010 |
Voc | -0.009 |
Token | provides |
Token ID | 3769 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
ingred | +0.066 |
Sect | +0.065 |
� | +0.064 |
ufact | +0.063 |
Voc | +0.062 |
Neg logit contributions | |
ó | -0.062 |
FB | -0.060 |
alert | -0.059 |
umber | -0.059 |
db | -0.059 |
Token |
|
Token ID | 198 |
Feature activation | -3.96e-03 |
Pos logit contributions | |
ingred | +0.001 |
Sect | +0.001 |
� | +0.001 |
ufact | +0.001 |
Voc | +0.001 |
Neg logit contributions | |
ó | -0.001 |
alert | -0.001 |
FB | -0.001 |
umber | -0.001 |
Teddy | -0.001 |
Token | ED |
Token ID | 1961 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
ó | +0.003 |
alert | +0.003 |
FB | +0.003 |
umber | +0.003 |
Teddy | +0.003 |
Neg logit contributions | |
ingred | -0.003 |
Sect | -0.003 |
� | -0.003 |
ufact | -0.003 |
Voc | -0.003 |
Token | M |
Token ID | 44 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ó | +0.033 |
alert | +0.032 |
FB | +0.031 |
umber | +0.031 |
Teddy | +0.031 |
Neg logit contributions | |
ingred | -0.038 |
Sect | -0.038 |
� | -0.037 |
ufact | -0.036 |
Voc | -0.036 |
Token | OND |
Token ID | 18672 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
ingred | +0.083 |
Sect | +0.082 |
� | +0.080 |
ufact | +0.079 |
Voc | +0.078 |
Neg logit contributions | |
ó | -0.075 |
alert | -0.072 |
FB | -0.072 |
umber | -0.071 |
Teddy | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
ó | +0.147 |
alert | +0.141 |
FB | +0.141 |
umber | +0.140 |
Teddy | +0.138 |
Neg logit contributions | |
ingred | -0.165 |
Sect | -0.162 |
� | -0.160 |
ufact | -0.158 |
Voc | -0.155 |
Token | Wash |
Token ID | 22892 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
ó | +0.010 |
alert | +0.010 |
FB | +0.010 |
umber | +0.010 |
Teddy | +0.010 |
Neg logit contributions | |
ingred | -0.009 |
Sect | -0.008 |
ufact | -0.008 |
� | -0.008 |
Voc | -0.008 |
Token | .– |
Token ID | 37585 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
ingred | +0.333 |
Sect | +0.330 |
� | +0.325 |
ufact | +0.320 |
Voc | +0.315 |
Neg logit contributions | |
ó | -0.268 |
alert | -0.257 |
FB | -0.256 |
umber | -0.254 |
Teddy | -0.252 |
Token | ( |
Token ID | 7 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ó | +0.039 |
FB | +0.038 |
alert | +0.038 |
umber | +0.037 |
Teddy | +0.037 |
Neg logit contributions | |
ingred | -0.043 |
Sect | -0.043 |
� | -0.042 |
ufact | -0.042 |
Voc | -0.041 |
Token | BUS |
Token ID | 45346 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
ingred | +0.103 |
Sect | +0.100 |
� | +0.099 |
ufact | +0.098 |
Voc | +0.095 |
Neg logit contributions | |
ó | -0.088 |
FB | -0.085 |
alert | -0.085 |
umber | -0.084 |
db | -0.083 |
Token | INESS |
Token ID | 44180 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
ó | +0.009 |
alert | +0.009 |
FB | +0.009 |
umber | +0.009 |
db | +0.009 |
Neg logit contributions | |
ingred | -0.008 |
Sect | -0.008 |
� | -0.008 |
ufact | -0.008 |
Voc | -0.008 |
Token | WI |
Token ID | 29360 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
ingred | +0.018 |
Sect | +0.017 |
ufact | +0.017 |
� | +0.016 |
Voc | +0.015 |
Neg logit contributions | |
ó | -0.052 |
alert | -0.051 |
FB | -0.051 |
db | -0.051 |
umber | -0.050 |
Token | to |
Token ID | 284 |
Feature activation | -8.56e-03 |
Pos logit contributions | |
ó | +0.082 |
FB | +0.079 |
alert | +0.078 |
umber | +0.078 |
Teddy | +0.077 |
Neg logit contributions | |
ingred | -0.099 |
Sect | -0.098 |
� | -0.097 |
ufact | -0.096 |
Voc | -0.094 |
Token | enable |
Token ID | 7139 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
ó | +0.006 |
FB | +0.006 |
alert | +0.006 |
umber | +0.006 |
Teddy | +0.005 |
Neg logit contributions | |
ingred | -0.007 |
Sect | -0.007 |
� | -0.007 |
ufact | -0.007 |
Voc | -0.007 |
Token | these |
Token ID | 777 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
ó | +0.013 |
FB | +0.013 |
alert | +0.013 |
umber | +0.013 |
Teddy | +0.012 |
Neg logit contributions | |
ingred | -0.016 |
Sect | -0.015 |
� | -0.015 |
ufact | -0.015 |
Voc | -0.015 |
Token | techniques |
Token ID | 7605 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ingred | +0.047 |
Sect | +0.046 |
� | +0.045 |
ufact | +0.045 |
Voc | +0.044 |
Neg logit contributions | |
ó | -0.042 |
FB | -0.040 |
alert | -0.040 |
umber | -0.040 |
Teddy | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -9.83e-03 |
Pos logit contributions | |
ingred | +0.112 |
Sect | +0.111 |
� | +0.109 |
ufact | +0.108 |
Voc | +0.106 |
Neg logit contributions | |
ó | -0.095 |
FB | -0.091 |
alert | -0.091 |
umber | -0.090 |
Teddy | -0.090 |
Token | Even |
Token ID | 3412 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
ó | +0.007 |
FB | +0.006 |
alert | +0.006 |
umber | +0.006 |
Teddy | +0.006 |
Neg logit contributions | |
ingred | -0.008 |
Sect | -0.008 |
� | -0.008 |
ufact | -0.008 |
Voc | -0.008 |
Token | without |
Token ID | 1231 |
Feature activation | +3.98e-03 |
Pos logit contributions | |
ingred | +0.041 |
Sect | +0.041 |
� | +0.040 |
ufact | +0.039 |
Voc | +0.039 |
Neg logit contributions | |
ó | -0.038 |
FB | -0.037 |
alert | -0.037 |
umber | -0.037 |
Teddy | -0.036 |
Token | them |
Token ID | 606 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
ingred | +0.003 |
Sect | +0.003 |
� | +0.003 |
ufact | +0.003 |
Voc | +0.003 |
Neg logit contributions | |
ó | -0.003 |
alert | -0.003 |
FB | -0.003 |
umber | -0.003 |
Teddy | -0.003 |
Token | I |
Token ID | 314 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
ingred | +0.137 |
Sect | +0.135 |
� | +0.133 |
ufact | +0.131 |
Voc | +0.129 |
Neg logit contributions | |
ó | -0.114 |
FB | -0.109 |
alert | -0.109 |
umber | -0.109 |
Teddy | -0.107 |
Token | believe |
Token ID | 1975 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ingred | +0.011 |
Sect | +0.011 |
� | +0.011 |
ufact | +0.011 |
Voc | +0.011 |
Neg logit contributions | |
ó | -0.010 |
FB | -0.009 |
alert | -0.009 |
