Token | they |
Token ID | 484 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
dollars | +0.042 |
over | +0.042 |
wounds | +0.042 |
oster | +0.041 |
vet | +0.041 |
Neg logit contributions | |
Jan | -0.036 |
Jos | -0.035 |
Sus | -0.034 |
stair | -0.033 |
Suz | -0.033 |
Token | pretended |
Token ID | 36766 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Jan | +0.027 |
stair | +0.026 |
Sus | +0.025 |
Nice | +0.025 |
Suz | +0.025 |
Neg logit contributions | |
oster | -0.024 |
End | -0.024 |
dollars | -0.023 |
pig | -0.023 |
wounds | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Jan | +0.043 |
Jos | +0.042 |
aph | +0.042 |
icated | +0.041 |
Suz | +0.040 |
Neg logit contributions | |
wounds | -0.038 |
dollars | -0.037 |
over | -0.037 |
vet | -0.036 |
pig | -0.036 |
Token | go |
Token ID | 467 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
dollars | +0.004 |
over | +0.004 |
wounds | +0.004 |
oster | +0.004 |
vet | +0.004 |
Neg logit contributions | |
Jan | -0.004 |
Jos | -0.003 |
Sus | -0.003 |
Suz | -0.003 |
od | -0.003 |
Token | on |
Token ID | 319 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Jan | +0.013 |
Jos | +0.012 |
Sus | +0.012 |
Suz | +0.012 |
od | +0.012 |
Neg logit contributions | |
over | -0.016 |
dollars | -0.015 |
wounds | -0.015 |
oster | -0.015 |
vet | -0.015 |
Token | an |
Token ID | 281 |
Feature activation | +6.37e+00 |
Pos logit contributions | |
Jan | +0.028 |
Jos | +0.027 |
ous | +0.027 |
Suz | +0.026 |
od | +0.026 |
Neg logit contributions | |
wounds | -0.027 |
over | -0.027 |
dollars | -0.027 |
vet | -0.026 |
promises | -0.025 |
Token | adventure |
Token ID | 8855 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Jan | +0.143 |
Jos | +0.132 |
ous | +0.130 |
Sus | +0.128 |
Suz | +0.127 |
Neg logit contributions | |
End | -0.142 |
vet | -0.142 |
oster | -0.138 |
wounds | -0.138 |
dollars | -0.136 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Jan | +0.005 |
Jos | +0.005 |
Suz | +0.005 |
Sus | +0.005 |
stair | +0.005 |
Neg logit contributions | |
over | -0.005 |
dollars | -0.005 |
oster | -0.005 |
wounds | -0.005 |
vet | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Jan | +0.030 |
Jos | +0.029 |
Jo | +0.028 |
Sus | +0.028 |
Suz | +0.028 |
Neg logit contributions | |
dollars | -0.031 |
wounds | -0.031 |
oster | -0.030 |
over | -0.030 |
injuries | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
Jan | +0.029 |
Jos | +0.028 |
Sus | +0.027 |
Suz | +0.027 |
Jo | +0.027 |
Neg logit contributions | |
dollars | -0.021 |
over | -0.020 |
wounds | -0.020 |
promises | -0.019 |
oster | -0.019 |
Token | The |
Token ID | 464 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
Jan | +0.022 |
Jos | +0.021 |
stair | +0.021 |
od | +0.021 |
Sus | +0.020 |
Neg logit contributions | |
dollars | -0.019 |
wounds | -0.019 |
over | -0.019 |
promises | -0.018 |
pig | -0.018 |
Token | bird |
Token ID | 6512 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Jan | +0.038 |
stair | +0.037 |
Jos | +0.036 |
Sus | +0.036 |
Suz | +0.036 |
Neg logit contributions | |
over | -0.028 |
dollars | -0.027 |
oster | -0.027 |
wounds | -0.027 |
ages | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Jan | +0.031 |
Jos | +0.029 |
Sus | +0.028 |
Suz | +0.028 |
stair | +0.028 |
Neg logit contributions | |
dollars | -0.043 |
over | -0.043 |
wounds | -0.042 |
oster | -0.042 |
vet | -0.041 |
Token | set |
Token ID | 900 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
over | +0.038 |
dollars | +0.037 |
oster | +0.036 |
wounds | +0.035 |
End | +0.035 |
Neg logit contributions | |
Jan | -0.031 |
Jos | -0.029 |
Sus | -0.028 |
Suz | -0.028 |
Jo | -0.027 |
Token | off |
Token ID | 572 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
Jan | +0.022 |
Jos | +0.020 |
Sus | +0.019 |
Suz | +0.019 |
Jo | +0.019 |
Neg logit contributions | |
dollars | -0.034 |
over | -0.033 |
oster | -0.032 |
wounds | -0.032 |
vet | -0.032 |
Token | on |
Token ID | 319 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
Jan | +0.016 |
Jos | +0.016 |
stair | +0.015 |
Sus | +0.015 |
Suz | +0.015 |
Neg logit contributions | |
over | -0.019 |
dollars | -0.019 |
wounds | -0.019 |
oster | -0.019 |
vet | -0.019 |
Token | an |
Token ID | 281 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
Jan | +0.041 |
Jos | +0.040 |
Sus | +0.038 |
Suz | +0.038 |
stair | +0.038 |
Neg logit contributions | |
over | -0.045 |
dollars | -0.045 |
wounds | -0.045 |
oster | -0.044 |
vet | -0.044 |
Token | adventure |
Token ID | 8855 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
Jan | +0.138 |
Jos | +0.134 |
Sus | +0.128 |
ous | +0.126 |
od | +0.126 |
Neg logit contributions | |
vet | -0.146 |
wounds | -0.145 |
End | -0.140 |
dollars | -0.140 |
over | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
Jan | +0.008 |
Jos | +0.008 |
Sus | +0.008 |
Suz | +0.008 |
stair | +0.008 |
Neg logit contributions | |
over | -0.007 |
dollars | -0.006 |
wounds | -0.006 |
oster | -0.006 |
vet | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Jan | +0.025 |
Jos | +0.024 |
Sus | +0.023 |
stair | +0.023 |
od | +0.023 |
Neg logit contributions | |
over | -0.015 |
dollars | -0.015 |
oster | -0.015 |
wounds | -0.015 |
vet | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
Jan | +0.031 |
Jos | +0.030 |
Sus | +0.029 |
stair | +0.029 |
Suz | +0.029 |
Neg logit contributions | |
over | -0.017 |
oster | -0.017 |
dollars | -0.017 |
wounds | -0.017 |
vet | -0.016 |
Token | Soon |
Token ID | 28093 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
Jos | +0.021 |
Sus | +0.021 |
Jan | +0.021 |
ous | +0.021 |
stair | +0.020 |
Neg logit contributions | |
oster | -0.013 |
over | -0.012 |
End | -0.012 |
vet | -0.012 |
Spot | -0.011 |
Token | ! |
Token ID | 0 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Jan | +0.018 |
Jos | +0.017 |
Suz | +0.016 |
Sus | +0.016 |
stair | +0.016 |
Neg logit contributions | |
over | -0.021 |
dollars | -0.021 |
wounds | -0.019 |
oster | -0.019 |
promises | -0.019 |
Token | Let |
Token ID | 3914 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Jan | +0.030 |
Jo | +0.029 |
Sus | +0.028 |
Jos | +0.028 |
J | +0.028 |
Neg logit contributions | |
wounds | -0.043 |
dollars | -0.042 |
over | -0.041 |
injuries | -0.040 |
oster | -0.040 |
Token | 's |
Token ID | 338 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
dollars | +0.025 |
over | +0.024 |
wounds | +0.024 |
oster | +0.024 |
vet | +0.023 |
Neg logit contributions | |
Jan | -0.025 |
Jos | -0.024 |
Sus | -0.023 |
Suz | -0.023 |
stair | -0.023 |
Token | go |
Token ID | 467 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Jan | +0.026 |
Jos | +0.025 |
Sus | +0.024 |
Suz | +0.023 |
stair | +0.023 |
Neg logit contributions | |
dollars | -0.042 |
over | -0.042 |
wounds | -0.042 |
oster | -0.042 |
vet | -0.041 |
Token | on |
Token ID | 319 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Jan | +0.040 |
Jos | +0.039 |
od | +0.037 |
Sus | +0.037 |
stair | +0.037 |
Neg logit contributions | |
over | -0.045 |
dollars | -0.045 |
wounds | -0.045 |
oster | -0.044 |
vet | -0.044 |
Token | an |
Token ID | 281 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
Jan | +0.040 |
Jos | +0.039 |
ous | +0.038 |
od | +0.038 |
Suz | +0.038 |
Neg logit contributions | |
wounds | -0.035 |
over | -0.034 |
vet | -0.033 |
promises | -0.033 |
dollars | -0.033 |
Token | adventure |
Token ID | 8855 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
Jan | +0.154 |
Jos | +0.150 |
Sus | +0.146 |
Suz | +0.143 |
ous | +0.142 |
Neg logit contributions | |
vet | -0.127 |
wounds | -0.125 |
End | -0.125 |
dollars | -0.119 |
oster | -0.117 |
Token | around |
Token ID | 1088 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Jan | +0.007 |
Jos | +0.006 |
Suz | +0.006 |
Sus | +0.006 |
od | +0.006 |
Neg logit contributions | |
over | -0.008 |
dollars | -0.008 |
oster | -0.008 |
wounds | -0.008 |
vet | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
Jan | +0.038 |
Jos | +0.037 |
Sus | +0.036 |
Suz | +0.036 |
ous | +0.035 |
Neg logit contributions | |
over | -0.033 |
wounds | -0.032 |
dollars | -0.032 |
oster | -0.031 |
vet | -0.031 |
Token | planet |
Token ID | 5440 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
Jan | +0.068 |
Suz | +0.064 |
Jos | +0.064 |
Sus | +0.062 |
ous | +0.061 |
Neg logit contributions | |
End | -0.098 |
over | -0.097 |
wounds | -0.097 |
promises | -0.096 |
vet | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Jan | +0.018 |
Jos | +0.017 |
Sus | +0.017 |
Suz | +0.016 |
od | +0.016 |
Neg logit contributions | |
over | -0.019 |
dollars | -0.019 |
oster | -0.019 |
wounds | -0.019 |
vet | -0.019 |
Token | she |
Token ID | 673 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
dollars | +0.073 |
over | +0.073 |
oster | +0.072 |
wounds | +0.072 |
ages | +0.069 |
Neg logit contributions | |
Jan | -0.045 |
Jos | -0.041 |
Sus | -0.041 |
Suz | -0.039 |
J | -0.039 |
Token | wanted |
Token ID | 2227 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
over | +0.027 |
wounds | +0.026 |
dollars | +0.026 |
oster | +0.026 |
vet | +0.024 |
Neg logit contributions | |
Jan | -0.023 |
Jos | -0.021 |
Sus | -0.021 |
Suz | -0.021 |
od | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
vet | +0.020 |
wounds | +0.020 |
medicine | +0.019 |
pig | +0.019 |
dollars | +0.019 |
Neg logit contributions | |
Jan | -0.019 |
stair | -0.019 |
ous | -0.018 |
yt | -0.018 |
Jos | -0.018 |
Token | go |
Token ID | 467 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
vet | +0.031 |
promises | +0.027 |
pig | +0.026 |
wounds | +0.026 |
oster | +0.026 |
Neg logit contributions | |
ous | -0.034 |
Jos | -0.034 |
stair | -0.034 |
Jan | -0.033 |
od | -0.033 |
Token | on |
Token ID | 319 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
Jan | +0.015 |
ous | +0.015 |
od | +0.015 |
Jos | +0.015 |
icated | +0.015 |
Neg logit contributions | |
over | -0.015 |
wounds | -0.014 |
vet | -0.014 |
dollars | -0.014 |
promises | -0.014 |
Token | an |
Token ID | 281 |
Feature activation | +6.24e+00 |
Pos logit contributions | |
Jan | +0.018 |
Jos | +0.018 |
ous | +0.018 |
od | +0.017 |
Suz | +0.017 |
Neg logit contributions | |
over | -0.018 |
wounds | -0.018 |
dollars | -0.018 |
vet | -0.018 |
promises | -0.017 |
Token | adventure |
Token ID | 8855 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Jan | +0.148 |
Jos | +0.144 |
ous | +0.143 |
cast | +0.141 |
Sus | +0.139 |
Neg logit contributions | |
vet | -0.126 |
End | -0.123 |
wounds | -0.120 |
promises | -0.116 |
dollars | -0.113 |
Token | . |
Token ID | 13 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
over | +0.002 |
dollars | +0.002 |
wounds | +0.002 |
vet | +0.002 |
oster | +0.002 |
Neg logit contributions | |
Jan | -0.003 |
Jos | -0.003 |
Suz | -0.003 |
Sus | -0.003 |
od | -0.003 |
Token | The |
Token ID | 383 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
Jan | +0.010 |
Jos | +0.009 |
Sus | +0.009 |
Jo | +0.009 |
Suz | +0.009 |
Neg logit contributions | |
dollars | -0.008 |
wounds | -0.008 |
over | -0.008 |
oster | -0.008 |
injuries | -0.008 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
over | +0.006 |
dollars | +0.006 |
wounds | +0.006 |
oster | +0.006 |
vet | +0.006 |
Neg logit contributions | |
Jan | -0.013 |
Jos | -0.013 |
Sus | -0.012 |
Suz | -0.012 |
od | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
Jan | +0.027 |
Jos | +0.025 |
Sus | +0.025 |
Suz | +0.025 |
Jo | +0.025 |
Neg logit contributions | |
over | -0.030 |
dollars | -0.029 |
wounds | -0.029 |
injuries | -0.028 |
oster | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
dollars | +0.036 |
over | +0.035 |
oster | +0.035 |
wounds | +0.035 |
End | +0.034 |
Neg logit contributions | |
Jan | -0.026 |
Jos | -0.024 |
Sus | -0.024 |
Jo | -0.023 |
Suz | -0.023 |
Token | tide |
Token ID | 20013 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
Jan | +0.021 |
Jos | +0.020 |
Sus | +0.019 |
Suz | +0.018 |
od | +0.018 |
Neg logit contributions | |
wounds | -0.034 |
over | -0.034 |
End | -0.034 |
oster | -0.034 |
dollars | -0.033 |
Token | take |
Token ID | 1011 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
Jan | +0.050 |
Jos | +0.047 |
stair | +0.046 |
Sus | +0.045 |
od | +0.045 |
Neg logit contributions | |
wounds | -0.064 |
over | -0.064 |
dollars | -0.063 |
oster | -0.063 |
promises | -0.061 |
Token | him |
Token ID | 683 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
dollars | +0.008 |
wounds | +0.008 |
oster | +0.008 |
over | +0.008 |
vet | +0.008 |
Neg logit contributions | |
Jan | -0.007 |
Jos | -0.006 |
Sus | -0.006 |
Suz | -0.006 |
Jo | -0.006 |
Token | on |
Token ID | 319 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Jan | +0.016 |
Jos | +0.015 |
Sus | +0.015 |
stair | +0.014 |
Suz | +0.014 |
Neg logit contributions | |
over | -0.018 |
dollars | -0.018 |
wounds | -0.018 |
oster | -0.017 |
promises | -0.017 |
Token | an |
Token ID | 281 |
Feature activation | +6.23e+00 |
Pos logit contributions | |
Jan | +0.028 |
Jos | +0.027 |
Sus | +0.026 |
Suz | +0.025 |
od | +0.025 |
Neg logit contributions | |
over | -0.022 |
dollars | -0.022 |
wounds | -0.022 |
oster | -0.021 |
vet | -0.021 |
Token | adventure |
Token ID | 8855 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
Jan | +0.149 |
Jos | +0.141 |
od | +0.134 |
Sus | +0.133 |
Suz | +0.130 |
Neg logit contributions | |
End | -0.137 |
vet | -0.132 |
wounds | -0.132 |
dollars | -0.130 |
oster | -0.128 |
Token | . |
Token ID | 13 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
Jan | +0.001 |
Jos | +0.001 |
Sus | +0.001 |
Suz | +0.001 |
stair | +0.001 |
Neg logit contributions | |
over | -0.001 |
dollars | -0.001 |
oster | -0.001 |
wounds | -0.001 |
vet | -0.001 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
Jan | +0.013 |
Jos | +0.013 |
Sus | +0.012 |
Jo | +0.012 |
J | +0.012 |
Neg logit contributions | |
wounds | -0.011 |
dollars | -0.011 |
oster | -0.011 |
over | -0.011 |
injuries | -0.010 |
Token | M |
Token ID | 44 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
wounds | +0.079 |
dollars | +0.078 |
oster | +0.073 |
injuries | +0.071 |
promises | +0.071 |
Neg logit contributions | |
Jan | -0.076 |
Sus | -0.072 |
Jos | -0.071 |
Jo | -0.071 |
J | -0.070 |
Token | olly |
Token ID | 5098 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
wounds | +0.029 |
oster | +0.026 |
dollars | +0.026 |
over | +0.025 |
ages | +0.025 |
Neg logit contributions | |
Jan | -0.035 |
Jos | -0.033 |
Sus | -0.033 |
Jo | -0.032 |
Suz | -0.032 |
Token | they |
Token ID | 484 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
wounds | +0.002 |
oster | +0.002 |
dollars | +0.002 |
over | +0.002 |
vet | +0.002 |
Neg logit contributions | |
Jan | -0.002 |
Jos | -0.002 |
Sus | -0.002 |
Suz | -0.001 |
Jo | -0.001 |
Token | both |
Token ID | 1111 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
Jan | +0.045 |
Jos | +0.043 |
Sus | +0.042 |
Suz | +0.041 |
stair | +0.041 |
Neg logit contributions | |
dollars | -0.052 |
over | -0.051 |
oster | -0.051 |
wounds | -0.050 |
vet | -0.050 |
Token | set |
Token ID | 900 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
Jan | +0.018 |
Jos | +0.017 |
Sus | +0.017 |
Jo | +0.017 |
Suz | +0.017 |
Neg logit contributions | |
wounds | -0.021 |
over | -0.021 |
dollars | -0.021 |
oster | -0.020 |
vet | -0.020 |
Token | off |
Token ID | 572 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
Jan | +0.012 |