umber | -0.009 |
Teddy | -0.009 |
Token | we |
Token ID | 356 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
ingred | +0.118 |
Sect | +0.116 |
� | +0.114 |
ufact | +0.113 |
Voc | +0.110 |
Neg logit contributions | |
ó | -0.111 |
alert | -0.107 |
FB | -0.107 |
umber | -0.106 |
Teddy | -0.105 |
Token | employing |
Token ID | 26490 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ingred | +0.021 |
Sect | +0.021 |
� | +0.021 |
ufact | +0.020 |
Voc | +0.020 |
Neg logit contributions | |
ó | -0.020 |
alert | -0.020 |
FB | -0.020 |
umber | -0.019 |
Teddy | -0.019 |
Token | this |
Token ID | 428 |
Feature activation | +9.59e-03 |
Pos logit contributions | |
ingred | +0.124 |
Sect | +0.122 |
� | +0.120 |
ufact | +0.119 |
Voc | +0.116 |
Neg logit contributions | |
ó | -0.105 |
alert | -0.100 |
FB | -0.100 |
umber | -0.099 |
Teddy | -0.098 |
Token | critical |
Token ID | 4688 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
ingred | +0.007 |
Sect | +0.007 |
� | +0.007 |
ufact | +0.007 |
Voc | +0.007 |
Neg logit contributions | |
ó | -0.007 |
alert | -0.007 |
FB | -0.007 |
umber | -0.007 |
Teddy | -0.007 |
Token | food |
Token ID | 2057 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
ó | +0.181 |
alert | +0.176 |
FB | +0.173 |
umber | +0.173 |
Teddy | +0.172 |
Neg logit contributions | |
ingred | -0.150 |
Sect | -0.147 |
� | -0.144 |
ufact | -0.144 |
Voc | -0.139 |
Token | security |
Token ID | 2324 |
Feature activation | -8.89e-03 |
Pos logit contributions | |
ingred | +0.030 |
Sect | +0.030 |
� | +0.029 |
ufact | +0.029 |
Voc | +0.028 |
Neg logit contributions | |
ó | -0.028 |
alert | -0.027 |
FB | -0.027 |
umber | -0.027 |
db | -0.027 |
Token | technique |
Token ID | 8173 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ó | +0.006 |
alert | +0.006 |
FB | +0.006 |
umber | +0.006 |
Teddy | +0.006 |
Neg logit contributions | |
ingred | -0.007 |
Sect | -0.007 |
� | -0.007 |
ufact | -0.007 |
Voc | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
ingred | +0.120 |
Sect | +0.118 |
� | +0.116 |
ufact | +0.115 |
Voc | +0.112 |
Neg logit contributions | |
ó | -0.101 |
FB | -0.097 |
alert | -0.097 |
umber | -0.096 |
Teddy | -0.095 |
Token | I |
Token ID | 314 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
ingred | +0.018 |
Sect | +0.018 |
� | +0.018 |
ufact | +0.017 |
Voc | +0.017 |
Neg logit contributions | |
ó | -0.015 |
alert | -0.015 |
FB | -0.015 |
umber | -0.015 |
Teddy | -0.014 |
Token | find |
Token ID | 1064 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
ingred | +0.033 |
Sect | +0.032 |
� | +0.032 |
ufact | +0.031 |
Voc | +0.031 |
Neg logit contributions | |
ó | -0.028 |
alert | -0.027 |
FB | -0.027 |
umber | -0.027 |
Teddy | -0.027 |
Token | that |
Token ID | 326 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
ó | +0.061 |
alert | +0.058 |
FB | +0.058 |
umber | +0.057 |
Teddy | +0.057 |
Neg logit contributions | |
ingred | -0.069 |
Sect | -0.068 |
� | -0.067 |
ufact | -0.067 |
Voc | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
ingred | +0.077 |
Sect | +0.076 |
� | +0.074 |
ufact | +0.074 |
Voc | +0.072 |
Neg logit contributions | |
ó | -0.068 |
alert | -0.066 |
FB | -0.065 |
umber | -0.065 |
Teddy | -0.065 |
Token | pressure |
Token ID | 3833 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
ó | +0.023 |
FB | +0.022 |
umber | +0.022 |
alert | +0.022 |
db | +0.022 |
Neg logit contributions | |
ingred | -0.030 |
Sect | -0.030 |
� | -0.029 |
ufact | -0.029 |
Voc | -0.028 |
Token | on |
Token ID | 319 |
Feature activation | +6.27e-02 |
Pos logit contributions | |
ingred | +0.025 |
Sect | +0.025 |
� | +0.024 |
ufact | +0.024 |
Voc | +0.024 |
Neg logit contributions | |
ó | -0.023 |
FB | -0.022 |
alert | -0.022 |
umber | -0.022 |
Teddy | -0.022 |
Token | his |
Token ID | 465 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
ingred | +0.054 |
Sect | +0.053 |
� | +0.052 |
ufact | +0.052 |
Voc | +0.051 |
Neg logit contributions | |
ó | -0.041 |
alert | -0.039 |
FB | -0.039 |
umber | -0.038 |
Teddy | -0.038 |
Token | job |
Token ID | 1693 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
ó | +0.049 |
alert | +0.048 |
FB | +0.047 |
umber | +0.047 |
Teddy | +0.047 |
Neg logit contributions | |
ingred | -0.063 |
Sect | -0.062 |
� | -0.061 |
ufact | -0.060 |
Voc | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ingred | +0.206 |
Sect | +0.204 |
� | +0.200 |
ufact | +0.198 |
Voc | +0.194 |
Neg logit contributions | |
ó | -0.182 |
FB | -0.175 |
alert | -0.174 |
umber | -0.173 |
Teddy | -0.171 |
Token | even |
Token ID | 772 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ingred | +0.008 |
Sect | +0.008 |
� | +0.008 |
ufact | +0.008 |
Voc | +0.008 |
Neg logit contributions | |
ó | -0.007 |
alert | -0.007 |
FB | -0.007 |
umber | -0.007 |
Teddy | -0.007 |
Token | though |
Token ID | 996 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
ingred | +0.077 |
Sect | +0.076 |
� | +0.074 |
ufact | +0.074 |
Voc | +0.072 |
Neg logit contributions | |
ó | -0.087 |
alert | -0.084 |
FB | -0.084 |
umber | -0.084 |
Teddy | -0.083 |
Token | he |
Token ID | 339 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
ingred | +0.179 |
Sect | +0.177 |
� | +0.174 |
ufact | +0.172 |
Voc | +0.168 |
Neg logit contributions | |
ó | -0.158 |
FB | -0.151 |
alert | -0.151 |
umber | -0.150 |
Teddy | -0.148 |
Token | was |
Token ID | 373 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
ingred | +0.022 |
Sect | +0.022 |
� | +0.021 |
ufact | +0.021 |
Voc | +0.021 |
Neg logit contributions | |
ó | -0.021 |
alert | -0.021 |
FB | -0.020 |
umber | -0.020 |
Teddy | -0.020 |
Token | pretty |
Token ID | 2495 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
ingred | +0.024 |
Sect | +0.024 |
� | +0.023 |
ufact | +0.023 |
Voc | +0.022 |
Neg logit contributions | |
ó | -0.021 |
alert | -0.021 |
FB | -0.021 |
umber | -0.020 |
Teddy | -0.020 |