Jos | +0.011 |
Sus | +0.011 |
Suz | +0.010 |
Jo | +0.010 |
Neg logit contributions | |
dollars | -0.030 |
over | -0.030 |
oster | -0.030 |
wounds | -0.029 |
vet | -0.029 |
Token | on |
Token ID | 319 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
Jan | +0.017 |
icated | +0.016 |
Jos | +0.016 |
od | +0.016 |
ous | +0.016 |
Neg logit contributions | |
over | -0.018 |
dollars | -0.017 |
wounds | -0.017 |
vet | -0.016 |
pig | -0.016 |
Token | an |
Token ID | 281 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
Jan | +0.044 |
Jos | +0.043 |
ous | +0.042 |
od | +0.041 |
Suz | +0.041 |
Neg logit contributions | |
wounds | -0.045 |
over | -0.045 |
dollars | -0.045 |
vet | -0.043 |
promises | -0.043 |
Token | adventure |
Token ID | 8855 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Jan | +0.137 |
Jos | +0.132 |
od | +0.125 |
Sus | +0.124 |
J | +0.123 |
Neg logit contributions | |
wounds | -0.141 |
End | -0.140 |
dollars | -0.140 |
vet | -0.138 |
over | -0.135 |
Token | to |
Token ID | 284 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
Jan | +0.003 |
Jos | +0.003 |
Sus | +0.003 |
Suz | +0.003 |
od | +0.003 |
Neg logit contributions | |
over | -0.003 |
dollars | -0.003 |
wounds | -0.003 |
oster | -0.003 |
vet | -0.003 |
Token | find |
Token ID | 1064 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Jan | +0.001 |
Jos | +0.001 |
Sus | +0.001 |
Suz | +0.001 |
od | +0.001 |
Neg logit contributions | |
over | -0.002 |
dollars | -0.002 |
wounds | -0.002 |
oster | -0.002 |
vet | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Jan | +0.032 |
Jos | +0.030 |
Sus | +0.030 |
Suz | +0.029 |
od | +0.028 |
Neg logit contributions | |
over | -0.034 |
oster | -0.034 |
dollars | -0.034 |
wounds | -0.034 |
vet | -0.033 |
Token | muff |
Token ID | 27563 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
Jan | +0.045 |
Jos | +0.044 |
od | +0.041 |
Sus | +0.041 |
Suz | +0.041 |
Neg logit contributions | |
dollars | -0.048 |
vet | -0.047 |
over | -0.047 |
oster | -0.047 |
wounds | -0.046 |
Token | it |
Token ID | 340 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
oster | +0.026 |
over | +0.025 |
dollars | +0.024 |
wounds | +0.024 |
End | +0.023 |
Neg logit contributions | |
Jan | -0.017 |
Sus | -0.016 |
Jo | -0.016 |
Jos | -0.015 |
Suz | -0.015 |
Token | fits |
Token ID | 11414 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
Jan | +0.007 |
Jos | +0.007 |
Sus | +0.006 |
stair | +0.006 |
Jo | +0.006 |
Neg logit contributions | |
over | -0.008 |
wounds | -0.007 |
dollars | -0.007 |
oster | -0.007 |
End | -0.007 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Jan | +0.001 |
Jos | +0.001 |
Sus | +0.000 |
Suz | +0.000 |
od | +0.000 |
Neg logit contributions | |
dollars | -0.001 |
over | -0.001 |
oster | -0.001 |
wounds | -0.001 |
vet | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
vet | +0.019 |
over | +0.019 |
promises | +0.018 |
ages | +0.018 |
wounds | +0.018 |
Neg logit contributions | |
stair | -0.026 |
icated | -0.026 |
ous | -0.026 |
Jos | -0.026 |
cast | -0.025 |
Token | helped |
Token ID | 4193 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
dollars | +0.034 |
oster | +0.034 |
over | +0.033 |
wounds | +0.033 |
vet | +0.033 |
Neg logit contributions | |
Jan | -0.040 |
Jos | -0.038 |
stair | -0.037 |
Sus | -0.037 |
Suz | -0.037 |
Token | Sil |
Token ID | 4243 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
stair | +0.004 |
icated | +0.004 |
ous | +0.004 |
Jan | +0.003 |
Jos | +0.003 |
Neg logit contributions | |
over | -0.005 |
wounds | -0.005 |
vet | -0.005 |
pig | -0.005 |
oster | -0.004 |
Token | via |
Token ID | 8869 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
Jan | +0.135 |
Jos | +0.130 |
od | +0.126 |
Sus | +0.125 |
Suz | +0.123 |
Neg logit contributions | |
over | -0.136 |
wounds | -0.135 |
dollars | -0.135 |
vet | -0.132 |
oster | -0.132 |
Token | put |
Token ID | 1234 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
Jan | +0.064 |
Jos | +0.061 |
Sus | +0.059 |
Suz | +0.058 |
stair | +0.058 |
Neg logit contributions | |
dollars | -0.079 |
over | -0.079 |
wounds | -0.079 |
oster | -0.078 |
vet | -0.077 |
Token | on |
Token ID | 319 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
vet | +0.001 |
oster | +0.001 |
over | +0.001 |
dollars | +0.001 |
End | +0.001 |
Neg logit contributions | |
Jan | -0.000 |
Sus | -0.000 |
Jos | -0.000 |
Suz | -0.000 |
Jo | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Jan | +0.014 |
Sus | +0.013 |
Jos | +0.013 |
Jo | +0.013 |
Suz | +0.012 |
Neg logit contributions | |
oster | -0.024 |
over | -0.024 |
dollars | -0.023 |
End | -0.023 |
vet | -0.023 |
Token | coat |
Token ID | 13209 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Jan | +0.047 |
Jos | +0.046 |
stair | +0.045 |
Sus | +0.044 |
Jo | +0.044 |
Neg logit contributions | |
over | -0.044 |
dollars | -0.043 |
oster | -0.043 |
End | -0.041 |
vet | -0.041 |
Token | we |
Token ID | 356 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
Jan | +0.068 |
Jos | +0.067 |
stair | +0.063 |
Suz | +0.062 |
Jo | +0.062 |
Neg logit contributions | |
wounds | -0.047 |
dollars | -0.047 |
promises | -0.047 |
vet | -0.043 |
over | -0.042 |
Token | love |
Token ID | 1842 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
Jan | +0.013 |
Jos | +0.012 |
Sus | +0.012 |
od | +0.012 |
contain | +0.012 |
Neg logit contributions | |
over | -0.015 |
dollars | -0.015 |
wounds | -0.015 |
oster | -0.014 |
vet | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Jan | +0.012 |
Jos | +0.011 |
Sus | +0.011 |
Suz | +0.011 |
stair | +0.011 |
Neg logit contributions | |
over | -0.012 |
dollars | -0.012 |
wounds | -0.012 |
oster | -0.012 |
vet | -0.012 |
Token | Dancing |
Token ID | 31799 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
Jan | +0.024 |
Jos | +0.023 |
Sus | +0.023 |
Suz | +0.022 |
Jo | +0.022 |
Neg logit contributions | |
wounds | -0.024 |
dollars | -0.024 |
oster | -0.024 |
over | -0.024 |
injuries | -0.023 |
Token | helped |
Token ID | 4193 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Jan | +0.014 |
Jos | +0.013 |
Sus | +0.013 |
stair | +0.013 |
ous | +0.012 |
Neg logit contributions | |
over | -0.014 |
oster | -0.014 |
dollars | -0.014 |
wounds | -0.013 |
vet | -0.013 |
Token | Ros |
Token ID | 10018 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
Jan | +0.040 |
Jos | +0.039 |
stair | +0.038 |
Sus | +0.038 |
ous | +0.037 |
Neg logit contributions | |
over | -0.031 |
wounds | -0.030 |
dollars | -0.030 |
oster | -0.029 |
vet | -0.029 |
Token | ie |
Token ID | 494 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
Jan | +0.115 |
Jos | +0.109 |
Sus | +0.105 |
stair | +0.103 |
Suz | +0.103 |
Neg logit contributions | |
over | -0.157 |
dollars | -0.156 |
oster | -0.155 |
wounds | -0.154 |
vet | -0.149 |
Token | feel |
Token ID | 1254 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
Jan | +0.044 |
Jos | +0.041 |
Sus | +0.040 |
Suz | +0.040 |
stair | +0.039 |
Neg logit contributions | |
dollars | -0.073 |
over | -0.073 |
wounds | -0.070 |
oster | -0.070 |
End | -0.069 |
Token | better |
Token ID | 1365 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
dollars | +0.021 |
over | +0.020 |
wounds | +0.020 |
oster | +0.020 |
eros | +0.020 |
Neg logit contributions | |
Sus | -0.016 |
Jan | -0.016 |
Jos | -0.016 |
Suz | -0.015 |
sorts | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
oster | +0.043 |
wounds | +0.041 |
vet | +0.040 |
dollars | +0.040 |
over | +0.039 |
Neg logit contributions | |
Jan | -0.030 |
Jos | -0.028 |
Sus | -0.028 |
ous | -0.028 |
J | -0.028 |
Token | gave |
Token ID | 2921 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
over | +0.041 |
oster | +0.040 |
dollars | +0.040 |
wounds | +0.037 |
handcuffs | +0.036 |
Neg logit contributions | |
Jan | -0.030 |
Sus | -0.029 |
Jos | -0.028 |
Suz | -0.028 |
sorts | -0.027 |
Token | it |
Token ID | 340 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
Jan | +0.002 |
Sus | +0.002 |
Jos | +0.002 |
Suz | +0.002 |
J | +0.002 |
Neg logit contributions | |
vet | -0.003 |
over | -0.003 |
oster | -0.003 |
wounds | -0.003 |
dollars | -0.003 |
Token | on |
Token ID | 319 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
over | +0.015 |
dollars | +0.015 |
wounds | +0.015 |
oster | +0.015 |
vet | +0.014 |
Neg logit contributions | |
Jan | -0.013 |
Jos | -0.013 |
Sus | -0.012 |
od | -0.012 |
Suz | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Jan | +0.018 |
Jos | +0.017 |
Sus | +0.016 |
stair | +0.016 |
Suz | +0.016 |
Neg logit contributions | |
dollars | -0.020 |
over | -0.020 |
oster | -0.020 |
wounds | -0.020 |
vet | -0.019 |
Token | go |
Token ID | 467 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
over | +0.027 |
dollars | +0.027 |
oster | +0.026 |
wounds | +0.026 |
vet | +0.025 |
Neg logit contributions | |
Jan | -0.019 |
Jos | -0.018 |
Sus | -0.018 |
Suz | -0.017 |
Jo | -0.017 |
Token | on |
Token ID | 319 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Jan | +0.024 |
Jos | +0.023 |
od | +0.023 |
icated | +0.022 |
ous | +0.022 |
Neg logit contributions | |
over | -0.028 |
dollars | -0.028 |
wounds | -0.027 |
oster | -0.027 |
vet | -0.026 |
Token | an |
Token ID | 281 |
Feature activation | +6.21e+00 |
Pos logit contributions | |
Jan | +0.037 |
Jos | +0.036 |
ous | +0.035 |
od | +0.035 |
Suz | +0.035 |
Neg logit contributions | |
over | -0.041 |
wounds | -0.040 |
dollars | -0.040 |
vet | -0.039 |
injuries | -0.038 |
Token | expedition |
Token ID | 22817 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Jan | +0.143 |
ous | +0.133 |
Jos | +0.133 |
od | +0.130 |
Suz | +0.130 |
Neg logit contributions | |
wounds | -0.136 |
dollars | -0.133 |
End | -0.133 |
vet | -0.131 |
over | -0.125 |
Token | . |
Token ID | 13 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
over | +0.002 |
dollars | +0.002 |
wounds | +0.002 |
oster | +0.002 |
vet | +0.002 |
Neg logit contributions | |
Jan | -0.003 |
Jos | -0.003 |
Sus | -0.003 |
Suz | -0.003 |
od | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Jan | +0.019 |
Jos | +0.018 |
Sus | +0.018 |
Jo | +0.018 |
Suz | +0.018 |
Neg logit contributions | |
dollars | -0.017 |
over | -0.017 |
wounds | -0.017 |
oster | -0.017 |
vet | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
Jan | +0.027 |
Jos | +0.025 |
Sus | +0.025 |
Suz | +0.024 |
Jo | +0.024 |
Neg logit contributions | |
dollars | -0.019 |
over | -0.019 |
wounds | -0.019 |
oster | -0.018 |
vet | -0.018 |
Token | Mark |
Token ID | 9704 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
Jan | +0.016 |
Jos | +0.015 |
Sus | +0.014 |
stair | +0.014 |
Suz | +0.014 |
Neg logit contributions | |
dollars | -0.013 |
over | -0.013 |
wounds | -0.013 |
oster | -0.013 |
vet | -0.013 |
Token | so |
Token ID | 523 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Jan | +0.020 |
Jos | +0.019 |
Sus | +0.018 |
Suz | +0.018 |
stair | +0.017 |
Neg logit contributions | |
over | -0.033 |
dollars | -0.033 |
wounds | -0.032 |
oster | -0.032 |
vet | -0.032 |
Token | excited |
Token ID | 6568 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
over | +0.030 |
dollars | +0.030 |
wounds | +0.030 |
oster | +0.030 |
vet | +0.029 |
Neg logit contributions | |
Jan | -0.035 |
Jos | -0.034 |
Sus | -0.033 |
stair | -0.032 |
Suz | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
Jan | +0.013 |
Jos | +0.012 |
stair | +0.012 |
Suz | +0.011 |
Sus | +0.011 |
Neg logit contributions | |
over | -0.013 |
dollars | -0.013 |
wounds | -0.013 |
vet | -0.012 |
oster | -0.012 |
Token | go |
Token ID | 467 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
oster | +0.011 |
vet | +0.011 |
wounds | +0.011 |
over | +0.011 |
promises | +0.011 |
Neg logit contributions | |
Jan | -0.010 |
Jos | -0.010 |
od | -0.010 |
stair | -0.010 |
ous | -0.010 |
Token | on |
Token ID | 319 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Jan | +0.029 |
Jos | +0.028 |
od | +0.027 |
stair | +0.026 |
icated | +0.026 |
Neg logit contributions | |
over | -0.029 |
dollars | -0.028 |
wounds | -0.028 |
oster | -0.028 |
vet | -0.028 |
Token | an |
Token ID | 281 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
Jan | +0.044 |
Jos | +0.043 |
od | +0.042 |
ous | +0.042 |
Suz | +0.041 |
Neg logit contributions | |
over | -0.042 |
wounds | -0.041 |
dollars | -0.040 |
vet | -0.040 |
promises | -0.039 |
Token | adventure |
Token ID | 8855 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Jan | +0.143 |
Jos | +0.135 |
ous | +0.129 |
od | +0.128 |
Sus | +0.128 |
Neg logit contributions | |
End | -0.136 |
vet | -0.135 |
wounds | -0.134 |
dollars | -0.132 |
oster | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Jan | +0.010 |
Jos | +0.009 |
Suz | +0.009 |
od | +0.009 |
Sus | +0.009 |
Neg logit contributions | |
over | -0.009 |
dollars | -0.008 |
oster | -0.008 |
wounds | -0.008 |
vet | -0.008 |
Token | It |
Token ID | 632 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
Jan | +0.029 |
Jos | +0.028 |
Sus | +0.027 |
J | +0.027 |
Suz | +0.027 |
Neg logit contributions | |
wounds | -0.032 |
dollars | -0.032 |
injuries | -0.030 |
oster | -0.030 |
over | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Jan | +0.022 |
Jos | +0.021 |
stair | +0.020 |
Sus | +0.020 |
od | +0.020 |
Neg logit contributions | |
oster | -0.021 |
over | -0.021 |
dollars | -0.021 |
wounds | -0.020 |
vet | -0.020 |
Token | so |
Token ID | 523 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Jan | +0.016 |
Jos | +0.016 |
stair | +0.016 |
od | +0.015 |
ous | +0.015 |
Neg logit contributions | |
over | -0.029 |
dollars | -0.028 |
oster | -0.028 |
End | -0.028 |
vet | -0.028 |
Token | He |
Token ID | 679 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
Jan | +0.027 |
Jos | +0.025 |
Suz | +0.025 |
Sus | +0.025 |
J | +0.024 |
Neg logit contributions | |
dollars | -0.023 |
wounds | -0.022 |
over | -0.022 |
oster | -0.022 |
injuries | -0.021 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
Jan | +0.007 |
Jos | +0.006 |
Sus | +0.006 |
Suz | +0.006 |
stair | +0.006 |
Neg logit contributions | |
dollars | -0.007 |
over | -0.007 |
wounds | -0.007 |
oster | -0.007 |
vet | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
Jos | +0.004 |
Jan | +0.004 |
yt | +0.003 |
od | +0.003 |
Sus | +0.003 |
Neg logit contributions | |
vet | -0.004 |
wounds | -0.004 |
dollars | -0.004 |
pig | -0.004 |
over | -0.004 |
Token | go |
Token ID | 467 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
vet | +0.013 |
wounds | +0.012 |
promises | +0.012 |
over | +0.012 |
pig | +0.012 |
Neg logit contributions | |
Jos | -0.012 |
Jan | -0.011 |
ous | -0.011 |
Sus | -0.011 |
icated | -0.011 |
Token | on |
Token ID | 319 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Jos | +0.034 |
od | +0.034 |
ous | +0.033 |
icated | +0.033 |
Jan | +0.033 |
Neg logit contributions | |
over | -0.027 |
vet | -0.027 |
pig | -0.026 |
promises | -0.026 |
wounds | -0.026 |
Token | an |
Token ID | 281 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
Jan | +0.031 |
Jos | +0.030 |
ous | +0.029 |
od | +0.029 |
Sus | +0.028 |
Neg logit contributions | |
over | -0.032 |
wounds | -0.031 |
vet | -0.031 |
promises | -0.030 |
dollars | -0.030 |
Token | adventure |
Token ID | 8855 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
Jan | +0.145 |
Jos | +0.143 |
ous | +0.137 |
Sus | +0.136 |
od | +0.134 |
Neg logit contributions | |
vet | -0.134 |
End | -0.129 |
wounds | -0.128 |
promises | -0.121 |
dollars | -0.121 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Jan | +0.002 |
Jos | +0.002 |
od | +0.001 |
icated | +0.001 |
Sus | +0.001 |
Neg logit contributions | |
over | -0.001 |
dollars | -0.001 |
vet | -0.001 |
oster | -0.001 |
pig | -0.001 |
Token | So |
Token ID | 1406 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
Jan | +0.024 |
Suz | +0.022 |
J | +0.021 |
Sus | +0.021 |
Jos | +0.021 |
Neg logit contributions | |
dollars | -0.024 |
wounds | -0.023 |
oster | -0.023 |
over | -0.022 |
injuries | -0.022 |
Token | he |
Token ID | 339 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
dollars | +0.010 |
wounds | +0.010 |
oster | +0.010 |
over | +0.010 |
etchup | +0.009 |
Neg logit contributions | |
Jan | -0.007 |
Suz | -0.006 |
Sus | -0.006 |
Jos | -0.006 |
J | -0.006 |
Token | hopped |
Token ID | 45230 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
Jan | +0.011 |
Jos | +0.011 |
Sus | +0.010 |
Suz | +0.010 |
stair | +0.010 |
Neg logit contributions | |
over | -0.013 |
dollars | -0.013 |
wounds | -0.013 |
oster | -0.012 |
vet | -0.012 |
Token | group |
Token ID | 1448 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
dollars | +0.024 |
over | +0.024 |
wounds | +0.024 |
ages | +0.023 |
aid | +0.023 |
Neg logit contributions | |
J | -0.020 |
Jan | -0.020 |
Jos | -0.020 |
tw | -0.019 |
stair | -0.019 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Jan | +0.043 |
Jos | +0.042 |
Sus | +0.040 |
Suz | +0.040 |
stair | +0.040 |
Neg logit contributions | |
over | -0.046 |
dollars | -0.045 |
oster | -0.045 |
vet | -0.044 |
wounds | -0.044 |
Token | to |
Token ID | 284 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
vet | +0.007 |
wounds | +0.007 |
dollars | +0.007 |
over | +0.007 |
oster | +0.007 |
Neg logit contributions | |
Jan | -0.005 |
Jos | -0.005 |
stair | -0.005 |
Sus | -0.005 |
Suz | -0.005 |
Token | go |
Token ID | 467 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
vet | +0.025 |
over | +0.025 |
oster | +0.025 |
wounds | +0.025 |
dollars | +0.024 |
Neg logit contributions | |
Jan | -0.020 |
Jos | -0.019 |
stair | -0.018 |
Sus | -0.018 |
ous | -0.018 |
Token | on |
Token ID | 319 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Jan | +0.029 |
Jos | +0.028 |
od | +0.028 |
ous | +0.028 |
stair | +0.027 |
Neg logit contributions | |
over | -0.026 |
vet | -0.025 |
wounds | -0.025 |
pig | -0.025 |
promises | -0.025 |
Token | an |
Token ID | 281 |
Feature activation | +6.18e+00 |
Pos logit contributions | |
Jan | +0.025 |
Jos | +0.024 |
ous | +0.024 |
od | +0.023 |
Suz | +0.023 |
Neg logit contributions | |
over | -0.025 |
wounds | -0.024 |
vet | -0.024 |
dollars | -0.024 |
promises | -0.024 |
Token | adventure |
Token ID | 8855 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Jan | +0.143 |
Jos | +0.137 |
ous | +0.134 |
Sus | +0.131 |
od | +0.130 |
Neg logit contributions | |
vet | -0.136 |
End | -0.133 |
wounds | -0.129 |
dollars | -0.128 |
over | -0.126 |
Token | . |
Token ID | 13 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
over | +0.004 |
dollars | +0.004 |
vet | +0.003 |
oster | +0.003 |
wounds | +0.003 |
Neg logit contributions | |
Jan | -0.005 |
Jos | -0.004 |
Suz | -0.004 |
Sus | -0.004 |
od | -0.004 |
Token | Anch |
Token ID | 29253 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
Jos | +0.017 |
stair | +0.017 |
icated | +0.017 |
Jan | +0.017 |
od | +0.017 |
Neg logit contributions | |
vet | -0.011 |
over | -0.011 |
dollars | -0.011 |
pig | -0.010 |
ages | -0.010 |
Token | or |
Token ID | 273 |
Feature activation | -9.61e-03 |
Pos logit contributions | |
Jan | +0.071 |
Jos | +0.067 |
Sus | +0.065 |
stair | +0.064 |
Suz | +0.064 |
Neg logit contributions | |
dollars | -0.086 |
over | -0.086 |
oster | -0.085 |
wounds | -0.083 |
vet | -0.081 |
Token | looked |
Token ID | 3114 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
wounds | +0.000 |
dollars | +0.000 |
vet | +0.000 |
injuries | +0.000 |
End | +0.000 |
Neg logit contributions | |
Jan | -0.000 |
Sus | -0.000 |
Jos | -0.000 |
J | -0.000 |
od | -0.000 |
Token | barn |
Token ID | 25203 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
dollars | +0.020 |
oster | +0.020 |
over | +0.020 |
wounds | +0.019 |
etchup | +0.019 |
Neg logit contributions | |
Jan | -0.024 |
stair | -0.023 |
Sus | -0.022 |
Jos | -0.022 |
Suz | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
dollars | +0.041 |
oster | +0.040 |
wounds | +0.040 |
over | +0.040 |
etchup | +0.039 |
Neg logit contributions | |
Jan | -0.033 |
Jos | -0.030 |
Sus | -0.030 |
Suz | -0.030 |
Jo | -0.029 |
Token | set |
Token ID | 900 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
dollars | +0.033 |
over | +0.033 |
oster | +0.032 |
wounds | +0.032 |
vet | +0.031 |
Neg logit contributions | |
Jan | -0.029 |
Jos | -0.027 |
Sus | -0.027 |
Suz | -0.026 |
Jo | -0.026 |
Token | off |
Token ID | 572 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
Jan | +0.011 |
Jos | +0.010 |
Sus | +0.009 |
Suz | +0.009 |
Jo | +0.009 |
Neg logit contributions | |
dollars | -0.033 |
over | -0.032 |
oster | -0.032 |
wounds | -0.032 |
vet | -0.032 |
Token | on |
Token ID | 319 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
Jan | +0.018 |
Jos | +0.018 |
stair | +0.017 |
icated | +0.017 |
od | +0.017 |
Neg logit contributions | |
over | -0.021 |
dollars | -0.021 |
wounds | -0.021 |
oster | -0.020 |
vet | -0.020 |
Token | an |
Token ID | 281 |
Feature activation | +6.18e+00 |
Pos logit contributions | |
Jan | +0.042 |
Jos | +0.040 |
Sus | +0.039 |
Suz | +0.038 |
stair | +0.038 |
Neg logit contributions | |
over | -0.046 |
dollars | -0.045 |
wounds | -0.045 |
oster | -0.044 |
vet | -0.043 |
Token | adventure |
Token ID | 8855 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
Jan | +0.131 |
Jos | +0.126 |
Sus | +0.120 |
od | +0.119 |
ous | +0.119 |
Neg logit contributions | |
End | -0.143 |
vet | -0.142 |
wounds | -0.141 |
dollars | -0.141 |
over | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Jan | +0.010 |
Jos | +0.009 |
Sus | +0.009 |
Suz | +0.009 |
stair | +0.009 |
Neg logit contributions | |
dollars | -0.008 |
over | -0.008 |
wounds | -0.008 |
oster | -0.008 |
vet | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Jan | +0.027 |
Jos | +0.025 |
Sus | +0.024 |
Suz | +0.024 |
J | +0.024 |
Neg logit contributions | |
dollars | -0.025 |
wounds | -0.025 |
oster | -0.024 |
over | -0.024 |
injuries | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
Jan | +0.029 |
Jos | +0.027 |
Suz | +0.027 |
Sus | +0.026 |
Jo | +0.026 |
Neg logit contributions | |
dollars | -0.024 |
wounds | -0.023 |
over | -0.022 |
promises | -0.022 |
injuries | -0.021 |
Token | As |
Token ID | 1722 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
Jan | +0.020 |
Jos | +0.019 |
Sus | +0.019 |
Suz | +0.019 |
od | +0.018 |
Neg logit contributions | |
dollars | -0.017 |
wounds | -0.016 |
over | -0.016 |
oster | -0.016 |
vet | -0.015 |
Token | fork |
Token ID | 15563 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
Jan | +0.024 |
Jos | +0.023 |
Sus | +0.023 |
stair | +0.023 |
Suz | +0.022 |
Neg logit contributions | |
over | -0.023 |
dollars | -0.023 |
oster | -0.022 |
wounds | -0.022 |
vet | -0.022 |
Token | got |
Token ID | 1392 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
over | +0.017 |
dollars | +0.017 |
wounds | +0.017 |
oster | +0.017 |
vet | +0.017 |
Neg logit contributions | |
Jan | -0.014 |
Jos | -0.013 |
Sus | -0.013 |
Suz | -0.012 |
ous | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Jan | +0.032 |
Sus | +0.030 |
Jos | +0.030 |
Suz | +0.029 |
J | +0.028 |
Neg logit contributions | |
over | -0.048 |
dollars | -0.048 |
oster | -0.047 |
wounds | -0.047 |
vet | -0.046 |
Token | go |
Token ID | 467 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
Jan | +0.006 |
Jos | +0.005 |
Sus | +0.005 |
Suz | +0.005 |
Jo | +0.005 |
Neg logit contributions | |
dollars | -0.009 |
over | -0.008 |
wounds | -0.008 |
oster | -0.008 |
vet | -0.008 |
Token | on |
Token ID | 319 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Jan | +0.016 |
Jos | +0.015 |
Sus | +0.015 |
Suz | +0.015 |
stair | +0.015 |
Neg logit contributions | |
over | -0.019 |
dollars | -0.019 |
wounds | -0.019 |
oster | -0.019 |
vet | -0.019 |
Token | an |
Token ID | 281 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
Jan | +0.033 |
Jos | +0.031 |
Sus | +0.030 |
Suz | +0.030 |
od | +0.030 |
Neg logit contributions | |
over | -0.034 |
dollars | -0.034 |
wounds | -0.034 |
oster | -0.033 |
vet | -0.033 |
Token | adventure |
Token ID | 8855 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
Jan | +0.136 |
Jos | +0.130 |
od | +0.127 |
ous | +0.125 |
Sus | +0.123 |
Neg logit contributions | |
End | -0.141 |
vet | -0.138 |
dollars | -0.137 |
wounds | -0.134 |
over | -0.133 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Jan | +0.002 |
Jos | +0.002 |
Sus | +0.002 |
Suz | +0.002 |
stair | +0.002 |
Neg logit contributions | |
dollars | -0.002 |
over | -0.002 |
wounds | -0.002 |
oster | -0.002 |
vet | -0.002 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
Jan | +0.024 |
Sus | +0.023 |
Jos | +0.023 |
Suz | +0.023 |
Jo | +0.023 |
Neg logit contributions | |
wounds | -0.022 |
dollars | -0.022 |
oster | -0.021 |
over | -0.021 |
injuries | -0.020 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
wounds | +0.073 |
dollars | +0.072 |
oster | +0.068 |
over | +0.066 |
vet | +0.066 |
Neg logit contributions | |
Jan | -0.076 |
Sus | -0.072 |
Jos | -0.072 |
Jo | -0.071 |
Suz | -0.070 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Jan | +0.024 |
Jos | +0.023 |
od | +0.022 |
icated | +0.022 |
Sus | +0.022 |
Neg logit contributions | |
over | -0.036 |
dollars | -0.036 |
End | -0.036 |
oster | -0.035 |
wounds | -0.035 |
Token | there |
Token ID | 612 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
Jan | +0.028 |
Jos | +0.027 |
Sus | +0.026 |
Suz | +0.026 |
Jo | +0.025 |
Neg logit contributions | |
over | -0.038 |
wounds | -0.038 |
dollars | -0.038 |
oster | -0.037 |
vet | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Jan | +0.018 |
Jos | +0.018 |
Sus | +0.017 |
stair | +0.017 |
Suz | +0.017 |
Neg logit contributions | |
over | -0.021 |
dollars | -0.021 |
wounds | -0.020 |
oster | -0.020 |
vet | -0.020 |
Token | take |
Token ID | 1011 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
dollars | +0.043 |
over | +0.043 |
wounds | +0.042 |
oster | +0.042 |
vet | +0.041 |
Neg logit contributions | |
Jan | -0.032 |
Jos | -0.030 |
Sus | -0.030 |
Suz | -0.029 |
stair | -0.028 |
Token | him |
Token ID | 683 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
wounds | +0.011 |
dollars | +0.011 |
oster | +0.011 |
End | +0.010 |
vet | +0.010 |
Neg logit contributions | |
Jan | -0.008 |
Sus | -0.008 |
Jos | -0.008 |
J | -0.008 |
Jo | -0.008 |
Token | on |
Token ID | 319 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Jan | +0.017 |
Jos | +0.016 |
Sus | +0.016 |
Suz | +0.015 |
stair | +0.015 |
Neg logit contributions | |
over | -0.025 |
dollars | -0.025 |
wounds | -0.025 |
oster | -0.025 |
vet | -0.024 |
Token | an |
Token ID | 281 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
Jan | +0.022 |
Jos | +0.021 |
Sus | +0.021 |
Suz | +0.020 |
stair | +0.020 |
Neg logit contributions | |
dollars | -0.025 |
over | -0.025 |
oster | -0.025 |
wounds | -0.025 |
vet | -0.024 |
Token | amazing |
Token ID | 4998 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Jan | +0.130 |
Jos | +0.122 |
Sus | +0.116 |
Suz | +0.116 |
od | +0.114 |
Neg logit contributions | |
dollars | -0.148 |
wounds | -0.147 |
vet | -0.145 |
End | -0.144 |
oster | -0.144 |
Token | adventure |
Token ID | 8855 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
Jan | +0.037 |
Jos | +0.036 |
od | +0.034 |
Suz | +0.033 |
Sus | +0.032 |
Neg logit contributions | |
over | -0.038 |
oster | -0.037 |
dollars | -0.037 |
pig | -0.037 |
End | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
wounds | +0.008 |
dollars | +0.008 |
oster | +0.008 |
over | +0.008 |
vet | +0.008 |
Neg logit contributions | |
Jan | -0.007 |
Jos | -0.006 |
Sus | -0.006 |
Suz | -0.006 |
stair | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Jan | +0.031 |
Jos | +0.030 |
Sus | +0.030 |
J | +0.030 |
Suz | +0.029 |
Neg logit contributions | |
wounds | -0.034 |
dollars | -0.034 |
oster | -0.033 |
injuries | -0.032 |
over | -0.032 |
Token | were |
Token ID | 547 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Jan | +0.035 |
Jos | +0.033 |
stair | +0.033 |
Sus | +0.032 |
Suz | +0.031 |
Neg logit contributions | |
dollars | -0.040 |
oster | -0.039 |
over | -0.039 |
wounds | -0.038 |
vet | -0.038 |
Token | out |
Token ID | 503 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
Jan | +0.014 |
Jos | +0.014 |
Sus | +0.013 |
Suz | +0.013 |
stair | +0.013 |
Neg logit contributions | |
over | -0.016 |
dollars | -0.016 |
wounds | -0.015 |
oster | -0.015 |
vet | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
Jan | +0.014 |
Sus | +0.013 |
Jo | +0.013 |
Jos | +0.012 |
Suz | +0.012 |
Neg logit contributions | |
oster | -0.022 |
over | -0.021 |
etchup | -0.020 |
ages | -0.020 |
vet | -0.019 |
Token | set |
Token ID | 900 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
wounds | +0.019 |
vet | +0.019 |
over | +0.019 |
dollars | +0.019 |
oster | +0.019 |
Neg logit contributions | |
Jan | -0.014 |
Jos | -0.013 |
od | -0.013 |
Sus | -0.013 |
ous | -0.012 |
Token | off |
Token ID | 572 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
Jan | +0.010 |
Jos | +0.010 |
Sus | +0.009 |
stair | +0.009 |
Suz | +0.009 |
Neg logit contributions | |
wounds | -0.022 |
over | -0.022 |
dollars | -0.022 |
oster | -0.021 |
vet | -0.021 |
Token | on |
Token ID | 319 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Jan | +0.002 |
Jos | +0.002 |
Sus | +0.002 |
stair | +0.002 |
ous | +0.002 |
Neg logit contributions | |
over | -0.002 |
dollars | -0.002 |
wounds | -0.002 |
oster | -0.002 |
vet | -0.002 |
Token | an |
Token ID | 281 |
Feature activation | +6.16e+00 |
Pos logit contributions | |
Jan | +0.034 |
ous | +0.033 |
Jos | +0.032 |
Sus | +0.031 |
Suz | +0.031 |
Neg logit contributions | |
wounds | -0.035 |
over | -0.034 |
dollars | -0.034 |
vet | -0.033 |
promises | -0.033 |
Token | adventure |
Token ID | 8855 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Jan | +0.147 |
Jos | +0.146 |
Sus | +0.142 |
ous | +0.139 |
od | +0.137 |
Neg logit contributions | |
vet | -0.129 |
wounds | -0.126 |
End | -0.122 |
pig | -0.117 |
dollars | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
over | +0.005 |
dollars | +0.005 |
wounds | +0.005 |
oster | +0.005 |
vet | +0.005 |
Neg logit contributions | |
Jan | -0.008 |
Jos | -0.007 |
Sus | -0.007 |
Suz | -0.007 |
stair | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Jan | +0.023 |
Sus | +0.022 |
Suz | +0.021 |
Jo | +0.021 |
Jos | +0.021 |
Neg logit contributions | |
dollars | -0.026 |
wounds | -0.026 |
over | -0.025 |
injuries | -0.025 |
oster | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +8.80e-01 |
Pos logit contributions | |
Jan | +0.036 |
Jos | +0.034 |
Sus | +0.034 |
Suz | +0.033 |
Jo | +0.033 |
Neg logit contributions | |
dollars | -0.026 |
over | -0.025 |
wounds | -0.025 |
oster | -0.024 |
vet | -0.024 |
Token | He |
Token ID | 1544 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Jan | +0.021 |