Token | much |
Token ID | 881 |
Feature activation | +5.85e-02 |
Pos logit contributions | |
ó | +0.048 |
alert | +0.046 |
FB | +0.046 |
umber | +0.045 |
Teddy | +0.045 |
Neg logit contributions | |
ingred | -0.046 |
Sect | -0.045 |
� | -0.044 |
ufact | -0.044 |
Voc | -0.043 |
Token | is |
Token ID | 271 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
Sect | +0.083 |
ingred | +0.083 |
� | +0.082 |
ufact | +0.079 |
Voc | +0.079 |
Neg logit contributions | |
ó | -0.105 |
FB | -0.102 |
alert | -0.101 |
Barney | -0.100 |
umber | -0.100 |
Token | od |
Token ID | 375 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
ingred | +0.085 |
Sect | +0.085 |
� | +0.084 |
ufact | +0.083 |
Voc | +0.082 |
Neg logit contributions | |
ó | -0.034 |
FB | -0.032 |
alert | -0.032 |
Teddy | -0.031 |
Barney | -0.031 |
Token | ia |
Token ID | 544 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
ó | +0.199 |
alert | +0.192 |
FB | +0.191 |
umber | +0.191 |
ory | +0.189 |
Neg logit contributions | |
ingred | -0.165 |
Sect | -0.162 |
� | -0.159 |
ufact | -0.157 |
Voc | -0.153 |
Token | , |
Token ID | 11 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
ingred | +0.103 |
Sect | +0.101 |
ufact | +0.099 |
� | +0.099 |
Voc | +0.097 |
Neg logit contributions | |
ó | -0.085 |
alert | -0.082 |
FB | -0.081 |
umber | -0.080 |
Teddy | -0.080 |
Token | and |
Token ID | 290 |
Feature activation | -3.22e-03 |
Pos logit contributions | |
ingred | +0.010 |
Sect | +0.010 |
� | +0.010 |
ufact | +0.010 |
Voc | +0.010 |
Neg logit contributions | |
ó | -0.009 |
alert | -0.009 |
FB | -0.009 |
umber | -0.009 |
Teddy | -0.009 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ó | +0.002 |
alert | +0.002 |
FB | +0.002 |
umber | +0.002 |
Teddy | +0.002 |
Neg logit contributions | |
ingred | -0.003 |
Sect | -0.003 |
� | -0.003 |
ufact | -0.002 |
Voc | -0.002 |
Token | how |
Token ID | 703 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
ingred | +0.085 |
Sect | +0.083 |
� | +0.082 |
ufact | +0.081 |
Voc | +0.079 |
Neg logit contributions | |
ó | -0.072 |
alert | -0.070 |
FB | -0.069 |
umber | -0.069 |
Teddy | -0.068 |
Token | Mr |
Token ID | 1770 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
ó | +0.016 |
FB | +0.016 |
alert | +0.015 |
umber | +0.015 |
db | +0.015 |
Neg logit contributions | |
ingred | -0.018 |
Sect | -0.018 |
� | -0.018 |
ufact | -0.017 |
Voc | -0.017 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
ingred | +0.016 |
Sect | +0.016 |
� | +0.016 |
ufact | +0.016 |
Voc | +0.016 |
Neg logit contributions | |
ó | -0.007 |
FB | -0.006 |
alert | -0.006 |
umber | -0.006 |
db | -0.006 |
Token | ar |
Token ID | 283 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
ó | +0.184 |
alert | +0.178 |
FB | +0.178 |
umber | +0.177 |
db | +0.176 |
Neg logit contributions | |
ingred | -0.101 |
Sect | -0.098 |
� | -0.095 |
ufact | -0.094 |
Voc | -0.091 |
Token | could |
Token ID | 714 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
ingred | +0.172 |
Sect | +0.170 |
� | +0.167 |
ufact | +0.165 |
Voc | +0.161 |
Neg logit contributions | |
ó | -0.173 |
FB | -0.167 |
umber | -0.165 |
alert | -0.165 |
db | -0.163 |
Token | immigrants |
Token ID | 7971 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
ó | +0.028 |
alert | +0.027 |
FB | +0.027 |
umber | +0.026 |
Teddy | +0.026 |
Neg logit contributions | |
ingred | -0.029 |
Sect | -0.029 |
� | -0.028 |
ufact | -0.028 |
Voc | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
ó | +0.028 |
alert | +0.027 |
FB | +0.026 |
umber | +0.026 |
db | +0.026 |
Neg logit contributions | |
ingred | -0.034 |
Sect | -0.034 |
� | -0.033 |
ufact | -0.033 |
Voc | -0.032 |
Token | we |
Token ID | 356 |
Feature activation | +6.08e-02 |
Pos logit contributions | |
ingred | +0.008 |
Sect | +0.008 |
ufact | +0.008 |
� | +0.008 |
Voc | +0.007 |
Neg logit contributions | |
ó | -0.007 |
alert | -0.007 |
FB | -0.007 |
umber | -0.007 |
Teddy | -0.007 |
Token | knew |
Token ID | 2993 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
ingred | +0.049 |
Sect | +0.048 |
� | +0.047 |
ufact | +0.047 |
Voc | +0.046 |
Neg logit contributions | |
ó | -0.043 |
alert | -0.041 |
FB | -0.041 |
umber | -0.041 |
Teddy | -0.040 |
Token | that |
Token ID | 326 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
ingred | +0.142 |
Sect | +0.140 |
� | +0.137 |
ufact | +0.137 |
Voc | +0.134 |
Neg logit contributions | |
ó | -0.129 |
alert | -0.124 |
FB | -0.123 |
umber | -0.123 |
Teddy | -0.122 |
Token | if |
Token ID | 611 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
ingred | +0.072 |
Sect | +0.071 |
� | +0.070 |
ufact | +0.070 |
Voc | +0.068 |
Neg logit contributions | |
ó | -0.065 |
alert | -0.063 |
FB | -0.062 |
umber | -0.062 |
Teddy | -0.062 |
Token | we |
Token ID | 356 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
ingred | +0.098 |
Sect | +0.096 |
� | +0.094 |
ufact | +0.094 |
Voc | +0.092 |
Neg logit contributions | |
ó | -0.093 |
alert | -0.089 |
FB | -0.089 |
umber | -0.089 |
Teddy | -0.088 |
Token | fl |
Token ID | 781 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
ingred | +0.052 |
Sect | +0.051 |
ufact | +0.050 |
� | +0.050 |
Voc | +0.049 |
Neg logit contributions | |
ó | -0.049 |
alert | -0.047 |
FB | -0.046 |
umber | -0.046 |
db | -0.046 |
Token | unk |
Token ID | 2954 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
ingred | +0.037 |
Sect | +0.036 |
� | +0.035 |
ufact | +0.035 |
Voc | +0.034 |
Neg logit contributions | |
ó | -0.032 |
FB | -0.031 |
alert | -0.031 |
umber | -0.031 |
ory | -0.030 |
Token | ed |
Token ID | 276 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
ingred | +0.011 |
Sect | +0.011 |
� | +0.010 |
ufact | +0.010 |
Voc | +0.010 |
Neg logit contributions | |
ó | -0.010 |
alert | -0.009 |
FB | -0.009 |
umber | -0.009 |
Teddy | -0.009 |
Token | out |
Token ID | 503 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
ingred | +0.039 |
Sect | +0.038 |
ufact | +0.037 |
� | +0.037 |
Voc | +0.036 |
Neg logit contributions | |
ó | -0.040 |
alert | -0.038 |
FB | -0.038 |
umber | -0.038 |
Teddy | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
ingred | +0.013 |
Sect | +0.013 |
� | +0.013 |
ufact | +0.012 |
Voc | +0.012 |
Neg logit contributions | |
ó | -0.011 |
FB | -0.011 |
alert | -0.011 |
umber | -0.011 |
Teddy | -0.010 |
Token | leaving |
Token ID | 4305 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
ó | +0.014 |
FB | +0.013 |
alert | +0.013 |
umber | +0.013 |
db | +0.013 |
Neg logit contributions | |
ingred | -0.015 |
Sect | -0.015 |
� | -0.015 |
ufact | -0.015 |
Voc | -0.014 |
Token | un |
Token ID | 555 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ingred | +0.031 |
Sect | +0.030 |
� | +0.030 |
ufact | +0.029 |
Voc | +0.029 |
Neg logit contributions | |
ó | -0.026 |
alert | -0.025 |
FB | -0.024 |
umber | -0.024 |
Teddy | -0.024 |
Token | har |
Token ID | 9869 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
ingred | +0.073 |
Sect | +0.072 |
� | +0.070 |
ufact | +0.069 |
Voc | +0.067 |
Neg logit contributions | |
ó | -0.103 |
FB | -0.100 |
alert | -0.100 |
umber | -0.099 |
Teddy | -0.098 |
Token | med |
Token ID | 1150 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
ingred | +0.068 |
Sect | +0.066 |
� | +0.063 |
ufact | +0.062 |
Voc | +0.059 |
Neg logit contributions | |
ó | -0.197 |
alert | -0.192 |
FB | -0.192 |
umber | -0.191 |
db | -0.190 |
Token | , |
Token ID | 11 |
Feature activation | -3.05e-03 |
Pos logit contributions | |
ingred | +0.278 |
Sect | +0.276 |
� | +0.272 |
ufact | +0.267 |
Voc | +0.263 |
Neg logit contributions | |
ó | -0.244 |
FB | -0.235 |
alert | -0.232 |
umber | -0.232 |
db | -0.229 |
Token | among |
Token ID | 1871 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
ó | +0.002 |
alert | +0.002 |
FB | +0.002 |
umber | +0.002 |
Teddy | +0.002 |
Neg logit contributions | |
ingred | -0.002 |
Sect | -0.002 |
� | -0.002 |
ufact | -0.002 |
Voc | -0.002 |
Token | them |
Token ID | 606 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
ó | +0.200 |
alert | +0.194 |
FB | +0.193 |
umber | +0.192 |
Teddy | +0.191 |
Neg logit contributions | |
ingred | -0.156 |
Sect | -0.152 |
� | -0.149 |
ufact | -0.148 |
Voc | -0.144 |
Token | many |
Token ID | 867 |
Feature activation | +9.79e-02 |
Pos logit contributions | |
ingred | +0.136 |
Sect | +0.134 |
� | +0.131 |
ufact | +0.130 |
Voc | +0.127 |
Neg logit contributions | |
ó | -0.118 |
alert | -0.113 |
FB | -0.113 |
umber | -0.112 |
Teddy | -0.111 |
Token | with |
Token ID | 351 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
ingred | +0.081 |
Sect | +0.080 |
� | +0.078 |
ufact | +0.078 |
Voc | +0.076 |
Neg logit contributions | |
ó | -0.067 |
FB | -0.064 |
alert | -0.064 |
umber | -0.063 |
Teddy | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
ó | +0.084 |
alert | +0.081 |
FB | +0.081 |
umber | +0.080 |
Teddy | +0.080 |
Neg logit contributions | |
ingred | -0.098 |
Sect | -0.096 |
� | -0.095 |
ufact | -0.094 |
Voc | -0.092 |
Token | persons |
Token ID | 6506 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
ingred | +0.063 |
Sect | +0.062 |
� | +0.061 |
ufact | +0.060 |
Voc | +0.059 |
Neg logit contributions | |
ó | -0.047 |
alert | -0.045 |
FB | -0.045 |
umber | -0.044 |
Teddy | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ó | +0.045 |
FB | +0.043 |
alert | +0.043 |
umber | +0.042 |
db | +0.042 |
Neg logit contributions | |
ingred | -0.053 |
Sect | -0.053 |
� | -0.052 |
ufact | -0.051 |
Voc | -0.050 |
Token | although |
Token ID | 3584 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ingred | +0.008 |
Sect | +0.008 |
� | +0.008 |
ufact | +0.008 |
Voc | +0.008 |
Neg logit contributions | |
ó | -0.007 |
FB | -0.007 |
alert | -0.007 |
umber | -0.007 |
Teddy | -0.007 |
Token | numerous |
Token ID | 6409 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ingred | +0.132 |
Sect | +0.130 |
� | +0.128 |
ufact | +0.127 |
Voc | +0.124 |
Neg logit contributions | |
ó | -0.107 |
FB | -0.103 |
alert | -0.103 |
umber | -0.102 |
Teddy | -0.101 |
Token | other |
Token ID | 584 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ingred | +0.084 |
Sect | +0.083 |
� | +0.082 |
ufact | +0.081 |
Voc | +0.079 |
Neg logit contributions | |
ó | -0.073 |
FB | -0.070 |
alert | -0.070 |
umber | -0.070 |
db | -0.069 |
Token | cases |
Token ID | 2663 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
ó | +0.119 |
alert | +0.114 |
FB | +0.114 |
umber | +0.113 |
Teddy | +0.112 |
Neg logit contributions | |
ingred | -0.116 |
Sect | -0.114 |
� | -0.112 |
ufact | -0.111 |
Voc | -0.108 |
Token | , |
Token ID | 11 |
Feature activation | +6.38e-03 |
Pos logit contributions | |
ingred | +0.023 |
Sect | +0.023 |
� | +0.022 |
ufact | +0.022 |
Voc | +0.022 |
Neg logit contributions | |
ó | -0.021 |
FB | -0.020 |
alert | -0.020 |
umber | -0.020 |
Teddy | -0.019 |
Token | since |
Token ID | 1201 |
Feature activation | +8.09e-03 |
Pos logit contributions | |
ingred | +0.005 |
Sect | +0.005 |
� | +0.005 |
ufact | +0.005 |
Voc | +0.005 |
Neg logit contributions | |
ó | -0.004 |
FB | -0.004 |
alert | -0.004 |
umber | -0.004 |
Teddy | -0.004 |
Token | Dartmouth |
Token ID | 47888 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
ingred | +0.007 |
Sect | +0.007 |
� | +0.007 |
ufact | +0.007 |
Voc | +0.006 |
Neg logit contributions | |
ó | -0.005 |
FB | -0.005 |
alert | -0.005 |
umber | -0.005 |
db | -0.005 |
Token | College |
Token ID | 5535 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ó | +0.069 |
FB | +0.066 |
alert | +0.066 |
umber | +0.066 |
Teddy | +0.065 |
Neg logit contributions | |
ingred | -0.072 |
Sect | -0.071 |
� | -0.070 |
ufact | -0.069 |
Voc | -0.067 |
Token | v |
Token ID | 410 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ó | +0.080 |
FB | +0.076 |
alert | +0.076 |