Jos | +0.020 |
stair | +0.019 |
Sus | +0.019 |
Suz | +0.019 |
Neg logit contributions | |
dollars | -0.018 |
wounds | -0.018 |
over | -0.018 |
promises | -0.017 |
oster | -0.017 |
Token | Andy |
Token ID | 12382 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
Jos | +0.047 |
od | +0.046 |
Jan | +0.045 |
J | +0.043 |
stair | +0.043 |
Neg logit contributions | |
wounds | -0.081 |
over | -0.080 |
vet | -0.080 |
promises | -0.079 |
dollars | -0.079 |
Token | decided |
Token ID | 3066 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Jan | +0.054 |
Jos | +0.052 |
Sus | +0.050 |
od | +0.049 |
J | +0.049 |
Neg logit contributions | |
dollars | -0.063 |
over | -0.062 |
wounds | -0.062 |
oster | -0.061 |
vet | -0.059 |
Token | to |
Token ID | 284 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
Jan | +0.005 |
Jos | +0.004 |
Suz | +0.004 |
Sus | +0.004 |
stair | +0.004 |
Neg logit contributions | |
dollars | -0.007 |
wounds | -0.007 |
over | -0.007 |
vet | -0.007 |
oster | -0.006 |
Token | go |
Token ID | 467 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
over | +0.022 |
oster | +0.022 |
dollars | +0.022 |
vet | +0.022 |
wounds | +0.022 |
Neg logit contributions | |
Jan | -0.016 |
Jos | -0.016 |
Sus | -0.015 |
Suz | -0.015 |
stair | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Jan | +0.036 |
Jos | +0.035 |
od | +0.034 |
ous | +0.034 |
Sus | +0.034 |
Neg logit contributions | |
over | -0.035 |
wounds | -0.035 |
vet | -0.034 |
dollars | -0.034 |
promises | -0.033 |
Token | an |
Token ID | 281 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
ous | +0.028 |
Jan | +0.027 |
Jos | +0.027 |
od | +0.027 |
Suz | +0.026 |
Neg logit contributions | |
over | -0.022 |
wounds | -0.022 |
vet | -0.022 |
promises | -0.021 |
injuries | -0.021 |
Token | adventure |
Token ID | 8855 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Jan | +0.148 |
Jos | +0.145 |
ous | +0.139 |
Sus | +0.139 |
Suz | +0.136 |
Neg logit contributions | |
vet | -0.127 |
End | -0.126 |
wounds | -0.121 |
dollars | -0.119 |
promises | -0.117 |
Token | and |
Token ID | 290 |
Feature activation | -9.77e-01 |
Pos logit contributions | |
over | +0.004 |
dollars | +0.003 |
wounds | +0.003 |
vet | +0.003 |
oster | +0.003 |
Neg logit contributions | |
Jan | -0.004 |
Jos | -0.004 |
Suz | -0.004 |
Sus | -0.004 |
od | -0.004 |
Token | explore |
Token ID | 7301 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
vet | +0.025 |
over | +0.024 |
wounds | +0.024 |
promises | +0.024 |
oster | +0.024 |
Neg logit contributions | |
Jan | -0.017 |
Jos | -0.016 |
od | -0.016 |
ous | -0.015 |
stair | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Jan | +0.040 |
Jos | +0.039 |
ous | +0.038 |
Sus | +0.037 |
Suz | +0.037 |
Neg logit contributions | |
over | -0.032 |
wounds | -0.032 |
dollars | -0.031 |
promises | -0.031 |
vet | -0.030 |
Token | park |
Token ID | 3952 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Jan | +0.050 |
Jos | +0.048 |
Suz | +0.047 |
ous | +0.047 |
Sus | +0.046 |
Neg logit contributions | |
over | -0.039 |
vet | -0.039 |
wounds | -0.039 |
promises | -0.038 |
dollars | -0.038 |
Token | o |
Token ID | 78 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
Jan | +0.051 |
stair | +0.050 |
contain | +0.049 |
Jos | +0.049 |
Sus | +0.048 |
Neg logit contributions | |
oster | -0.050 |
over | -0.050 |
dollars | -0.049 |
wounds | -0.047 |
etchup | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
Jan | +0.015 |
Sus | +0.014 |
Jo | +0.014 |
J | +0.014 |
Jos | +0.014 |
Neg logit contributions | |
wounds | -0.023 |
dollars | -0.023 |
over | -0.022 |
End | -0.022 |
aid | -0.022 |
Token | He |
Token ID | 679 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
Jan | +0.019 |
Jos | +0.019 |
Sus | +0.018 |
Suz | +0.018 |
stair | +0.018 |
Neg logit contributions | |
over | -0.021 |
dollars | -0.021 |
wounds | -0.020 |
oster | -0.020 |
vet | -0.020 |
Token | helped |
Token ID | 4193 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
over | +0.009 |
dollars | +0.009 |
wounds | +0.009 |
injuries | +0.009 |
oster | +0.009 |
Neg logit contributions | |
Jan | -0.007 |
Sus | -0.006 |
Suz | -0.006 |
Jo | -0.006 |
Jos | -0.006 |
Token | G |
Token ID | 402 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
Jan | +0.012 |
Jos | +0.011 |
stair | +0.011 |
od | +0.011 |
Sus | +0.011 |
Neg logit contributions | |
over | -0.016 |
oster | -0.016 |
wounds | -0.016 |
dollars | -0.016 |
vet | -0.016 |
Token | iz |
Token ID | 528 |
Feature activation | +6.13e+00 |
Pos logit contributions | |
contain | +0.059 |
stair | +0.055 |
Jan | +0.054 |
icated | +0.054 |
sorts | +0.054 |
Neg logit contributions | |
oster | -0.087 |
wounds | -0.086 |
dollars | -0.082 |
End | -0.082 |
eros | -0.081 |
Token | mo |
Token ID | 5908 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Jan | +0.133 |
Jos | +0.125 |
Sus | +0.123 |
Suz | +0.122 |
Jo | +0.119 |
Neg logit contributions | |
over | -0.142 |
dollars | -0.140 |
wounds | -0.137 |
oster | -0.136 |
vet | -0.134 |
Token | up |
Token ID | 510 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
Jan | +0.025 |
Jos | +0.022 |
Suz | +0.022 |
Sus | +0.022 |
ous | +0.021 |
Neg logit contributions | |
over | -0.040 |
dollars | -0.039 |
oster | -0.038 |
wounds | -0.037 |
End | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
dollars | +0.001 |
over | +0.001 |
oster | +0.001 |
wounds | +0.001 |
vet | +0.001 |
Neg logit contributions | |
Jan | -0.001 |
Jos | -0.001 |
Sus | -0.001 |
Suz | -0.001 |
Jo | -0.001 |
Token | explained |
Token ID | 4893 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
over | +0.028 |
dollars | +0.028 |
wounds | +0.027 |
oster | +0.027 |
End | +0.026 |
Neg logit contributions | |
Jan | -0.025 |
Sus | -0.024 |
Jos | -0.023 |
Suz | -0.023 |
Jo | -0.023 |
Token | that |
Token ID | 326 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
over | +0.009 |
dollars | +0.009 |
wounds | +0.009 |
oster | +0.009 |
vet | +0.009 |
Neg logit contributions | |
Jan | -0.008 |
Jos | -0.007 |
Sus | -0.007 |
Suz | -0.007 |
stair | -0.007 |
Token | shoes |
Token ID | 10012 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
Jan | +0.012 |
stair | +0.012 |
Sus | +0.011 |
Jos | +0.011 |
Jo | +0.011 |
Neg logit contributions | |
oster | -0.013 |
dollars | -0.013 |
wounds | -0.013 |
vet | -0.013 |
over | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
over | +0.021 |
dollars | +0.021 |
wounds | +0.021 |
oster | +0.021 |
vet | +0.020 |
Neg logit contributions | |
Jan | -0.021 |
Jos | -0.020 |
Sus | -0.019 |
Suz | -0.019 |
od | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
Jan | +0.029 |
Jos | +0.028 |
Sus | +0.027 |
stair | +0.027 |
Suz | +0.027 |
Neg logit contributions | |
dollars | -0.035 |
over | -0.035 |
oster | -0.035 |
wounds | -0.034 |
vet | -0.033 |
Token | go |
Token ID | 467 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
dollars | +0.016 |
over | +0.016 |
oster | +0.016 |
wounds | +0.016 |
End | +0.015 |
Neg logit contributions | |
Jan | -0.011 |
Jos | -0.010 |
Sus | -0.010 |
Suz | -0.009 |
Jo | -0.009 |
Token | on |
Token ID | 319 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Jan | +0.034 |
Jos | +0.033 |
od | +0.032 |
icated | +0.031 |
ous | +0.031 |
Neg logit contributions | |
over | -0.037 |
dollars | -0.036 |
wounds | -0.036 |
oster | -0.035 |
vet | -0.034 |
Token | an |
Token ID | 281 |
Feature activation | +6.13e+00 |
Pos logit contributions | |
Jan | +0.043 |
Jos | +0.042 |
ous | +0.042 |
od | +0.041 |
icated | +0.040 |
Neg logit contributions | |
over | -0.051 |
wounds | -0.050 |
dollars | -0.049 |
vet | -0.048 |
promises | -0.048 |
Token | adventure |
Token ID | 8855 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
Jan | +0.138 |
Jos | +0.133 |
Sus | +0.126 |
ous | +0.126 |
od | +0.126 |
Neg logit contributions | |
vet | -0.136 |
wounds | -0.134 |
End | -0.133 |
dollars | -0.132 |
over | -0.131 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Jan | +0.016 |
Jos | +0.016 |
Sus | +0.015 |
od | +0.015 |
Suz | +0.015 |
Neg logit contributions | |
over | -0.013 |
dollars | -0.012 |
wounds | -0.012 |
oster | -0.012 |
vet | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Jan | +0.027 |
Sus | +0.026 |
Jos | +0.026 |
Suz | +0.025 |
Jo | +0.025 |
Neg logit contributions | |
wounds | -0.032 |
dollars | -0.032 |
oster | -0.031 |
injuries | -0.031 |
over | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
Jan | +0.028 |
Jos | +0.026 |
Sus | +0.026 |
Jo | +0.026 |
Suz | +0.026 |
Neg logit contributions | |
dollars | -0.028 |
wounds | -0.027 |
promises | -0.025 |
over | -0.025 |
injuries | -0.025 |
Token | The |
Token ID | 464 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
Jan | +0.018 |
Jos | +0.017 |
Sus | +0.017 |
stair | +0.017 |
Suz | +0.017 |
Neg logit contributions | |
dollars | -0.018 |
wounds | -0.018 |
promises | -0.017 |
over | -0.017 |
pig | -0.017 |
Token | he |
Token ID | 339 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
over | +0.013 |
dollars | +0.013 |
oster | +0.012 |
pig | +0.012 |
End | +0.012 |
Neg logit contributions | |
Jan | -0.014 |
Jos | -0.013 |
stair | -0.013 |
od | -0.013 |
Suz | -0.012 |
Token | would |
Token ID | 561 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Jan | +0.019 |
Jos | +0.019 |
Sus | +0.018 |
Suz | +0.018 |
ous | +0.018 |
Neg logit contributions | |
oster | -0.020 |
over | -0.020 |
vet | -0.020 |
wounds | -0.019 |
pig | -0.019 |
Token | skip |
Token ID | 14267 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
Jan | +0.022 |
Jos | +0.022 |
od | +0.021 |
Sus | +0.021 |
ous | +0.020 |
Neg logit contributions | |
vet | -0.025 |
oster | -0.024 |
promises | -0.024 |
over | -0.024 |
pig | -0.024 |
Token | off |
Token ID | 572 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
Jos | +0.022 |
ous | +0.021 |
od | +0.021 |
Jan | +0.021 |
Suz | +0.020 |
Neg logit contributions | |
Spot | -0.010 |
over | -0.009 |
pig | -0.009 |
medicine | -0.009 |
promises | -0.008 |
Token | on |
Token ID | 319 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Jan | +0.021 |
Jos | +0.021 |
Sus | +0.020 |
od | +0.020 |
Suz | +0.020 |
Neg logit contributions | |
pig | -0.012 |
vet | -0.012 |
over | -0.012 |
oster | -0.012 |
wounds | -0.012 |
Token | an |
Token ID | 281 |
Feature activation | +6.12e+00 |
Pos logit contributions | |
Jan | +0.049 |
ous | +0.048 |
Jos | +0.048 |
od | +0.046 |
Sus | +0.046 |
Neg logit contributions | |
wounds | -0.035 |
vet | -0.033 |
promises | -0.033 |
over | -0.033 |
pig | -0.033 |
Token | adventure |
Token ID | 8855 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Jan | +0.144 |
Jos | +0.140 |
Sus | +0.136 |
ous | +0.130 |
od | +0.129 |
Neg logit contributions | |
wounds | -0.133 |
vet | -0.131 |
End | -0.131 |
oster | -0.125 |
over | -0.122 |
Token | . |
Token ID | 13 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
over | +0.004 |
dollars | +0.004 |
oster | +0.004 |
vet | +0.004 |
wounds | +0.004 |
Neg logit contributions | |
Jan | -0.006 |
Jos | -0.006 |
Sus | -0.006 |
Suz | -0.006 |
od | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Jan | +0.023 |
Jos | +0.022 |
Sus | +0.022 |
Suz | +0.021 |
Jo | +0.021 |
Neg logit contributions | |
dollars | -0.018 |
wounds | -0.018 |
over | -0.017 |
oster | -0.017 |
vet | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
Jan | +0.032 |
Jos | +0.031 |
Sus | +0.030 |
Suz | +0.030 |
stair | +0.030 |
Neg logit contributions | |
over | -0.018 |
oster | -0.017 |
dollars | -0.017 |
wounds | -0.017 |
vet | -0.017 |
Token | One |
Token ID | 3198 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
Jan | +0.015 |
Jos | +0.015 |
Sus | +0.014 |
Suz | +0.014 |
ous | +0.014 |
Neg logit contributions | |
oster | -0.011 |
over | -0.011 |
vet | -0.011 |
dollars | -0.011 |
End | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
Jan | +0.000 |
Jos | +0.000 |
contain | +0.000 |
ous | +0.000 |
icated | +0.000 |
Neg logit contributions | |
over | -0.000 |
End | -0.000 |
vet | -0.000 |
oster | -0.000 |
pig | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
over | +0.007 |
dollars | +0.007 |
wounds | +0.007 |
oster | +0.007 |
vet | +0.007 |
Neg logit contributions | |
Jan | -0.007 |
Jos | -0.007 |
Sus | -0.007 |
stair | -0.007 |
ous | -0.007 |
Token | bald |
Token ID | 28273 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
wounds | +0.027 |
dollars | +0.026 |
over | +0.026 |
ages | +0.025 |
promises | +0.025 |
Neg logit contributions | |
Jan | -0.026 |
stair | -0.026 |
Jos | -0.026 |
Sus | -0.025 |
Suz | -0.024 |
Token | man |
Token ID | 582 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
wounds | +0.057 |
dollars | +0.055 |
promises | +0.054 |
injuries | +0.050 |
etchup | +0.049 |
Neg logit contributions | |
ous | -0.081 |
stair | -0.081 |
od | -0.079 |
Jan | -0.078 |
J | -0.077 |
Token | named |
Token ID | 3706 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
wounds | +0.034 |
dollars | +0.033 |
oster | +0.032 |
End | +0.032 |
injuries | +0.032 |
Neg logit contributions | |
Jan | -0.038 |
od | -0.036 |
Jos | -0.036 |
Sus | -0.035 |
J | -0.035 |
Token | Mr |
Token ID | 1770 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
pig | +0.043 |
dollars | +0.043 |
vet | +0.042 |
oster | +0.042 |
over | +0.042 |
Neg logit contributions | |
Jan | -0.043 |
stair | -0.042 |
Jos | -0.041 |
contain | -0.041 |
ous | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
oster | +0.183 |
dollars | +0.173 |
End | +0.171 |
wounds | +0.170 |
promises | +0.167 |
Neg logit contributions | |
Jan | -0.114 |
od | -0.112 |
J | -0.104 |
Jos | -0.102 |
ous | -0.102 |
Token | Smith |
Token ID | 4176 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
wounds | +0.043 |
dollars | +0.043 |
over | +0.043 |
oster | +0.043 |
vet | +0.041 |
Neg logit contributions | |
Jan | -0.040 |
Jos | -0.038 |
Sus | -0.037 |
Suz | -0.036 |
stair | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
Jan | +0.017 |
Jos | +0.016 |
od | +0.016 |
Sus | +0.015 |
Suz | +0.015 |
Neg logit contributions | |
wounds | -0.017 |
over | -0.016 |
dollars | -0.016 |
injuries | -0.016 |
oster | -0.016 |
Token | He |
Token ID | 679 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
dollars | +0.001 |
over | +0.001 |
wounds | +0.001 |
oster | +0.001 |
vet | +0.001 |
Neg logit contributions | |
Jan | -0.001 |
Jos | -0.001 |
Sus | -0.001 |
Suz | -0.001 |
stair | -0.001 |
Token | lived |
Token ID | 5615 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
dollars | +0.005 |
wounds | +0.005 |
over | +0.005 |
promises | +0.005 |
injuries | +0.004 |
Neg logit contributions | |
Jan | -0.004 |
Jos | -0.004 |
Sus | -0.004 |
od | -0.004 |
Suz | -0.004 |
Token | gr |
Token ID | 1036 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
dollars | +0.032 |
wounds | +0.032 |
over | +0.031 |
ages | +0.030 |
promises | +0.029 |
Neg logit contributions | |
Jan | -0.032 |
stair | -0.031 |
Jos | -0.031 |
Sus | -0.030 |
J | -0.029 |
Token | umpy |
Token ID | 32152 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
over | +0.025 |
oster | +0.024 |
dollars | +0.024 |
wounds | +0.023 |
vet | +0.023 |
Neg logit contributions | |
Jan | -0.038 |
Jos | -0.036 |
Sus | -0.036 |
Suz | -0.035 |
stair | -0.035 |
Token | old |
Token ID | 1468 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
dollars | +0.036 |
wounds | +0.036 |
over | +0.036 |
oster | +0.034 |
vet | +0.033 |