umber | +0.076 |
Teddy | +0.075 |
Neg logit contributions | |
ingred | -0.090 |
Sect | -0.088 |
� | -0.087 |
ufact | -0.086 |
Voc | -0.084 |
Token | toll |
Token ID | 13592 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
ingred | +0.020 |
Sect | +0.020 |
� | +0.019 |
ufact | +0.019 |
Voc | +0.019 |
Neg logit contributions | |
ó | -0.015 |
alert | -0.014 |
FB | -0.014 |
umber | -0.014 |
Teddy | -0.014 |
Token | on |
Token ID | 319 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
ó | +0.033 |
FB | +0.031 |
alert | +0.031 |
umber | +0.031 |
Teddy | +0.031 |
Neg logit contributions | |
ingred | -0.033 |
Sect | -0.033 |
� | -0.033 |
ufact | -0.032 |
Voc | -0.031 |
Token | employees |
Token ID | 4409 |
Feature activation | +6.49e-02 |
Pos logit contributions | |
ingred | +0.039 |
Sect | +0.038 |
� | +0.038 |
ufact | +0.037 |
Voc | +0.037 |
Neg logit contributions | |
ó | -0.030 |
FB | -0.029 |
umber | -0.029 |
alert | -0.028 |
ory | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -1.00e-03 |
Pos logit contributions | |
ingred | +0.053 |
Sect | +0.052 |
� | +0.052 |
ufact | +0.051 |
Voc | +0.050 |
Neg logit contributions | |
ó | -0.044 |
FB | -0.043 |
alert | -0.042 |
umber | -0.042 |
Teddy | -0.042 |
Token |
|
Token ID | 198 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
ó | +0.001 |
alert | +0.001 |
FB | +0.001 |
umber | +0.001 |
Teddy | +0.001 |
Neg logit contributions | |
ingred | -0.001 |
Sect | -0.001 |
� | -0.001 |
ufact | -0.001 |
Voc | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -2.02e-03 |
Pos logit contributions | |
ingred | +0.002 |
Sect | +0.002 |
� | +0.002 |
ufact | +0.002 |
Voc | +0.002 |
Neg logit contributions | |
ó | -0.002 |
alert | -0.002 |
FB | -0.002 |
umber | -0.002 |
Teddy | -0.002 |
Token | Ms |
Token ID | 10128 |
Feature activation | -8.68e-02 |
Pos logit contributions | |
ó | +0.001 |
alert | +0.001 |
FB | +0.001 |
umber | +0.001 |
Teddy | +0.001 |
Neg logit contributions | |
ingred | -0.002 |
Sect | -0.002 |
� | -0.002 |
ufact | -0.002 |
Voc | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-03 |
Pos logit contributions | |
ó | +0.058 |
alert | +0.055 |
FB | +0.055 |
umber | +0.055 |
Teddy | +0.054 |
Neg logit contributions | |
ingred | -0.074 |
Sect | -0.072 |
ufact | -0.070 |
� | -0.070 |
Voc | -0.068 |
Token | Lap |
Token ID | 26944 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
ó | +0.002 |
alert | +0.002 |
FB | +0.002 |
umber | +0.002 |
Teddy | +0.002 |
Neg logit contributions | |
ingred | -0.001 |
Sect | -0.001 |
� | -0.001 |
ufact | -0.001 |
Voc | -0.001 |
Token | eral |
Token ID | 1691 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
ingred | +0.216 |
Sect | +0.216 |
� | +0.214 |
ufact | +0.210 |
Voc | +0.208 |
Neg logit contributions | |
ó | -0.155 |
FB | -0.150 |
alert | -0.150 |
Teddy | -0.147 |
Barney | -0.146 |
Token | also |
Token ID | 635 |
Feature activation | -1.77e-04 |
Pos logit contributions | |
ó | +0.066 |
FB | +0.064 |
alert | +0.064 |
umber | +0.063 |
Teddy | +0.063 |
Neg logit contributions | |
ingred | -0.076 |
Sect | -0.075 |
� | -0.074 |
ufact | -0.073 |
Voc | -0.072 |
Token | Using |
Token ID | 8554 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
ingred | +0.009 |
Sect | +0.009 |
� | +0.009 |
ufact | +0.009 |
Voc | +0.008 |
Neg logit contributions | |
ó | -0.007 |
alert | -0.007 |
FB | -0.007 |
umber | -0.007 |
Teddy | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
ingred | +0.086 |
Sect | +0.085 |
� | +0.084 |
ufact | +0.083 |
Voc | +0.082 |
Neg logit contributions | |
ó | -0.051 |
alert | -0.048 |
FB | -0.048 |
umber | -0.048 |
Teddy | -0.047 |
Token | variety |
Token ID | 4996 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ingred | +0.028 |
Sect | +0.027 |
� | +0.027 |
ufact | +0.027 |
Voc | +0.026 |
Neg logit contributions | |
ó | -0.027 |
alert | -0.026 |
FB | -0.026 |
umber | -0.026 |
Teddy | -0.026 |
Token | of |
Token ID | 286 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
ingred | +0.123 |
Sect | +0.121 |
� | +0.119 |
ufact | +0.118 |
Voc | +0.115 |
Neg logit contributions | |
ó | -0.115 |
alert | -0.110 |
FB | -0.110 |
umber | -0.109 |
Teddy | -0.108 |
Token | quick |
Token ID | 2068 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ingred | +0.012 |
Sect | +0.012 |
� | +0.012 |
ufact | +0.011 |
Voc | +0.011 |
Neg logit contributions | |
ó | -0.013 |
FB | -0.013 |
alert | -0.013 |
umber | -0.012 |
Teddy | -0.012 |
Token | moving |
Token ID | 3867 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
ingred | +0.008 |
Sect | +0.007 |
� | +0.007 |
ufact | +0.007 |
Voc | +0.007 |
Neg logit contributions | |
ó | -0.008 |
alert | -0.008 |
FB | -0.008 |
umber | -0.008 |
Teddy | -0.007 |
Token | attacks |
Token ID | 3434 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
ó | +0.008 |
alert | +0.008 |
FB | +0.008 |
umber | +0.008 |
Teddy | +0.008 |
Neg logit contributions | |
ingred | -0.008 |
Sect | -0.007 |
� | -0.007 |
ufact | -0.007 |
Voc | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
ingred | +0.040 |
Sect | +0.039 |
� | +0.039 |
ufact | +0.038 |
Voc | +0.037 |
Neg logit contributions | |
ó | -0.033 |
FB | -0.032 |
alert | -0.032 |
umber | -0.031 |
db | -0.031 |
Token | command |
Token ID | 3141 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
ó | +0.011 |
alert | +0.011 |
FB | +0.011 |
umber | +0.011 |
Teddy | +0.010 |
Neg logit contributions | |
ingred | -0.011 |
Sect | -0.011 |
� | -0.011 |
ufact | -0.011 |
Voc | -0.011 |
Token | grabs |
Token ID | 22378 |
Feature activation | +8.53e-02 |
Pos logit contributions | |
ó | +0.026 |
alert | +0.025 |
FB | +0.025 |
umber | +0.025 |
Teddy | +0.025 |
Neg logit contributions | |
ingred | -0.025 |
Sect | -0.025 |
� | -0.025 |
ufact | -0.024 |
Voc | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -6.59e-03 |
Pos logit contributions | |
ingred | +0.070 |
Sect | +0.069 |
� | +0.068 |
ufact | +0.067 |
Voc | +0.066 |
Neg logit contributions | |
ó | -0.058 |
FB | -0.056 |
alert | -0.056 |
umber | -0.056 |
Teddy | -0.055 |
Token | relief |
Token ID | 8259 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
ingred | +0.048 |
Sect | +0.047 |
� | +0.046 |
ufact | +0.046 |
Voc | +0.045 |
Neg logit contributions | |
ó | -0.036 |
alert | -0.035 |
FB | -0.035 |
umber | -0.034 |
Teddy | -0.034 |
Token | when |
Token ID | 618 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ó | +0.218 |
alert | +0.210 |
FB | +0.209 |
umber | +0.207 |
Teddy | +0.206 |
Neg logit contributions | |
ingred | -0.245 |
Sect | -0.241 |
� | -0.237 |
ufact | -0.236 |
Voc | -0.230 |
Token | Resident |
Token ID | 22373 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ingred | +0.085 |
Sect | +0.083 |
� | +0.082 |
ufact | +0.081 |
Voc | +0.080 |
Neg logit contributions | |
ó | -0.068 |
FB | -0.065 |
alert | -0.065 |
umber | -0.064 |
Teddy | -0.064 |
Token | Evil |
Token ID | 10461 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
ingred | +0.145 |
Sect | +0.145 |
� | +0.142 |
ufact | +0.140 |
Voc | +0.138 |
Neg logit contributions | |
ó | -0.092 |
FB | -0.088 |
alert | -0.088 |
umber | -0.087 |
Teddy | -0.085 |
Token | 4 |
Token ID | 604 |
Feature activation | +9.53e-03 |
Pos logit contributions | |
ó | +0.079 |
FB | +0.076 |
alert | +0.076 |
umber | +0.076 |
Teddy | +0.075 |
Neg logit contributions | |
ingred | -0.080 |
Sect | -0.079 |
� | -0.078 |
ufact | -0.077 |
Voc | -0.075 |
Token | � |
Token ID | 447 |
Feature activation | -7.43e-03 |
Pos logit contributions | |
ingred | +0.008 |
Sect | +0.007 |
� | +0.007 |
ufact | +0.007 |
Voc | +0.007 |
Neg logit contributions | |
ó | -0.007 |
FB | -0.006 |
alert | -0.006 |
umber | -0.006 |
Teddy | -0.006 |
Token | � |
Token ID | 247 |
Feature activation | -8.58e-03 |
Pos logit contributions | |
ó | +0.006 |
FB | +0.005 |
alert | +0.005 |
umber | +0.005 |
db | +0.005 |
Neg logit contributions | |
ingred | -0.006 |
Sect | -0.005 |
� | -0.005 |
ufact | -0.005 |
Voc | -0.005 |
Token | s |
Token ID | 82 |
Feature activation | +4.03e-04 |
Pos logit contributions | |
ó | +0.006 |
alert | +0.006 |
FB | +0.006 |
umber | +0.005 |
Teddy | +0.005 |
Neg logit contributions | |
ingred | -0.007 |
Sect | -0.007 |
� | -0.007 |
ufact | -0.007 |
Voc | -0.007 |
Token | bliss |
Token ID | 30533 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
ingred | +0.000 |
Sect | +0.000 |
� | +0.000 |
ufact | +0.000 |
Voc | +0.000 |
Neg logit contributions | |
ó | -0.000 |
FB | -0.000 |
alert | -0.000 |
umber | -0.000 |
Teddy | -0.000 |
Token | ful |
Token ID | 913 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ó | +0.076 |
FB | +0.073 |
alert | +0.072 |
umber | +0.072 |
Teddy | +0.071 |
Neg logit contributions | |
ingred | -0.117 |
Sect | -0.116 |
� | -0.114 |
ufact | -0.113 |
Voc | -0.111 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
ó | +0.072 |
alert | +0.069 |
FB | +0.069 |
umber | +0.068 |
Teddy | +0.067 |
Neg logit contributions | |
ingred | -0.087 |
Sect | -0.086 |
� | -0.084 |
ufact | -0.083 |
Voc | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
ingred | +0.081 |
Sect | +0.080 |
� | +0.079 |
ufact | +0.077 |
Voc | +0.076 |
Neg logit contributions | |
ó | -0.069 |
FB | -0.066 |
alert | -0.066 |
umber | -0.066 |
Teddy | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | -5.72e-03 |
Pos logit contributions | |
ó | +0.002 |
alert | +0.002 |
FB | +0.002 |
umber | +0.002 |
Teddy | +0.002 |
Neg logit contributions | |
ingred | -0.003 |
Sect | -0.003 |
� | -0.003 |
ufact | -0.003 |
Voc | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
ó | +0.004 |
alert | +0.004 |
FB | +0.004 |
umber | +0.004 |
Teddy | +0.004 |
Neg logit contributions | |
ingred | -0.005 |
Sect | -0.005 |
� | -0.004 |
ufact | -0.004 |
Voc | -0.004 |
Token | Follow |
Token ID | 7155 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
ó | +0.007 |
alert | +0.007 |
FB | +0.007 |
umber | +0.007 |
Teddy | +0.007 |
Neg logit contributions | |
ingred | -0.009 |
Sect | -0.008 |
� | -0.008 |
ufact | -0.008 |
Voc | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -2.20e-03 |
Pos logit contributions | |
ó | +0.055 |
alert | +0.053 |
FB | +0.053 |
umber | +0.053 |
Teddy | +0.052 |
Neg logit contributions | |
ingred | -0.053 |
Sect | -0.052 |
� | -0.051 |
ufact | -0.051 |
Voc | -0.049 |
Token | Downtown |
Token ID | 25657 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
ó | +0.001 |
FB | +0.001 |
alert | +0.001 |
umber | +0.001 |
Teddy | +0.001 |
Neg logit contributions | |
ingred | -0.002 |
Sect | -0.002 |
� | -0.002 |
ufact | -0.002 |
Voc | -0.002 |
Token | Blog |
Token ID | 14001 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
ó | +0.219 |
FB | +0.210 |
alert | +0.210 |
umber | +0.209 |
Teddy | +0.206 |
Neg logit contributions | |
ingred | -0.244 |
Sect | -0.241 |
� | -0.237 |
ufact | -0.234 |
Voc | -0.229 |
Token | on |
Token ID | 319 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
ó | +0.096 |
alert | +0.092 |
FB | +0.092 |
umber | +0.091 |
Teddy | +0.090 |
Neg logit contributions | |
ingred | -0.106 |
Sect | -0.104 |
� | -0.102 |
ufact | -0.101 |
Voc | -0.099 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -7.48e-02 |
Pos logit contributions | |
ingred | +0.036 |
Sect | +0.036 |
� | +0.036 |
ufact | +0.035 |
Voc | +0.034 |
Neg logit contributions | |
ó | -0.026 |
alert | -0.025 |
FB | -0.025 |
umber | -0.025 |
db | -0.024 |
Token | : |
Token ID | 25 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
ó | +0.056 |
FB | +0.054 |
alert | +0.054 |
umber | +0.053 |
Teddy | +0.053 |
Neg logit contributions | |
ingred | -0.056 |
Sect | -0.056 |
� | -0.055 |
ufact | -0.054 |
Voc | -0.053 |
Token | twitter |
Token ID | 17044 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
ó | +0.061 |
alert | +0.059 |
FB | +0.059 |
umber | +0.059 |
Teddy | +0.058 |