Neg logit contributions | |
Jan | -0.059 |
Jos | -0.057 |
Sus | -0.056 |
Suz | -0.055 |
stair | -0.055 |
Token | man |
Token ID | 582 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
dollars | +0.057 |
over | +0.056 |
wounds | +0.056 |
oster | +0.054 |
promises | +0.051 |
Neg logit contributions | |
Jan | -0.123 |
Jos | -0.119 |
Sus | -0.118 |
stair | -0.117 |
Suz | -0.116 |
Token | named |
Token ID | 3706 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
wounds | +0.039 |
dollars | +0.037 |
End | +0.037 |
oster | +0.037 |
injuries | +0.036 |
Neg logit contributions | |
Jan | -0.038 |
od | -0.036 |
Jos | -0.035 |
Sus | -0.034 |
J | -0.034 |
Token | Mr |
Token ID | 1770 |
Feature activation | -6.64e+00 |
Pos logit contributions | |
pig | +0.036 |
vet | +0.035 |
dollars | +0.035 |
wounds | +0.034 |
oster | +0.034 |
Neg logit contributions | |
Jan | -0.038 |
stair | -0.037 |
Jos | -0.037 |
od | -0.036 |
ous | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
oster | +0.189 |
End | +0.177 |
wounds | +0.176 |
dollars | +0.175 |
promises | +0.171 |
Neg logit contributions | |
Jan | -0.099 |
od | -0.099 |
J | -0.090 |
Jos | -0.088 |
ill | -0.088 |
Token | Brown |
Token ID | 4373 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
dollars | +0.038 |
over | +0.037 |
wounds | +0.037 |
oster | +0.037 |
vet | +0.036 |
Neg logit contributions | |
Jan | -0.036 |
Jos | -0.035 |
Sus | -0.034 |
Suz | -0.033 |
stair | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Jan | +0.008 |
od | +0.008 |
Jos | +0.008 |
icated | +0.008 |
Sus | +0.008 |
Neg logit contributions | |
wounds | -0.011 |
over | -0.011 |
dollars | -0.011 |
injuries | -0.011 |
vet | -0.011 |
Token | He |
Token ID | 679 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
over | +0.004 |
wounds | +0.004 |
dollars | +0.004 |
oster | +0.004 |
vet | +0.004 |
Neg logit contributions | |
Jan | -0.004 |
Jos | -0.004 |
Sus | -0.004 |
Suz | -0.004 |
stair | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Jan | +0.001 |
Jos | +0.001 |
Sus | +0.001 |
od | +0.001 |
Suz | +0.001 |
Neg logit contributions | |
dollars | -0.001 |
over | -0.001 |
wounds | -0.001 |
oster | -0.001 |
promises | -0.001 |
Token | know |
Token ID | 760 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
wounds | +0.062 |
oster | +0.062 |
over | +0.062 |
dollars | +0.061 |
eros | +0.059 |
Neg logit contributions | |
Jan | -0.045 |
Sus | -0.042 |
Jos | -0.042 |
Suz | -0.041 |
J | -0.040 |
Token | you |
Token ID | 345 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
Jan | +0.003 |
Sus | +0.003 |
Jos | +0.003 |
Jo | +0.003 |
Suz | +0.003 |
Neg logit contributions | |
oster | -0.003 |
over | -0.003 |
wounds | -0.003 |
dollars | -0.003 |
vet | -0.003 |
Token | love |
Token ID | 1842 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
over | +0.083 |
oster | +0.082 |
wounds | +0.082 |
dollars | +0.080 |
vet | +0.080 |
Neg logit contributions | |
Jan | -0.051 |
Jos | -0.048 |
Sus | -0.047 |
od | -0.046 |
Suz | -0.045 |
Token | your |
Token ID | 534 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
oster | +0.056 |
over | +0.053 |
vet | +0.050 |
dollars | +0.050 |
wounds | +0.049 |
Neg logit contributions | |
Jan | -0.032 |
Sus | -0.030 |
Jo | -0.030 |
Jos | -0.030 |
icated | -0.029 |
Token | pink |
Token ID | 11398 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
oster | +0.074 |
over | +0.071 |
dollars | +0.068 |
ages | +0.067 |
cents | +0.066 |
Neg logit contributions | |
stair | -0.040 |
tw | -0.039 |
Jan | -0.039 |
Sus | -0.038 |
spin | -0.038 |
Token | sweater |
Token ID | 35685 |
Feature activation | -6.64e+00 |
Pos logit contributions | |
oster | +0.050 |
dollars | +0.049 |
over | +0.048 |
wounds | +0.046 |
End | +0.045 |
Neg logit contributions | |
Jan | -0.044 |
stair | -0.043 |
Sus | -0.042 |
Jos | -0.041 |
Jo | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
dollars | +0.133 |
wounds | +0.133 |
over | +0.133 |
oster | +0.132 |
vet | +0.128 |
Neg logit contributions | |
Jan | -0.155 |
Jos | -0.148 |
Sus | -0.146 |
stair | -0.144 |
Suz | -0.142 |
Token | but |
Token ID | 475 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Jan | +0.018 |
ous | +0.017 |
Jos | +0.017 |
stair | +0.017 |
od | +0.017 |
Neg logit contributions | |
dollars | -0.024 |
wounds | -0.024 |
vet | -0.024 |
over | -0.024 |
promises | -0.024 |
Token | it |
Token ID | 340 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
over | +0.003 |
oster | +0.003 |
dollars | +0.003 |
wounds | +0.003 |
vet | +0.003 |
Neg logit contributions | |
Jan | -0.003 |
Jos | -0.003 |
Sus | -0.003 |
Suz | -0.003 |
J | -0.003 |
Token | is |
Token ID | 318 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
over | +0.003 |
oster | +0.003 |
injuries | +0.003 |
wounds | +0.003 |
dollars | +0.002 |
Neg logit contributions | |
Jan | -0.002 |
stair | -0.002 |
Jos | -0.002 |
tw | -0.002 |
od | -0.002 |
Token | not |
Token ID | 407 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Jan | +0.012 |
Sus | +0.011 |
Jos | +0.011 |
Suz | +0.010 |
tw | +0.010 |
Neg logit contributions | |
over | -0.017 |
oster | -0.016 |
eros | -0.015 |
wounds | -0.015 |
ages | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
over | +0.003 |
End | +0.003 |
oster | +0.003 |
vet | +0.003 |
dollars | +0.003 |
Neg logit contributions | |
Jan | -0.004 |
Jos | -0.004 |
contain | -0.004 |
ous | -0.004 |
icated | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
over | +0.015 |
dollars | +0.015 |
wounds | +0.015 |
oster | +0.015 |
vet | +0.015 |
Neg logit contributions | |
Jan | -0.015 |
Jos | -0.014 |
Sus | -0.014 |
Suz | -0.013 |
stair | -0.013 |
Token | kind |
Token ID | 1611 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
dollars | +0.033 |
wounds | +0.033 |
over | +0.032 |
ages | +0.031 |
promises | +0.031 |
Neg logit contributions | |
Jan | -0.031 |
stair | -0.030 |
Jos | -0.030 |
Sus | -0.029 |
J | -0.029 |
Token | man |
Token ID | 582 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
wounds | +0.035 |
dollars | +0.035 |
over | +0.034 |
oster | +0.034 |
promises | +0.032 |
Neg logit contributions | |
Jan | -0.065 |
Jos | -0.063 |
Sus | -0.062 |
Suz | -0.061 |
stair | -0.061 |
Token | named |
Token ID | 3706 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
wounds | +0.039 |
dollars | +0.037 |
injuries | +0.037 |
End | +0.037 |
oster | +0.036 |
Neg logit contributions | |
Jan | -0.035 |
od | -0.034 |
Jos | -0.033 |
Sus | -0.033 |
sorts | -0.032 |
Token | Mr |
Token ID | 1770 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
dollars | +0.045 |
pig | +0.045 |
over | +0.045 |
vet | +0.045 |
oster | +0.044 |
Neg logit contributions | |
Jan | -0.041 |
Jos | -0.039 |
stair | -0.039 |
od | -0.038 |
ous | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
oster | +0.185 |
End | +0.179 |
wounds | +0.175 |
dollars | +0.174 |
promises | +0.170 |
Neg logit contributions | |
Jan | -0.098 |
od | -0.096 |
ill | -0.089 |
J | -0.089 |
Jos | -0.085 |
Token | Smith |
Token ID | 4176 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
wounds | +0.046 |
dollars | +0.046 |
oster | +0.045 |
over | +0.045 |
vet | +0.043 |
Neg logit contributions | |
Jan | -0.040 |
Jos | -0.038 |
Sus | -0.037 |
Suz | -0.036 |
stair | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
Jan | +0.020 |
od | +0.019 |
Jos | +0.019 |
Sus | +0.019 |
sorts | +0.018 |
Neg logit contributions | |
wounds | -0.023 |
injuries | -0.022 |
over | -0.022 |
dollars | -0.022 |
oster | -0.022 |
Token | He |
Token ID | 679 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
over | +0.002 |
dollars | +0.002 |
wounds | +0.002 |
oster | +0.002 |
vet | +0.002 |
Neg logit contributions | |
Jan | -0.003 |
Jos | -0.002 |
Sus | -0.002 |
Suz | -0.002 |
stair | -0.002 |
Token | had |
Token ID | 550 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
dollars | +0.005 |
wounds | +0.005 |
over | +0.004 |
injuries | +0.004 |
promises | +0.004 |
Neg logit contributions | |
Jan | -0.004 |
Jos | -0.004 |
Sus | -0.004 |
Suz | -0.003 |
od | -0.003 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
oster | +0.046 |
dollars | +0.045 |
over | +0.045 |
wounds | +0.045 |
End | +0.043 |
Neg logit contributions | |
Sus | -0.024 |
Jan | -0.024 |
Suz | -0.021 |
Jos | -0.021 |
Jo | -0.020 |
Token | my |
Token ID | 1820 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
Jan | +0.037 |
Jos | +0.035 |
Sus | +0.035 |
Suz | +0.032 |
sorts | +0.031 |
Neg logit contributions | |
oster | -0.093 |
over | -0.092 |
wounds | -0.090 |
dollars | -0.090 |
vet | -0.088 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Jan | +0.017 |
Jos | +0.017 |
Sus | +0.016 |
sorts | +0.016 |
J | +0.016 |
Neg logit contributions | |
oster | -0.026 |
over | -0.026 |
wounds | -0.025 |
dollars | -0.025 |
vet | -0.025 |
Token | warm |
Token ID | 5814 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
Jan | +0.026 |
Jos | +0.025 |
Sus | +0.024 |
od | +0.024 |
Suz | +0.023 |
Neg logit contributions | |
dollars | -0.023 |
over | -0.023 |
oster | -0.023 |
wounds | -0.023 |
vet | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
wounds | +0.008 |
dollars | +0.008 |
oster | +0.008 |
over | +0.008 |
cents | +0.008 |
Neg logit contributions | |
Sus | -0.007 |
Suz | -0.007 |
Jan | -0.006 |
stair | -0.006 |
sorts | -0.006 |
Token | freshly |
Token ID | 29026 |
Feature activation | -6.53e+00 |
Pos logit contributions | |
Jan | +0.017 |
Sus | +0.017 |
Jos | +0.016 |
Suz | +0.016 |
J | +0.015 |
Neg logit contributions | |
oster | -0.024 |
over | -0.024 |
wounds | -0.023 |
End | -0.023 |
dollars | -0.023 |
Token | baked |
Token ID | 22979 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
wounds | +0.182 |
dollars | +0.177 |
injuries | +0.165 |
eros | +0.163 |
clinic | +0.158 |
Neg logit contributions | |
tw | -0.100 |
sorts | -0.092 |
od | -0.090 |
lots | -0.089 |
Jan | -0.088 |
Token | cookie |
Token ID | 19751 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
wounds | +0.007 |
injuries | +0.007 |
oster | +0.007 |
End | +0.007 |
dollars | +0.007 |
Neg logit contributions | |
Jan | -0.008 |
Sus | -0.008 |
Jos | -0.008 |
od | -0.008 |
Suz | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
End | +0.059 |
wounds | +0.059 |
oster | +0.057 |
dollars | +0.057 |
over | +0.057 |
Neg logit contributions | |
Jan | -0.054 |
Sus | -0.052 |
Jos | -0.052 |
od | -0.051 |
Suz | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
Jan | +0.015 |
Sus | +0.014 |
Jos | +0.014 |
Suz | +0.013 |
Jo | +0.013 |
Neg logit contributions | |
wounds | -0.018 |
dollars | -0.018 |
oster | -0.018 |
over | -0.018 |
injuries | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
Jan | +0.010 |
Sus | +0.010 |
Jos | +0.010 |
Suz | +0.010 |
Jo | +0.009 |
Neg logit contributions | |
wounds | -0.010 |
dollars | -0.010 |
promises | -0.009 |
over | -0.009 |
injuries | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
over | +0.005 |
End | +0.004 |
oster | +0.004 |
vet | +0.004 |
dollars | +0.004 |
Neg logit contributions | |
Jan | -0.006 |
Jos | -0.006 |
ous | -0.006 |
Sus | -0.006 |
icated | -0.006 |
Token | an |
Token ID | 281 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
dollars | +0.018 |
over | +0.018 |
wounds | +0.018 |
oster | +0.018 |
vet | +0.017 |
Neg logit contributions | |
Jan | -0.017 |
Jos | -0.016 |
Sus | -0.015 |
Suz | -0.015 |
stair | -0.015 |
Token | old |
Token ID | 1468 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
Jan | +0.041 |
Jos | +0.039 |
Sus | +0.039 |
ous | +0.038 |
Jo | +0.038 |
Neg logit contributions | |
over | -0.031 |
dollars | -0.031 |
oster | -0.031 |
wounds | -0.031 |
vet | -0.030 |
Token | judge |
Token ID | 5052 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
dollars | +0.059 |
wounds | +0.058 |
over | +0.058 |
oster | +0.056 |
promises | +0.053 |
Neg logit contributions | |
Jan | -0.125 |
stair | -0.120 |
Jos | -0.119 |
Sus | -0.119 |
Suz | -0.118 |
Token | named |
Token ID | 3706 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
wounds | +0.012 |
dollars | +0.012 |
oster | +0.012 |
injuries | +0.011 |
promises | +0.011 |
Neg logit contributions | |
Jan | -0.013 |
od | -0.013 |
Jos | -0.013 |
Sus | -0.012 |
J | -0.012 |
Token | Mr |
Token ID | 1770 |
Feature activation | -6.50e+00 |
Pos logit contributions | |
over | +0.040 |
vet | +0.040 |
dollars | +0.040 |
pig | +0.039 |
oster | +0.038 |
Neg logit contributions | |
stair | -0.049 |
Jos | -0.048 |
yt | -0.048 |
cast | -0.047 |
Jan | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
oster | +0.184 |
End | +0.182 |
dollars | +0.177 |
wounds | +0.176 |
promises | +0.171 |
Neg logit contributions | |
od | -0.094 |
Jan | -0.092 |
ill | -0.083 |
J | -0.082 |
ous | -0.081 |
Token | Owl |
Token ID | 37007 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
wounds | +0.049 |
oster | +0.048 |
dollars | +0.048 |
over | +0.047 |
promises | +0.045 |
Neg logit contributions | |
Jan | -0.038 |
Sus | -0.036 |
Jos | -0.036 |
J | -0.034 |
Jo | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
wounds | +0.003 |
dollars | +0.002 |
injuries | +0.002 |
over | +0.002 |
oster | +0.002 |
Neg logit contributions | |
Jan | -0.002 |
od | -0.002 |
Sus | -0.002 |
Jos | -0.002 |
Suz | -0.002 |
Token | He |
Token ID | 679 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
Jan | +0.000 |
Sus | +0.000 |
Jos | +0.000 |
stair | +0.000 |
Suz | +0.000 |
Neg logit contributions | |
wounds | -0.000 |
oster | -0.000 |
over | -0.000 |
dollars | -0.000 |
vet | -0.000 |
Token | lived |
Token ID | 5615 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
dollars | +0.010 |
over | +0.010 |
wounds | +0.010 |
injuries | +0.009 |
oster | +0.009 |
Neg logit contributions | |
Jan | -0.009 |
Jos | -0.009 |
Sus | -0.009 |
od | -0.008 |
Suz | -0.008 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
over | +0.038 |
dollars | +0.037 |
oster | +0.036 |
being | +0.035 |
aid | +0.034 |
Neg logit contributions | |
stair | -0.036 |
Jan | -0.035 |
tr | -0.034 |
tw | -0.034 |
spinning | -0.033 |
Token | my |
Token ID | 1820 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Jan | +0.040 |
Jos | +0.037 |
Sus | +0.036 |
Suz | +0.035 |
Jo | +0.034 |
Neg logit contributions | |
over | -0.060 |
dollars | -0.059 |
wounds | -0.059 |
oster | -0.058 |
End | -0.055 |
Token | surprised |
Token ID | 6655 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
Jan | +0.036 |
Jos | +0.034 |
Sus | +0.034 |
Suz | +0.033 |
Jo | +0.032 |
Neg logit contributions | |
over | -0.043 |
dollars | -0.042 |
wounds | -0.042 |
oster | -0.041 |
End | -0.039 |
Token | him |
Token ID | 683 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
Jan | +0.014 |
Jos | +0.013 |
Sus | +0.013 |
Suz | +0.013 |
stair | +0.013 |
Neg logit contributions | |
over | -0.013 |
dollars | -0.013 |
wounds | -0.013 |
oster | -0.013 |
vet | -0.013 |
Token | with |
Token ID | 351 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
dollars | +0.022 |
oster | +0.022 |
over | +0.022 |
vet | +0.021 |
wounds | +0.021 |
Neg logit contributions | |
Jan | -0.019 |
Jos | -0.018 |
Sus | -0.018 |
Suz | -0.018 |
stair | -0.018 |
Token | freshly |
Token ID | 29026 |
Feature activation | -6.49e+00 |
Pos logit contributions | |
oster | +0.013 |
over | +0.013 |
dollars | +0.012 |
ages | +0.012 |
cents | +0.012 |
Neg logit contributions | |
Jan | -0.006 |
Sus | -0.006 |
Suz | -0.006 |
Jos | -0.006 |
J | -0.005 |
Token | baked |
Token ID | 22979 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
dollars | +0.163 |
over | +0.159 |
wounds | +0.157 |
oster | +0.155 |
injuries | +0.147 |
Neg logit contributions | |
Jan | -0.117 |
tw | -0.109 |
od | -0.108 |
Jos | -0.107 |
sorts | -0.107 |
Token | cookies |
Token ID | 14746 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
oster | +0.013 |
End | +0.013 |
dollars | +0.013 |
wounds | +0.012 |
over | +0.012 |
Neg logit contributions | |
Jan | -0.013 |
Sus | -0.012 |
Jos | -0.012 |
Suz | -0.012 |
J | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
dollars | +0.038 |
over | +0.038 |
wounds | +0.037 |
oster | +0.037 |
vet | +0.036 |
Neg logit contributions | |
Jan | -0.044 |
Jos | -0.042 |
Sus | -0.041 |
Suz | -0.040 |
stair | -0.040 |
Token | Tim |
Token ID | 5045 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
Jan | +0.029 |
Jos | +0.028 |
od | +0.028 |
contain | +0.028 |
stair | +0.027 |
Neg logit contributions | |
vet | -0.029 |
over | -0.029 |
dollars | -0.028 |
wounds | -0.028 |
pig | -0.028 |
Token | my |
Token ID | 1820 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Jan | +0.051 |
Jos | +0.046 |
Sus | +0.043 |
Suz | +0.042 |
Jo | +0.041 |
Neg logit contributions | |
over | -0.122 |
dollars | -0.119 |
oster | -0.118 |
wounds | -0.117 |
vet | -0.114 |
Token | was |
Token ID | 373 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
over | +0.003 |
End | +0.003 |
oster | +0.003 |
vet | +0.003 |
wounds | +0.003 |
Neg logit contributions | |
Jan | -0.004 |
Jos | -0.004 |
ous | -0.004 |
icated | -0.004 |
contain | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
dollars | +0.016 |
over | +0.016 |
wounds | +0.016 |
oster | +0.016 |
vet | +0.016 |
Neg logit contributions | |
Jan | -0.015 |
Jos | -0.015 |
Sus | -0.014 |
Suz | -0.014 |
stair | -0.014 |
Token | gray |
Token ID | 12768 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
dollars | +0.034 |
wounds | +0.034 |
over | +0.033 |
ages | +0.033 |
promises | +0.032 |
Neg logit contributions | |
Jan | -0.032 |
stair | -0.032 |
Jos | -0.031 |
Sus | -0.031 |
Suz | -0.030 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
dollars | +0.038 |
wounds | +0.038 |
over | +0.037 |
oster | +0.036 |
promises | +0.035 |
Neg logit contributions | |
Jan | -0.063 |
Jos | -0.061 |
stair | -0.060 |
Sus | -0.060 |
Suz | -0.059 |
Token | named |
Token ID | 3706 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
dollars | +0.023 |
over | +0.023 |
wounds | +0.023 |
oster | +0.022 |
vet | +0.021 |
Neg logit contributions | |
Jan | -0.042 |
Jos | -0.040 |
Sus | -0.040 |
Suz | -0.039 |
stair | -0.039 |
Token | Mr |
Token ID | 1770 |
Feature activation | -6.48e+00 |
Pos logit contributions | |
dollars | +0.055 |
wounds | +0.054 |
over | +0.053 |
oster | +0.053 |
End | +0.051 |
Neg logit contributions | |
Jan | -0.054 |
Jos | -0.051 |
Sus | -0.050 |
Suz | -0.049 |
Jo | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
oster | +0.170 |
End | +0.169 |
wounds | +0.168 |
dollars | +0.167 |
promises | +0.164 |
Neg logit contributions | |
Jan | -0.107 |
od | -0.105 |
ill | -0.098 |
icated | -0.095 |
ous | -0.095 |
Token | Wh |
Token ID | 854 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
dollars | +0.044 |
wounds | +0.043 |
over | +0.043 |
oster | +0.043 |
vet | +0.042 |
Neg logit contributions | |
Jan | -0.046 |
Jos | -0.043 |
Sus | -0.042 |
Suz | -0.042 |
stair | -0.041 |
Token | isk |
Token ID | 1984 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
dollars | +0.019 |
wounds | +0.019 |
over | +0.018 |
End | +0.018 |
vet | +0.018 |
Neg logit contributions | |
Jan | -0.025 |
od | -0.023 |
Jos | -0.023 |
Suz | -0.023 |
ous | -0.022 |
Token | ers |
Token ID | 364 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
dollars | +0.047 |
wounds | +0.045 |
injuries | +0.043 |
vet | +0.043 |
over | +0.042 |
Neg logit contributions | |
Jan | -0.107 |
od | -0.105 |
Jos | -0.102 |
Sus | -0.100 |
Suz | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
dollars | +0.009 |
wounds | +0.009 |
over | +0.008 |
oster | +0.008 |
vet | +0.008 |
Neg logit contributions | |
Jan | -0.010 |
Jos | -0.009 |
Sus | -0.009 |
od | -0.009 |
Suz | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
over | +0.005 |
dollars | +0.005 |
oster | +0.005 |
wounds | +0.005 |
End | +0.005 |
Neg logit contributions | |
Jan | -0.006 |
Jos | -0.006 |
ous | -0.006 |
Sus | -0.006 |
stair | -0.006 |
Token | an |
Token ID | 281 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
over | +0.010 |
dollars | +0.010 |
wounds | +0.010 |
oster | +0.010 |
vet | +0.010 |
Neg logit contributions | |
Jan | -0.011 |
Jos | -0.010 |
Sus | -0.010 |
Suz | -0.010 |
stair | -0.010 |
Token | elderly |
Token ID | 13830 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
Jan | +0.046 |
Jos | +0.044 |
Sus | +0.043 |
ous | +0.043 |
Jo | +0.042 |
Neg logit contributions | |
dollars | -0.034 |
over | -0.034 |
wounds | -0.033 |
oster | -0.033 |
vet | -0.032 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
wounds | +0.090 |
dollars | +0.083 |
promises | +0.082 |
injuries | +0.080 |
oster | +0.078 |
Neg logit contributions | |
Jan | -0.150 |
Sus | -0.147 |
Jos | -0.146 |
stair | -0.144 |
Suz | -0.142 |
Token | named |
Token ID | 3706 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
dollars | +0.023 |
wounds | +0.022 |
over | +0.022 |
oster | +0.022 |
End | +0.021 |
Neg logit contributions | |
Jan | -0.037 |
Jos | -0.035 |
Sus | -0.035 |
Suz | -0.034 |
od | -0.034 |
Token | Mr |
Token ID | 1770 |
Feature activation | -6.47e+00 |
Pos logit contributions | |
over | +0.036 |
dollars | +0.035 |
wounds | +0.035 |
vet | +0.035 |
oster | +0.035 |
Neg logit contributions | |
Jan | -0.041 |
Jos | -0.040 |
Sus | -0.038 |
od | -0.038 |
stair | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
oster | +0.175 |
wounds | +0.164 |
dollars | +0.162 |
End | +0.160 |
promises | +0.157 |
Neg logit contributions | |
Jan | -0.112 |
od | -0.108 |
Jos | -0.104 |
ill | -0.101 |
icated | -0.099 |
Token | Wh |
Token ID | 854 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
dollars | +0.044 |
wounds | +0.044 |
oster | +0.043 |
over | +0.043 |
vet | +0.041 |
Neg logit contributions | |
Jan | -0.042 |
Jos | -0.039 |
Sus | -0.039 |
Suz | -0.038 |
Jo | -0.037 |
Token | isk |
Token ID | 1984 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
dollars | +0.012 |
wounds | +0.011 |
oster | +0.011 |
over | +0.011 |
End | +0.011 |
Neg logit contributions | |
Jan | -0.016 |
Jos | -0.015 |
od | -0.015 |
Sus | -0.014 |
Suz | -0.014 |
Token | ers |
Token ID | 364 |
Feature activation | +8.72e-03 |
Pos logit contributions | |
dollars | +0.043 |
wounds | +0.041 |
injuries | +0.039 |
vet | +0.039 |
over | +0.039 |
Neg logit contributions | |
Jan | -0.098 |
od | -0.096 |
Jos | -0.095 |
Sus | -0.093 |
Suz | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
Jan | +0.000 |
Jos | +0.000 |
Sus | +0.000 |
od | +0.000 |
Suz | +0.000 |
Neg logit contributions | |
dollars | -0.000 |
wounds | -0.000 |
over | -0.000 |
oster | -0.000 |
vet | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
over | +0.003 |
End | +0.003 |
oster | +0.003 |
vet | +0.003 |
wounds | +0.003 |
Neg logit contributions | |
Jan | -0.004 |
Jos | -0.004 |
ous | -0.004 |
contain | -0.004 |
icated | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
over | +0.011 |
dollars | +0.011 |
wounds | +0.011 |
oster | +0.011 |
vet | +0.011 |
Neg logit contributions | |
Jan | -0.011 |
Jos | -0.011 |
Sus | -0.010 |
Suz | -0.010 |
stair | -0.010 |
Token | gray |
Token ID | 12768 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
dollars | +0.030 |
wounds | +0.030 |
over | +0.030 |
ages | +0.029 |
promises | +0.028 |
Neg logit contributions | |
Jan | -0.030 |
stair | -0.029 |
Jos | -0.029 |
Sus | -0.029 |
Suz | -0.028 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
dollars | +0.037 |
wounds | +0.037 |
over | +0.036 |
oster | +0.035 |
promises | +0.034 |
Neg logit contributions | |
Jan | -0.063 |
Jos | -0.060 |
Sus | -0.060 |
stair | -0.059 |
Suz | -0.059 |
Token | named |
Token ID | 3706 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
dollars | +0.025 |
wounds | +0.024 |
over | +0.024 |
oster | +0.024 |
vet | +0.023 |
Neg logit contributions | |
Jan | -0.043 |
Jos | -0.042 |
Sus | -0.041 |
Suz | -0.040 |
stair | -0.040 |
Token | Mr |
Token ID | 1770 |
Feature activation | -6.43e+00 |
Pos logit contributions | |
dollars | +0.055 |
over | +0.054 |
wounds | +0.054 |
oster | +0.053 |
vet | +0.051 |
Neg logit contributions | |
Jan | -0.055 |
Jos | -0.052 |
Sus | -0.051 |
Suz | -0.050 |
Jo | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
oster | +0.170 |
dollars | +0.164 |
End | +0.163 |
wounds | +0.163 |
promises | +0.158 |
Neg logit contributions | |
Jan | -0.113 |
od | -0.108 |
Jos | -0.100 |
icated | -0.099 |
ous | -0.098 |
Token | Wh |
Token ID | 854 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
dollars | +0.042 |
wounds | +0.042 |
oster | +0.041 |
over | +0.041 |
vet | +0.040 |
Neg logit contributions | |
Jan | -0.043 |
Jos | -0.041 |
Sus | -0.040 |
Suz | -0.039 |
Jo | -0.039 |
Token | isk |
Token ID | 1984 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
dollars | +0.013 |
wounds | +0.013 |
over | +0.012 |
oster | +0.012 |
vet | +0.012 |
Neg logit contributions | |
Jan | -0.019 |
Jos | -0.018 |
od | -0.018 |
Sus | -0.018 |
Suz | -0.018 |
Token | ers |
Token ID | 364 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
dollars | +0.044 |
wounds | +0.042 |
over | +0.039 |
vet | +0.039 |
injuries | +0.039 |
Neg logit contributions | |
Jan | -0.104 |
od | -0.101 |
Jos | -0.100 |
Sus | -0.099 |
Suz | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
dollars | +0.005 |
wounds | +0.005 |
over | +0.005 |
oster | +0.005 |
vet | +0.005 |
Neg logit contributions | |
Jan | -0.006 |
Jos | -0.005 |
Sus | -0.005 |
od | -0.005 |
Suz | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
over | +0.005 |
dollars | +0.005 |
oster | +0.005 |
wounds | +0.005 |
End | +0.005 |
Neg logit contributions | |
Jan | -0.006 |
Jos | -0.006 |
ous | -0.006 |
Sus | -0.006 |
od | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
dollars | +0.013 |
over | +0.013 |
wounds | +0.013 |
oster | +0.013 |
vet | +0.013 |
Neg logit contributions | |
Jan | -0.012 |
Jos | -0.012 |
Sus | -0.012 |
Suz | -0.011 |
stair | -0.011 |
Token | kind |
Token ID | 1611 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
wounds | +0.029 |
dollars | +0.029 |
over | +0.028 |
ages | +0.027 |
promises | +0.027 |
Neg logit contributions | |
Jan | -0.027 |
stair | -0.027 |
Jos | -0.026 |
Sus | -0.026 |
J | -0.025 |
Token | man |
Token ID | 582 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
wounds | +0.034 |
dollars | +0.033 |
over | +0.033 |
oster | +0.032 |
promises | +0.031 |
Neg logit contributions | |
Jan | -0.059 |
Jos | -0.057 |
Sus | -0.057 |
Suz | -0.056 |
stair | -0.055 |
Token | named |
Token ID | 3706 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
wounds | +0.034 |
dollars | +0.032 |
End | +0.032 |
injuries | +0.032 |
oster | +0.031 |
Neg logit contributions | |
Jan | -0.032 |
od | -0.031 |
Jos | -0.030 |
Sus | -0.030 |
sorts | -0.029 |
Token | Mr |
Token ID | 1770 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
pig | +0.042 |
dollars | +0.042 |
vet | +0.041 |
over | +0.041 |
oster | +0.041 |
Neg logit contributions | |
Jan | -0.042 |
stair | -0.040 |
Jos | -0.040 |
od | -0.040 |
ous | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
oster | +0.184 |
End | +0.174 |
dollars | +0.170 |
wounds | +0.170 |
promises | +0.166 |
Neg logit contributions | |
od | -0.093 |
Jan | -0.093 |
ill | -0.086 |
J | -0.084 |
Jos | -0.082 |
Token | Bear |
Token ID | 14732 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
wounds | +0.044 |
dollars | +0.044 |
over | +0.043 |
oster | +0.043 |
vet | +0.042 |
Neg logit contributions | |
Jan | -0.039 |
Jos | -0.037 |
Sus | -0.036 |
Suz | -0.035 |
stair | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
Jan | +0.005 |
Sus | +0.005 |
Jos | +0.004 |
od | +0.004 |
Suz | +0.004 |
Neg logit contributions | |
wounds | -0.005 |
dollars | -0.005 |
injuries | -0.005 |
oster | -0.005 |
over | -0.005 |
Token | He |
Token ID | 679 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
over | +0.001 |
dollars | +0.001 |
wounds | +0.001 |
oster | +0.001 |
vet | +0.001 |
Neg logit contributions | |
Jan | -0.001 |
Jos | -0.001 |
Sus | -0.001 |
Suz | -0.001 |
stair | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
dollars | +0.008 |
wounds | +0.008 |
over | +0.008 |
promises | +0.007 |
injuries | +0.007 |
Neg logit contributions | |
Jan | -0.007 |
Jos | -0.006 |
Sus | -0.006 |
Suz | -0.006 |
od | -0.006 |
Token | so |
Token ID | 523 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Jan | +0.019 |
Jos | +0.018 |
stair | +0.018 |
icated | +0.017 |
Sus | +0.017 |
Neg logit contributions | |
over | -0.029 |
dollars | -0.029 |
wounds | -0.029 |
oster | -0.028 |
vet | -0.028 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
over | +0.017 |
dollars | +0.017 |
oster | +0.016 |
wounds | +0.016 |
End | +0.016 |
Neg logit contributions | |
Jan | -0.028 |
Jos | -0.027 |
stair | -0.027 |
Sus | -0.027 |
Suz | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Jan | +0.005 |
Jos | +0.005 |
Sus | +0.005 |
stair | +0.005 |
Suz | +0.005 |
Neg logit contributions | |
over | -0.005 |
dollars | -0.005 |
wounds | -0.005 |
oster | -0.005 |
vet | -0.005 |
Token | see |
Token ID | 766 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
vet | +0.021 |
over | +0.021 |
End | +0.021 |
oster | +0.020 |
wounds | +0.020 |
Neg logit contributions | |
Jan | -0.027 |
stair | -0.027 |
icated | -0.026 |
Jos | -0.026 |
ous | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Jan | +0.056 |
Jos | +0.053 |
Sus | +0.052 |
Suz | +0.051 |
stair | +0.051 |
Neg logit contributions | |
over | -0.053 |
dollars | -0.053 |
wounds | -0.052 |
oster | -0.052 |
vet | -0.050 |
Token | freshly |
Token ID | 29026 |
Feature activation | -6.32e+00 |
Pos logit contributions | |
Jan | +0.030 |
Jos | +0.029 |
Sus | +0.028 |
stair | +0.028 |
Suz | +0.027 |
Neg logit contributions | |
over | -0.036 |
dollars | -0.036 |
wounds | -0.036 |
oster | -0.035 |
vet | -0.034 |
Token | baked |
Token ID | 22979 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
dollars | +0.147 |
wounds | +0.145 |
over | +0.136 |
oster | +0.133 |
injuries | +0.131 |
Neg logit contributions | |
Jan | -0.134 |
od | -0.124 |
Jos | -0.123 |
sorts | -0.120 |
Suz | -0.120 |
Token | bean |
Token ID | 26394 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
wounds | +0.025 |
dollars | +0.023 |
oster | +0.023 |
injuries | +0.023 |
promises | +0.023 |
Neg logit contributions | |
Jan | -0.019 |
Jos | -0.019 |
Sus | -0.019 |
stair | -0.018 |
od | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
over | +0.011 |
dollars | +0.011 |
wounds | +0.011 |
oster | +0.011 |
vet | +0.010 |
Neg logit contributions | |
Jan | -0.010 |
Jos | -0.010 |
Sus | -0.010 |
Suz | -0.010 |
stair | -0.009 |
Token | After |
Token ID | 2293 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Jan | +0.025 |
Jos | +0.024 |
Sus | +0.024 |
Suz | +0.023 |
Jo | +0.023 |
Neg logit contributions | |
dollars | -0.021 |
wounds | -0.021 |
over | -0.021 |
oster | -0.020 |
injuries | -0.020 |
Token | that |