Neg logit contributions | |
ingred | -0.049 |
Sect | -0.048 |
� | -0.048 |
ufact | -0.046 |
Voc | -0.046 |
Token | enough |
Token ID | 1576 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
ingred | +0.012 |
Sect | +0.012 |
� | +0.012 |
ufact | +0.012 |
Voc | +0.011 |
Neg logit contributions | |
ó | -0.008 |
FB | -0.007 |
umber | -0.007 |
alert | -0.007 |
Teddy | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
ó | +0.152 |
FB | +0.146 |
alert | +0.146 |
umber | +0.145 |
Teddy | +0.143 |
Neg logit contributions | |
ingred | -0.176 |
Sect | -0.174 |
� | -0.171 |
ufact | -0.169 |
Voc | -0.166 |
Token |
|
Token ID | 198 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
ingred | +0.005 |
Sect | +0.005 |
� | +0.005 |
ufact | +0.005 |
Voc | +0.005 |
Neg logit contributions | |
ó | -0.004 |
alert | -0.004 |
FB | -0.004 |
umber | -0.004 |
db | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
ingred | +0.008 |
Sect | +0.008 |
� | +0.008 |
ufact | +0.008 |
Voc | +0.008 |
Neg logit contributions | |
ó | -0.007 |
alert | -0.007 |
FB | -0.007 |
umber | -0.007 |
Teddy | -0.007 |
Token | Tw |
Token ID | 5080 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
ingred | +0.009 |
Sect | +0.009 |
� | +0.009 |
ufact | +0.009 |
Voc | +0.008 |
Neg logit contributions | |
ó | -0.008 |
alert | -0.008 |
FB | -0.008 |
umber | -0.008 |
Teddy | -0.008 |
Token | itch |
Token ID | 2007 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
ó | +0.101 |
alert | +0.095 |
FB | +0.095 |
umber | +0.093 |
Teddy | +0.092 |
Neg logit contributions | |
ingred | -0.250 |
Sect | -0.247 |
� | -0.244 |
ufact | -0.242 |
Voc | -0.239 |
Token | : |
Token ID | 25 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
ó | +0.213 |
alert | +0.205 |
FB | +0.204 |
umber | +0.203 |
Teddy | +0.201 |
Neg logit contributions | |
ingred | -0.233 |
Sect | -0.230 |
� | -0.226 |
ufact | -0.223 |
Voc | -0.219 |
Token | http |
Token ID | 2638 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
ó | +0.038 |
alert | +0.037 |
FB | +0.037 |
umber | +0.037 |
db | +0.036 |
Neg logit contributions | |
ingred | -0.044 |
Sect | -0.043 |
� | -0.043 |
ufact | -0.042 |
Voc | -0.041 |
Token | :// |
Token ID | 1378 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
ó | +0.032 |
alert | +0.030 |
FB | +0.030 |
umber | +0.029 |
Teddy | +0.029 |
Neg logit contributions | |
ingred | -0.073 |
Sect | -0.073 |
� | -0.072 |
ufact | -0.071 |
Voc | -0.070 |
Token | twitch |
Token ID | 31844 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ó | +0.161 |
FB | +0.155 |
alert | +0.155 |
umber | +0.154 |
db | +0.152 |
Neg logit contributions | |
ingred | -0.155 |
Sect | -0.153 |
� | -0.150 |
ufact | -0.148 |
Voc | -0.145 |
Token | . |
Token ID | 13 |
Feature activation | +6.41e-03 |
Pos logit contributions | |
ó | +0.077 |
alert | +0.074 |
FB | +0.074 |
umber | +0.073 |
Teddy | +0.072 |
Neg logit contributions | |
ingred | -0.094 |
Sect | -0.093 |
� | -0.091 |
ufact | -0.090 |
Voc | -0.088 |
Token | said |
Token ID | 531 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
ó | +0.007 |
FB | +0.006 |
alert | +0.006 |
umber | +0.006 |
Teddy | +0.006 |
Neg logit contributions | |
ingred | -0.008 |
Sect | -0.007 |
� | -0.007 |
ufact | -0.007 |
Voc | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
ó | +0.025 |
alert | +0.024 |
FB | +0.024 |
umber | +0.024 |
Teddy | +0.024 |
Neg logit contributions | |
ingred | -0.031 |
Sect | -0.030 |
� | -0.030 |
ufact | -0.029 |
Voc | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -5.30e-03 |
Pos logit contributions | |
ó | +0.007 |
alert | +0.007 |
FB | +0.007 |
umber | +0.007 |
Teddy | +0.007 |
Neg logit contributions | |
ingred | -0.009 |
Sect | -0.008 |
� | -0.008 |
ufact | -0.008 |
Voc | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -8.11e-03 |
Pos logit contributions | |
ó | +0.004 |
alert | +0.004 |
FB | +0.004 |
umber | +0.004 |
Teddy | +0.003 |
Neg logit contributions | |
ingred | -0.004 |
Sect | -0.004 |
� | -0.004 |
ufact | -0.004 |
Voc | -0.004 |
Token | G |
Token ID | 38 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
ó | +0.006 |
alert | +0.005 |
FB | +0.005 |
umber | +0.005 |
Teddy | +0.005 |
Neg logit contributions | |
ingred | -0.006 |
Sect | -0.006 |
� | -0.006 |
ufact | -0.006 |
Voc | -0.006 |
Token | ob |
Token ID | 672 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
ó | +0.070 |
alert | +0.068 |
FB | +0.067 |
Barney | +0.067 |
Teddy | +0.067 |
Neg logit contributions | |
ingred | -0.182 |
Sect | -0.179 |
� | -0.179 |
ufact | -0.177 |
Voc | -0.174 |
Token | ler |
Token ID | 1754 |
Feature activation | -9.26e-03 |
Pos logit contributions | |
ó | +0.204 |
FB | +0.197 |
alert | +0.197 |
umber | +0.195 |
Teddy | +0.194 |
Neg logit contributions | |
ingred | -0.214 |
Sect | -0.211 |
� | -0.208 |
ufact | -0.205 |
Voc | -0.201 |
Token | � |
Token ID | 447 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
ó | +0.006 |
alert | +0.006 |
FB | +0.006 |
umber | +0.006 |
Teddy | +0.006 |
Neg logit contributions | |
ingred | -0.007 |
Sect | -0.007 |
� | -0.007 |
ufact | -0.007 |
Voc | -0.007 |
Token | � |
Token ID | 247 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
ó | +0.017 |
FB | +0.016 |
alert | +0.016 |
umber | +0.016 |
Teddy | +0.016 |
Neg logit contributions | |
ingred | -0.016 |
Sect | -0.016 |
� | -0.015 |
ufact | -0.015 |
Voc | -0.015 |
Token | s |
Token ID | 82 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
ó | +0.013 |
alert | +0.013 |
FB | +0.013 |
umber | +0.012 |
Teddy | +0.012 |
Neg logit contributions | |
ingred | -0.016 |
Sect | -0.016 |
� | -0.016 |
ufact | -0.015 |
Voc | -0.015 |
Token | team |
Token ID | 1074 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
ó | +0.011 |
alert | +0.011 |
FB | +0.011 |
umber | +0.011 |
Teddy | +0.011 |
Neg logit contributions | |
ingred | -0.012 |
Sect | -0.012 |
� | -0.012 |
ufact | -0.012 |