Token ID | 326 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
Jan | +0.003 |
Jos | +0.003 |
Sus | +0.003 |
Suz | +0.003 |
J | +0.002 |
Neg logit contributions | |
oster | -0.003 |
dollars | -0.003 |
wounds | -0.003 |
over | -0.003 |
promises | -0.003 |
Token | sky |
Token ID | 6766 |
Feature activation | +7.70e-02 |
Pos logit contributions | |
Jan | +0.037 |
Jos | +0.036 |
Sus | +0.035 |
Suz | +0.034 |
od | +0.034 |
Neg logit contributions | |
over | -0.039 |
dollars | -0.038 |
oster | -0.038 |
wounds | -0.038 |
vet | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
Jan | +0.002 |
Jos | +0.002 |
Sus | +0.002 |
Suz | +0.002 |
od | +0.002 |
Neg logit contributions | |
dollars | -0.002 |
wounds | -0.002 |
oster | -0.001 |
over | -0.001 |
vet | -0.001 |
Token | The |
Token ID | 383 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
Jan | +0.018 |
Jos | +0.017 |
Sus | +0.017 |
Suz | +0.017 |
Jo | +0.016 |
Neg logit contributions | |
dollars | -0.018 |
wounds | -0.018 |
over | -0.018 |
oster | -0.017 |
vet | -0.017 |
Token | grass |
Token ID | 8701 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
dollars | +0.010 |
wounds | +0.010 |
over | +0.010 |
ages | +0.010 |
oster | +0.009 |
Neg logit contributions | |
stair | -0.007 |
Jan | -0.007 |
Sus | -0.006 |
Jos | -0.006 |
J | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
dollars | +0.005 |
wounds | +0.005 |
over | +0.005 |
oster | +0.005 |
vet | +0.005 |
Neg logit contributions | |
Jan | -0.004 |
Jos | -0.004 |
Sus | -0.004 |
Suz | -0.004 |
stair | -0.004 |
Token | freshly |
Token ID | 29026 |
Feature activation | -6.28e+00 |
Pos logit contributions | |
Jan | +0.018 |
od | +0.018 |
Jos | +0.017 |
aph | +0.017 |
ous | +0.017 |
Neg logit contributions | |
over | -0.021 |
End | -0.021 |
vet | -0.020 |
oster | -0.020 |
pig | -0.020 |
Token | cut |
Token ID | 2005 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
wounds | +0.133 |
dollars | +0.130 |
vet | +0.120 |
injuries | +0.120 |
oster | +0.118 |
Neg logit contributions | |
Jan | -0.147 |
od | -0.143 |
tw | -0.137 |
Jos | -0.137 |
Suz | -0.135 |
Token | , |
Token ID | 11 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Jan | +0.018 |
Jos | +0.017 |
Sus | +0.016 |
Suz | +0.016 |
od | +0.016 |
Neg logit contributions | |
dollars | -0.019 |
wounds | -0.019 |
over | -0.019 |
vet | -0.019 |
oster | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Jan | +0.030 |
Jos | +0.028 |
Sus | +0.028 |
Suz | +0.027 |
stair | +0.027 |
Neg logit contributions | |
over | -0.036 |
dollars | -0.036 |
wounds | -0.035 |
oster | -0.035 |
vet | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
over | +0.029 |
dollars | +0.029 |
wounds | +0.028 |
oster | +0.028 |
vet | +0.027 |
Neg logit contributions | |
Jan | -0.027 |
Jos | -0.026 |
Sus | -0.025 |
Suz | -0.025 |
stair | -0.025 |
Token | gentle |
Token ID | 10296 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Jan | +0.029 |
stair | +0.029 |
Jos | +0.028 |
Sus | +0.028 |
Suz | +0.027 |
Neg logit contributions | |
wounds | -0.034 |
over | -0.034 |
dollars | -0.034 |
oster | -0.033 |
promises | -0.033 |
Token | there |
Token ID | 612 |
Feature activation | +9.01e-03 |
Pos logit contributions | |
over | +0.008 |
End | +0.008 |
dollars | +0.008 |
pig | +0.007 |
eros | +0.007 |
Neg logit contributions | |
contain | -0.013 |
sorts | -0.013 |
icated | -0.013 |
Jos | -0.012 |
Jan | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
Jan | +0.000 |
Jos | +0.000 |
stair | +0.000 |
ous | +0.000 |
Sus | +0.000 |
Neg logit contributions | |
over | -0.000 |
dollars | -0.000 |
oster | -0.000 |
wounds | -0.000 |
vet | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
dollars | +0.020 |
wounds | +0.020 |
oster | +0.020 |
over | +0.020 |
vet | +0.019 |
Neg logit contributions | |
Jan | -0.017 |
Jos | -0.017 |
Sus | -0.016 |
Suz | -0.016 |
od | -0.016 |
Token | lady |
Token ID | 10846 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
dollars | +0.031 |
wounds | +0.031 |
over | +0.030 |
ages | +0.029 |
promises | +0.029 |
Neg logit contributions | |
Jan | -0.029 |
stair | -0.028 |
Jos | -0.027 |
Sus | -0.027 |
Suz | -0.026 |
Token | named |
Token ID | 3706 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
wounds | +0.022 |
dollars | +0.021 |
oster | +0.021 |
injuries | +0.020 |
End | +0.020 |
Neg logit contributions | |
Jan | -0.026 |
Jos | -0.025 |
od | -0.024 |
Sus | -0.024 |
Suz | -0.024 |
Token | Mrs |
Token ID | 9074 |
Feature activation | -6.24e+00 |
Pos logit contributions | |
over | +0.046 |
vet | +0.045 |
dollars | +0.045 |
oster | +0.044 |
pig | +0.043 |
Neg logit contributions | |
Jan | -0.049 |
Jos | -0.047 |
stair | -0.046 |
ous | -0.046 |
od | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
oster | +0.171 |
wounds | +0.160 |
dollars | +0.156 |
promises | +0.155 |
End | +0.153 |
Neg logit contributions | |
Jan | -0.115 |
od | -0.107 |
Sus | -0.106 |
Jos | -0.105 |
Jo | -0.103 |
Token | Greene |
Token ID | 28132 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
over | +0.053 |
dollars | +0.053 |
wounds | +0.052 |
oster | +0.051 |
vet | +0.051 |
Neg logit contributions | |
Jan | -0.042 |
Jos | -0.040 |
Sus | -0.038 |
Suz | -0.038 |
stair | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
wounds | +0.043 |
dollars | +0.042 |
oster | +0.040 |
over | +0.040 |
injuries | +0.040 |
Neg logit contributions | |
Jan | -0.041 |
Sus | -0.039 |
Jos | -0.038 |
od | -0.038 |
Suz | -0.037 |
Token | One |
Token ID | 1881 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
over | +0.021 |
dollars | +0.020 |
wounds | +0.020 |
vet | +0.020 |
oster | +0.020 |
Neg logit contributions | |
Jan | -0.018 |
Jos | -0.017 |
Sus | -0.017 |
Suz | -0.017 |
od | -0.016 |
Token | day |
Token ID | 1110 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
dollars | +0.040 |
wounds | +0.040 |
over | +0.039 |
oster | +0.039 |
vet | +0.038 |
Neg logit contributions | |
Jan | -0.030 |
Jos | -0.028 |
Sus | -0.027 |
Suz | -0.027 |
stair | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
over | +0.002 |
oster | +0.002 |
dollars | +0.002 |
wounds | +0.002 |
vet | +0.002 |
Neg logit contributions | |
Jan | -0.003 |
Jos | -0.003 |
stair | -0.003 |
ous | -0.003 |
od | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
dollars | +0.026 |
wounds | +0.026 |
oster | +0.026 |
over | +0.025 |
vet | +0.025 |
Neg logit contributions | |
Jan | -0.021 |
Jos | -0.020 |
Sus | -0.020 |
Suz | -0.019 |
od | -0.019 |
Token | wise |
Token ID | 10787 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
wounds | +0.035 |
dollars | +0.034 |
over | +0.033 |
ages | +0.032 |
promises | +0.032 |
Neg logit contributions | |
Jan | -0.031 |
stair | -0.030 |
Jos | -0.029 |
Sus | -0.029 |
Suz | -0.028 |
Token | guy |
Token ID | 3516 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
wounds | +0.048 |
dollars | +0.046 |
injuries | +0.044 |
over | +0.044 |
promises | +0.044 |
Neg logit contributions | |
Jan | -0.065 |
Sus | -0.062 |
Jos | -0.061 |
Suz | -0.061 |
stair | -0.061 |
Token | called |
Token ID | 1444 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
wounds | +0.029 |
dollars | +0.029 |
End | +0.028 |
oster | +0.027 |
over | +0.027 |
Neg logit contributions | |
Jan | -0.035 |
od | -0.033 |
Jos | -0.032 |
Sus | -0.032 |
Suz | -0.032 |
Token | Mr |
Token ID | 1770 |
Feature activation | -6.24e+00 |
Pos logit contributions | |
over | +0.070 |
dollars | +0.070 |
wounds | +0.069 |
oster | +0.068 |
vet | +0.067 |
Neg logit contributions | |
Jan | -0.062 |
Jos | -0.059 |
Sus | -0.057 |
Suz | -0.056 |
stair | -0.055 |
Token | Smith |
Token ID | 4176 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
oster | +0.155 |
dollars | +0.154 |
wounds | +0.154 |
End | +0.153 |
promises | +0.150 |
Neg logit contributions | |
Jan | -0.112 |
od | -0.108 |
ous | -0.102 |
Jo | -0.101 |
J | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
wounds | +0.025 |
oster | +0.024 |
over | +0.024 |
dollars | +0.023 |
vet | +0.023 |
Neg logit contributions | |
Jan | -0.023 |
od | -0.021 |
Jos | -0.021 |
ous | -0.021 |
Sus | -0.020 |
Token | He |
Token ID | 679 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
wounds | +0.028 |
dollars | +0.028 |
oster | +0.028 |
over | +0.027 |
vet | +0.026 |
Neg logit contributions | |
Jan | -0.024 |
Jos | -0.022 |
Sus | -0.022 |
J | -0.021 |
Suz | -0.021 |
Token | had |
Token ID | 550 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
dollars | +0.016 |
wounds | +0.016 |
over | +0.016 |
oster | +0.015 |
injuries | +0.015 |
Neg logit contributions | |
Jan | -0.015 |
Jos | -0.014 |
Sus | -0.014 |
od | -0.013 |
Suz | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
Jan | +0.010 |
Jos | +0.009 |
Sus | +0.009 |
Jo | +0.009 |
Suz | +0.009 |
Neg logit contributions | |
dollars | -0.014 |
over | -0.014 |
oster | -0.014 |
wounds | -0.013 |
End | -0.013 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
wounds | +0.073 |
dollars | +0.072 |
oster | +0.068 |
vet | +0.065 |
promises | +0.065 |
Neg logit contributions | |
Jan | -0.077 |
Sus | -0.073 |
Jos | -0.072 |
Jo | -0.072 |
Suz | -0.070 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
Jan | +0.021 |
Jos | +0.020 |
icated | +0.019 |
od | +0.019 |
stair | +0.019 |
Neg logit contributions | |
over | -0.031 |
dollars | -0.030 |
End | -0.030 |
wounds | -0.030 |
oster | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
dollars | +0.059 |
oster | +0.058 |
wounds | +0.057 |
over | +0.056 |
vet | +0.055 |
Neg logit contributions | |
Jan | -0.041 |
Jos | -0.039 |
Sus | -0.038 |
Jo | -0.037 |
Suz | -0.037 |
Token | time |
Token ID | 640 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
wounds | +0.000 |
dollars | +0.000 |
oster | +0.000 |
vet | +0.000 |
over | +0.000 |
Neg logit contributions | |
Jan | -0.000 |
Jos | -0.000 |
Sus | -0.000 |
stair | -0.000 |
Suz | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
over | +0.011 |
End | +0.010 |
dollars | +0.010 |
pig | +0.010 |
promises | +0.009 |
Neg logit contributions | |
contain | -0.016 |
sorts | -0.016 |
icated | -0.016 |
Jos | -0.016 |
Jan | -0.015 |
Token | Mr |
Token ID | 1770 |
Feature activation | -6.24e+00 |
Pos logit contributions | |
Jan | +0.045 |
Jos | +0.043 |
Sus | +0.042 |
Suz | +0.041 |
stair | +0.041 |
Neg logit contributions | |
dollars | -0.040 |
wounds | -0.039 |
over | -0.039 |
oster | -0.039 |
vet | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
oster | +0.159 |
dollars | +0.155 |
wounds | +0.154 |
End | +0.147 |
cents | +0.146 |
Neg logit contributions | |
Jan | -0.120 |
od | -0.114 |
Jos | -0.108 |
icated | -0.107 |
ous | -0.106 |
Token | Frog |
Token ID | 28328 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
wounds | +0.050 |
dollars | +0.050 |
oster | +0.048 |
over | +0.048 |
vet | +0.047 |
Neg logit contributions | |
Jan | -0.048 |
Jos | -0.046 |
Sus | -0.045 |
Suz | -0.044 |
Jo | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
Jan | +0.020 |
Jos | +0.019 |
Sus | +0.019 |
Suz | +0.018 |
od | +0.018 |
Neg logit contributions | |
wounds | -0.024 |
dollars | -0.024 |
over | -0.023 |
vet | -0.023 |
oster | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
over | +0.065 |
dollars | +0.065 |
wounds | +0.063 |
vet | +0.063 |
oster | +0.063 |
Neg logit contributions | |
Jan | -0.069 |
Jos | -0.067 |
stair | -0.065 |
od | -0.064 |
Sus | -0.064 |
Token | naughty |
Token ID | 45128 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
dollars | +0.004 |
wounds | +0.004 |
over | +0.004 |
oster | +0.004 |
promises | +0.004 |
Neg logit contributions | |
Jan | -0.005 |
Jos | -0.005 |
Sus | -0.005 |
Suz | -0.005 |
stair | -0.005 |
Token | She |
Token ID | 1375 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
Jan | +0.020 |
Jos | +0.019 |
Sus | +0.019 |
Suz | +0.018 |
od | +0.018 |
Neg logit contributions | |
over | -0.017 |
dollars | -0.017 |
wounds | -0.016 |
oster | -0.016 |
vet | -0.016 |
Token | said |
Token ID | 531 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Jan | +0.007 |
Jos | +0.007 |
Sus | +0.007 |
Suz | +0.007 |
stair | +0.007 |
Neg logit contributions | |
over | -0.007 |
dollars | -0.007 |
wounds | -0.007 |
oster | -0.007 |
vet | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
pig | +0.022 |
dollars | +0.020 |
vet | +0.020 |
over | +0.019 |
wounds | +0.019 |
Neg logit contributions | |
sorts | -0.034 |
Jos | -0.033 |
icated | -0.033 |
contain | -0.032 |
Jan | -0.031 |
Token | " |
Token ID | 366 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
Jan | +0.053 |
Jos | +0.051 |
Sus | +0.049 |
stair | +0.049 |
Suz | +0.049 |
Neg logit contributions | |
over | -0.044 |
dollars | -0.044 |
wounds | -0.044 |
oster | -0.044 |
vet | -0.043 |
Token | Hello |
Token ID | 15496 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
over | +0.017 |
vet | +0.017 |
oster | +0.016 |
wounds | +0.016 |
End | +0.016 |
Neg logit contributions | |
Jan | -0.021 |
Jos | -0.020 |
ous | -0.020 |
Sus | -0.020 |
Suz | -0.020 |
Token | Mr |
Token ID | 1770 |
Feature activation | -6.24e+00 |
Pos logit contributions | |
over | +0.021 |
dollars | +0.021 |
pig | +0.020 |
vet | +0.020 |
promises | +0.020 |
Neg logit contributions | |
Jan | -0.020 |
Jos | -0.020 |
contain | -0.019 |
Sus | -0.019 |
Suz | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
oster | +0.149 |
wounds | +0.147 |
dollars | +0.144 |
End | +0.141 |
over | +0.137 |
Neg logit contributions | |
Jan | -0.129 |
od | -0.120 |
Jos | -0.119 |
J | -0.118 |
Sus | -0.117 |
Token | Beetle |
Token ID | 47464 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
over | +0.030 |
vet | +0.029 |
dollars | +0.029 |
End | +0.028 |
oster | +0.028 |
Neg logit contributions | |
Jan | -0.028 |
Jos | -0.027 |
Sus | -0.027 |
contain | -0.026 |
Suz | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Jan | +0.001 |
Jos | +0.001 |
Sus | +0.001 |
od | +0.001 |
stair | +0.001 |
Neg logit contributions | |
wounds | -0.003 |
over | -0.002 |
oster | -0.002 |
dollars | -0.002 |
vet | -0.002 |
Token | you |
Token ID | 345 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Jan | +0.043 |
Jos | +0.042 |
Suz | +0.040 |
Jo | +0.040 |
Sus | +0.040 |
Neg logit contributions | |
pig | -0.029 |
dollars | -0.028 |
vet | -0.028 |
promises | -0.028 |
End | -0.027 |
Token | look |
Token ID | 804 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
promises | +0.041 |
oster | +0.040 |
pig | +0.040 |
dollars | +0.040 |
over | +0.040 |
Neg logit contributions | |
Jos | -0.030 |
Jan | -0.029 |
stair | -0.028 |
Jo | -0.027 |
Sus | -0.027 |
Token | gr |
Token ID | 1036 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
wounds | +0.018 |
dollars | +0.018 |
promises | +0.017 |
over | +0.017 |
ages | +0.016 |
Neg logit contributions | |
Jan | -0.016 |
stair | -0.016 |
Sus | -0.015 |
Jos | -0.015 |
J | -0.015 |
Token | umpy |
Token ID | 32152 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
over | +0.016 |
dollars | +0.016 |
oster | +0.016 |
wounds | +0.015 |
vet | +0.015 |
Neg logit contributions | |
Jan | -0.023 |
Jos | -0.022 |
Sus | -0.022 |
Suz | -0.021 |
stair | -0.021 |
Token | old |
Token ID | 1468 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
wounds | +0.028 |
dollars | +0.028 |
over | +0.025 |
promises | +0.025 |
oster | +0.024 |
Neg logit contributions | |
Jan | -0.050 |
Sus | -0.048 |
Jos | -0.047 |
stair | -0.047 |
ous | -0.047 |
Token | man |