Voc | -0.011 |
Token | love |
Token ID | 1842 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
ó | +0.009 |
alert | +0.009 |
FB | +0.009 |
umber | +0.009 |
Teddy | +0.008 |
Neg logit contributions | |
ingred | -0.010 |
Sect | -0.010 |
� | -0.010 |
ufact | -0.010 |
Voc | -0.009 |
Token | resurrect |
Token ID | 27603 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ingred | +0.062 |
Sect | +0.061 |
� | +0.060 |
ufact | +0.059 |
Voc | +0.058 |
Neg logit contributions | |
ó | -0.055 |
alert | -0.053 |
FB | -0.053 |
umber | -0.052 |
Teddy | -0.052 |
Token | ing |
Token ID | 278 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
ingred | +0.075 |
Sect | +0.074 |
ufact | +0.072 |
� | +0.072 |
Voc | +0.070 |
Neg logit contributions | |
ó | -0.078 |
alert | -0.075 |
FB | -0.075 |
umber | -0.074 |
ory | -0.074 |
Token | my |
Token ID | 616 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
ingred | +0.059 |
Sect | +0.058 |
� | +0.057 |
ufact | +0.057 |
Voc | +0.056 |
Neg logit contributions | |
ó | -0.051 |
alert | -0.049 |
FB | -0.049 |
umber | -0.048 |
Teddy | -0.048 |
Token | Do |
Token ID | 2141 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
ó | +0.019 |
alert | +0.019 |
FB | +0.019 |
umber | +0.018 |
Teddy | +0.018 |
Neg logit contributions | |
ingred | -0.021 |
Sect | -0.020 |
� | -0.020 |
ufact | -0.020 |
Voc | -0.019 |
Token | oms |
Token ID | 3150 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
ó | +0.031 |
alert | +0.029 |
FB | +0.029 |
umber | +0.029 |
Teddy | +0.029 |
Neg logit contributions | |
ingred | -0.070 |
Sect | -0.070 |
� | -0.069 |
ufact | -0.068 |
Voc | -0.067 |
Token | ayers |
Token ID | 6962 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
ó | +0.231 |
umber | +0.219 |
FB | +0.219 |
alert | +0.217 |
Teddy | +0.215 |
Neg logit contributions | |
ingred | -0.377 |
Sect | -0.369 |
� | -0.365 |
ufact | -0.364 |
Voc | -0.355 |
Token | , |
Token ID | 11 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
ó | +0.034 |
alert | +0.033 |
FB | +0.033 |
umber | +0.033 |
Teddy | +0.032 |
Neg logit contributions | |
ingred | -0.041 |
Sect | -0.040 |
� | -0.039 |
ufact | -0.039 |
Voc | -0.038 |
Token | too |
Token ID | 1165 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
ó | +0.012 |
FB | +0.012 |
alert | +0.012 |
umber | +0.012 |
Teddy | +0.012 |
Neg logit contributions | |
ingred | -0.014 |
Sect | -0.014 |
� | -0.013 |
ufact | -0.013 |
Voc | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
ó | +0.034 |
alert | +0.033 |
FB | +0.033 |
umber | +0.033 |
Teddy | +0.032 |
Neg logit contributions | |
ingred | -0.041 |
Sect | -0.041 |
� | -0.040 |
ufact | -0.040 |
Voc | -0.039 |
Token | That |
Token ID | 1320 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
ó | +0.013 |
alert | +0.012 |
FB | +0.012 |
umber | +0.012 |
db | +0.012 |
Neg logit contributions | |
ingred | -0.016 |
Sect | -0.016 |
� | -0.015 |
ufact | -0.015 |
Voc | -0.015 |
Token | This |
Token ID | 770 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
ó | +0.007 |
alert | +0.007 |
FB | +0.007 |
umber | +0.007 |
Teddy | +0.007 |
Neg logit contributions | |
ingred | -0.008 |
Sect | -0.008 |
� | -0.008 |
ufact | -0.008 |
Voc | -0.008 |
Token | is |
Token ID | 318 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
ó | +0.025 |
alert | +0.024 |
FB | +0.024 |
umber | +0.023 |
Teddy | +0.023 |
Neg logit contributions | |
ingred | -0.027 |
Sect | -0.026 |
� | -0.026 |
ufact | -0.026 |
Voc | -0.025 |
Token | not |
Token ID | 407 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
ó | +0.039 |
alert | +0.037 |
FB | +0.037 |
umber | +0.037 |
Teddy | +0.036 |
Neg logit contributions | |
ingred | -0.042 |
Sect | -0.042 |
� | -0.041 |
ufact | -0.041 |
Voc | -0.040 |
Token | some |
Token ID | 617 |
Feature activation | +9.85e-03 |
Pos logit contributions | |
ó | +0.020 |
alert | +0.020 |
FB | +0.020 |
umber | +0.019 |
Teddy | +0.019 |
Neg logit contributions | |
ingred | -0.021 |
Sect | -0.021 |
� | -0.020 |
ufact | -0.020 |
Voc | -0.019 |
Token | ed |
Token ID | 1225 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
ingred | +0.008 |
Sect | +0.008 |
� | +0.007 |
ufact | +0.007 |
Voc | +0.007 |
Neg logit contributions | |
ó | -0.007 |
FB | -0.007 |
alert | -0.007 |
umber | -0.007 |
Teddy | -0.007 |
Token | gy |
Token ID | 1360 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
ingred | +0.050 |
Sect | +0.050 |
� | +0.050 |
ufact | +0.049 |
Voc | +0.048 |
Neg logit contributions | |
ó | -0.023 |
FB | -0.022 |
alert | -0.022 |
umber | -0.021 |
Barney | -0.021 |
Token | new |
Token ID | 649 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
ó | +0.278 |
FB | +0.267 |
alert | +0.266 |
umber | +0.264 |
db | +0.261 |
Neg logit contributions | |
ingred | -0.317 |
Sect | -0.313 |
� | -0.308 |
ufact | -0.304 |
Voc | -0.299 |
Token | f |
Token ID | 277 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ingred | +0.187 |
Sect | +0.185 |
� | +0.182 |
ufact | +0.179 |
Voc | +0.177 |
Neg logit contributions | |
ó | -0.159 |
FB | -0.153 |
alert | -0.152 |
umber | -0.152 |
db | -0.149 |
Token | ad |
Token ID | 324 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
ó | +0.086 |
FB | +0.082 |
alert | +0.082 |
umber | +0.081 |
Teddy | +0.080 |
Neg logit contributions | |
ingred | -0.154 |
Sect | -0.153 |
� | -0.151 |
ufact | -0.149 |
Voc | -0.147 |
Token | that |
Token ID | 326 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
ó | +0.117 |
alert | +0.112 |
FB | +0.112 |
umber | +0.111 |
Teddy | +0.110 |
Neg logit contributions | |
ingred | -0.139 |
Sect | -0.137 |
� | -0.134 |
ufact | -0.133 |
Voc | -0.131 |
Token | can |
Token ID | 460 |
Feature activation | +8.03e-04 |
Pos logit contributions | |
ingred | +0.053 |
Sect | +0.052 |
� | +0.051 |
ufact | +0.050 |
Voc | +0.049 |
Neg logit contributions | |
ó | -0.050 |
alert | -0.048 |
FB | -0.047 |
umber | -0.047 |
Teddy | -0.047 |