Token ID | 582 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
dollars | +0.062 |
wounds | +0.061 |
End | +0.055 |
over | +0.055 |
promises | +0.054 |
Neg logit contributions | |
Jan | -0.103 |
stair | -0.103 |
Sus | -0.101 |
ous | -0.098 |
Suz | -0.098 |
Token | named |
Token ID | 3706 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
wounds | +0.022 |
over | +0.022 |
dollars | +0.022 |
oster | +0.021 |
End | +0.020 |
Neg logit contributions | |
Jan | -0.018 |
Jos | -0.017 |
Sus | -0.017 |
od | -0.017 |
Suz | -0.017 |
Token | Mr |
Token ID | 1770 |
Feature activation | -6.21e+00 |
Pos logit contributions | |
pig | +0.039 |
dollars | +0.037 |
vet | +0.037 |
beef | +0.037 |
oster | +0.036 |
Neg logit contributions | |
Jos | -0.048 |
Jan | -0.048 |
stair | -0.047 |
od | -0.047 |
yt | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
oster | +0.168 |
End | +0.163 |
dollars | +0.162 |
wounds | +0.162 |
over | +0.155 |
Neg logit contributions | |
od | -0.100 |
Jan | -0.097 |
J | -0.091 |
ous | -0.086 |
ill | -0.086 |
Token | Brown |
Token ID | 4373 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
dollars | +0.040 |
over | +0.040 |
wounds | +0.039 |
oster | +0.039 |
vet | +0.038 |
Neg logit contributions | |
Jan | -0.041 |
Jos | -0.039 |
Sus | -0.038 |
Suz | -0.038 |
stair | -0.038 |
Token | lived |
Token ID | 5615 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Jan | +0.004 |
od | +0.004 |
Sus | +0.004 |
Jos | +0.004 |
icated | +0.004 |
Neg logit contributions | |
wounds | -0.006 |
dollars | -0.006 |
over | -0.006 |
injuries | -0.006 |
oster | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
dollars | +0.007 |
wounds | +0.007 |
over | +0.007 |
oster | +0.007 |
End | +0.007 |
Neg logit contributions | |
Jan | -0.004 |
stair | -0.003 |
od | -0.003 |
Jos | -0.003 |
Sus | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
dollars | +0.013 |
oster | +0.013 |
cents | +0.012 |
wounds | +0.012 |
over | +0.012 |
Neg logit contributions | |
Jan | -0.005 |
Jos | -0.004 |
Sus | -0.004 |
Jo | -0.004 |
Fr | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
Jan | +0.028 |
Jos | +0.026 |
Sus | +0.026 |
stair | +0.025 |
Suz | +0.025 |
Neg logit contributions | |
over | -0.025 |
dollars | -0.025 |
wounds | -0.024 |
oster | -0.024 |
vet | -0.024 |
Token | sweet |
Token ID | 6029 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
dollars | +0.013 |
over | +0.013 |
wounds | +0.013 |
oster | +0.013 |
vet | +0.012 |
Neg logit contributions | |
Jan | -0.012 |
Jos | -0.012 |
Sus | -0.012 |
Suz | -0.011 |
stair | -0.011 |
Token | aroma |
Token ID | 31242 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
Jan | +0.006 |
Jos | +0.006 |
Sus | +0.006 |
Suz | +0.005 |
od | +0.005 |
Neg logit contributions | |
over | -0.006 |
oster | -0.006 |
dollars | -0.006 |
wounds | -0.006 |
vet | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | -8.49e-01 |
Pos logit contributions | |
over | +0.008 |
dollars | +0.008 |
wounds | +0.007 |
oster | +0.007 |
vet | +0.007 |
Neg logit contributions | |
Jan | -0.009 |
Jos | -0.009 |
Sus | -0.008 |
Suz | -0.008 |
stair | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
over | +0.021 |
oster | +0.020 |
dollars | +0.020 |
wounds | +0.019 |
vet | +0.019 |
Neg logit contributions | |
Jan | -0.018 |
Jos | -0.017 |
Sus | -0.017 |
Suz | -0.016 |
J | -0.016 |
Token | freshly |
Token ID | 29026 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
Jan | +0.036 |
Jos | +0.034 |
Sus | +0.034 |
stair | +0.033 |
Suz | +0.033 |
Neg logit contributions | |
over | -0.037 |
dollars | -0.037 |
wounds | -0.037 |
oster | -0.036 |
vet | -0.035 |
Token | baked |
Token ID | 22979 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
wounds | +0.151 |
dollars | +0.149 |
vet | +0.143 |
over | +0.142 |
oster | +0.139 |
Neg logit contributions | |
Jan | -0.121 |
od | -0.116 |
Jos | -0.115 |
Sus | -0.112 |
sorts | -0.112 |
Token | cake |
Token ID | 12187 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
wounds | +0.010 |
dollars | +0.010 |
oster | +0.010 |
over | +0.010 |
vet | +0.010 |
Neg logit contributions | |
Jan | -0.010 |
Jos | -0.009 |
Sus | -0.009 |
od | -0.009 |
Suz | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
over | +0.019 |
dollars | +0.019 |
wounds | +0.018 |
ages | +0.017 |
vet | +0.017 |
Neg logit contributions | |
Jan | -0.027 |
Jos | -0.026 |
icated | -0.026 |
Sus | -0.025 |
J | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Jan | +0.017 |
Jos | +0.016 |
Sus | +0.016 |
Suz | +0.015 |
Jo | +0.015 |
Neg logit contributions | |
dollars | -0.017 |
wounds | -0.017 |
oster | -0.016 |
over | -0.016 |
injuries | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
Jan | +0.030 |
Jos | +0.029 |
Sus | +0.028 |
stair | +0.028 |
ous | +0.028 |
Neg logit contributions | |
over | -0.015 |
oster | -0.015 |
vet | -0.015 |
wounds | -0.015 |
dollars | -0.014 |
Token | j |
Token ID | 474 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
dollars | +0.028 |
wounds | +0.028 |
over | +0.027 |
ages | +0.027 |
promises | +0.026 |
Neg logit contributions | |
Jan | -0.024 |
stair | -0.024 |
Jos | -0.023 |
Sus | -0.023 |
Suz | -0.022 |
Token | olly |
Token ID | 5098 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
wounds | +0.035 |
dollars | +0.034 |
over | +0.033 |
oster | +0.032 |
vet | +0.032 |
Neg logit contributions | |
Jan | -0.046 |
Jos | -0.044 |
Sus | -0.043 |
stair | -0.043 |
Suz | -0.042 |
Token | old |
Token ID | 1468 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
wounds | +0.032 |
dollars | +0.031 |
promises | +0.030 |
injuries | +0.029 |
being | +0.029 |
Neg logit contributions | |
Jan | -0.030 |
stair | -0.030 |
Sus | -0.030 |
Jos | -0.029 |
Suz | -0.029 |
Token | lady |
Token ID | 10846 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
dollars | +0.067 |
wounds | +0.066 |
over | +0.065 |
oster | +0.064 |
promises | +0.060 |
Neg logit contributions | |
Jan | -0.122 |
Jos | -0.117 |
stair | -0.117 |
Sus | -0.117 |
Suz | -0.115 |
Token | named |
Token ID | 3706 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
wounds | +0.023 |
oster | +0.022 |
injuries | +0.022 |
dollars | +0.022 |
End | +0.021 |
Neg logit contributions | |
Jan | -0.024 |
Jos | -0.023 |
Sus | -0.023 |
od | -0.023 |
Suz | -0.022 |
Token | Mrs |
Token ID | 9074 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
over | +0.037 |
vet | +0.036 |
dollars | +0.036 |
pig | +0.035 |
oster | +0.035 |
Neg logit contributions | |
Jan | -0.047 |
Jos | -0.045 |
stair | -0.044 |
ous | -0.044 |
od | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
oster | +0.165 |
wounds | +0.153 |
dollars | +0.151 |
promises | +0.149 |
over | +0.148 |
Neg logit contributions | |
Jan | -0.114 |
od | -0.110 |
Jos | -0.104 |
ous | -0.103 |
Jo | -0.102 |
Token | Maple |
Token ID | 21249 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
over | +0.044 |
dollars | +0.043 |
wounds | +0.042 |
oster | +0.042 |
vet | +0.042 |
Neg logit contributions | |
Jan | -0.035 |
Jos | -0.034 |
Sus | -0.033 |
Suz | -0.032 |
stair | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
wounds | +0.041 |
dollars | +0.039 |
injuries | +0.039 |
ringe | +0.039 |
etchup | +0.038 |
Neg logit contributions | |
Jan | -0.029 |
od | -0.028 |
Sus | -0.028 |
Jo | -0.028 |
J | -0.026 |
Token | Every |
Token ID | 3887 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
over | +0.010 |
dollars | +0.010 |
wounds | +0.009 |
oster | +0.009 |
vet | +0.009 |
Neg logit contributions | |
Jan | -0.009 |
Jos | -0.008 |
Sus | -0.008 |
Suz | -0.008 |
od | -0.008 |
Token | morning |
Token ID | 3329 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
wounds | +0.102 |
dollars | +0.101 |
oster | +0.097 |
over | +0.096 |
promises | +0.095 |
Neg logit contributions | |
Jan | -0.074 |
Jos | -0.069 |
stair | -0.069 |
Sus | -0.068 |
Jo | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
Jan | +0.001 |
Jos | +0.001 |
od | +0.001 |
ous | +0.001 |
Sus | +0.001 |
Neg logit contributions | |
End | -0.001 |
over | -0.001 |
vet | -0.001 |
wounds | -0.001 |
oster | -0.001 |
Token | end |
Token ID | 886 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Jan | +0.061 |
Jos | +0.058 |
Sus | +0.057 |
Suz | +0.057 |
ous | +0.056 |
Neg logit contributions | |
over | -0.035 |
vet | -0.035 |
dollars | -0.035 |
oster | -0.034 |
End | -0.034 |
Token | of |
Token ID | 286 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
Jan | +0.007 |
Jos | +0.007 |
od | +0.006 |
stair | +0.006 |
icated | +0.006 |
Neg logit contributions | |
over | -0.007 |
dollars | -0.007 |
vet | -0.007 |
oster | -0.006 |
wounds | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Jan | +0.004 |
Jos | +0.004 |
Sus | +0.004 |
Suz | +0.004 |
stair | +0.004 |
Neg logit contributions | |
dollars | -0.005 |
over | -0.005 |
wounds | -0.005 |
oster | -0.005 |
vet | -0.005 |
Token | day |
Token ID | 1110 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Jan | +0.019 |
Jos | +0.018 |
Sus | +0.018 |
Suz | +0.018 |
od | +0.017 |
Neg logit contributions | |
over | -0.025 |
dollars | -0.025 |
wounds | -0.025 |
oster | -0.025 |
vet | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
over | +0.026 |
dollars | +0.025 |
oster | +0.025 |
wounds | +0.025 |
vet | +0.025 |
Neg logit contributions | |
Jan | -0.021 |
Jos | -0.020 |
Sus | -0.019 |
stair | -0.019 |
Suz | -0.019 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
Jan | +0.046 |
Sus | +0.043 |
Suz | +0.041 |
Jos | +0.040 |
J | +0.039 |
Neg logit contributions | |
dollars | -0.096 |
wounds | -0.095 |
oster | -0.094 |
over | -0.094 |
vet | -0.089 |
Token | knew |
Token ID | 2993 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Jan | +0.059 |
Jos | +0.056 |
Sus | +0.055 |
Jo | +0.054 |
J | +0.053 |
Neg logit contributions | |
dollars | -0.065 |
over | -0.065 |
wounds | -0.064 |
oster | -0.063 |
vet | -0.061 |
Token | he |
Token ID | 339 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
oster | +0.037 |
over | +0.037 |
dollars | +0.036 |
wounds | +0.035 |
etchup | +0.034 |
Neg logit contributions | |
Jan | -0.033 |
Sus | -0.031 |
Jos | -0.030 |
Suz | -0.030 |
Jo | -0.030 |
Token | had |
Token ID | 550 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
wounds | +0.020 |
over | +0.020 |
dollars | +0.020 |
oster | +0.020 |
vet | +0.019 |
Neg logit contributions | |
Jan | -0.012 |
Sus | -0.011 |
Jos | -0.011 |
Jo | -0.010 |
od | -0.010 |
Token | played |
Token ID | 2826 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Jan | +0.003 |
Jos | +0.003 |
Sus | +0.003 |
Suz | +0.003 |
stair | +0.003 |
Neg logit contributions | |
over | -0.005 |
dollars | -0.005 |
oster | -0.005 |
wounds | -0.005 |
vet | -0.005 |
Token | that |
Token ID | 326 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
Jan | +0.026 |
Jos | +0.024 |
Sus | +0.024 |
od | +0.023 |
Suz | +0.023 |
Neg logit contributions | |
wounds | -0.037 |
over | -0.036 |
dollars | -0.036 |
oster | -0.036 |
vet | -0.035 |
Token | if |
Token ID | 611 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
pig | +0.009 |
vet | +0.009 |
dollars | +0.008 |
over | +0.008 |
promises | +0.008 |
Neg logit contributions | |
Jan | -0.011 |
Jos | -0.010 |
od | -0.010 |
Suz | -0.010 |
contain | -0.010 |
Token | you |
Token ID | 345 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
over | +0.037 |
dollars | +0.037 |
wounds | +0.036 |
oster | +0.036 |
vet | +0.035 |
Neg logit contributions | |
Jan | -0.037 |
Jos | -0.035 |
Sus | -0.035 |
Suz | -0.034 |
Jo | -0.034 |
Token | hide |
Token ID | 7808 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
over | +0.033 |
dollars | +0.033 |
wounds | +0.033 |
oster | +0.032 |
vet | +0.032 |
Neg logit contributions | |
Jan | -0.025 |
Jos | -0.024 |
Sus | -0.024 |
Suz | -0.023 |
od | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
over | +0.006 |
dollars | +0.006 |
oster | +0.006 |
wounds | +0.006 |
vet | +0.006 |
Neg logit contributions | |
Jan | -0.005 |
Jos | -0.005 |
Sus | -0.005 |
Suz | -0.005 |
Jo | -0.005 |
Token | people |
Token ID | 661 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
Jan | +0.043 |
Jos | +0.041 |
Sus | +0.040 |
Suz | +0.039 |
stair | +0.039 |
Neg logit contributions | |
over | -0.047 |
dollars | -0.046 |
wounds | -0.046 |
oster | -0.046 |
vet | -0.044 |
Token | can |
Token ID | 460 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
Jan | +0.066 |
Sus | +0.062 |
Jos | +0.061 |
ous | +0.060 |
Suz | +0.059 |
Neg logit contributions | |
over | -0.085 |
wounds | -0.085 |
dollars | -0.084 |
oster | -0.083 |
vet | -0.082 |
Token | 't |
Token ID | 470 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
Jan | +0.032 |
Jos | +0.032 |
Sus | +0.030 |
od | +0.030 |
stair | +0.030 |
Neg logit contributions | |
vet | -0.035 |
oster | -0.035 |
wounds | -0.034 |
over | -0.034 |
pig | -0.033 |
Token | find |
Token ID | 1064 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Jan | +0.064 |
Jos | +0.062 |
Sus | +0.058 |
stair | +0.058 |
od | +0.058 |
Neg logit contributions | |
over | -0.071 |
vet | -0.070 |
oster | -0.070 |
dollars | -0.069 |
wounds | -0.069 |
Token | you |
Token ID | 345 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Jan | +0.030 |
Jos | +0.028 |
Sus | +0.028 |
Suz | +0.027 |
Jo | +0.027 |
Neg logit contributions | |
over | -0.030 |
dollars | -0.029 |
oster | -0.029 |
wounds | -0.029 |
vet | -0.028 |
Token | ? |
Token ID | 30 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
over | +0.027 |
dollars | +0.027 |
oster | +0.027 |
wounds | +0.027 |
vet | +0.026 |
Neg logit contributions | |
Jan | -0.019 |
Jos | -0.018 |
Sus | -0.017 |
Suz | -0.017 |
stair | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
Jan | +0.024 |
Jos | +0.023 |
Sus | +0.023 |
od | +0.022 |
Suz | +0.022 |
Neg logit contributions | |
oster | -0.031 |
dollars | -0.031 |
over | -0.031 |
wounds | -0.030 |
vet | -0.030 |
Token | From |
Token ID | 3574 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Jan | +0.019 |
Jos | +0.018 |
od | +0.017 |
stair | +0.017 |
Sus | +0.017 |
Neg logit contributions | |
over | -0.018 |
vet | -0.018 |
dollars | -0.018 |
wounds | -0.017 |
promises | -0.017 |
Token | that |
Token ID | 326 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
dollars | +0.041 |
over | +0.039 |
oster | +0.038 |
wounds | +0.037 |
ages | +0.037 |
Neg logit contributions | |
Jan | -0.036 |
Sus | -0.033 |
Suz | -0.033 |
J | -0.032 |
Jos | -0.032 |
Token | day |
Token ID | 1110 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
End | +0.001 |
over | +0.001 |
promises | +0.001 |
oster | +0.001 |
vet | +0.001 |
Neg logit contributions | |
Jan | -0.001 |
Jos | -0.001 |
od | -0.001 |
Suz | -0.001 |
Sus | -0.001 |
Token | on |
Token ID | 319 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
over | +0.042 |
dollars | +0.041 |
End | +0.039 |
oster | +0.038 |
vet | +0.038 |
Neg logit contributions | |
Jan | -0.049 |
Jos | -0.048 |
Sus | -0.047 |
Suz | -0.047 |
od | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
over | +0.004 |
dollars | +0.004 |
wounds | +0.004 |
oster | +0.004 |
vet | +0.003 |
Neg logit contributions | |
Jan | -0.003 |
Jos | -0.003 |
Sus | -0.003 |
Suz | -0.002 |
stair | -0.002 |
Token | Ros |
Token ID | 10018 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
Jan | +0.065 |
Jos | +0.062 |
ous | +0.062 |
stair | +0.061 |
contain | +0.060 |
Neg logit contributions | |
vet | -0.070 |
over | -0.070 |
dollars | -0.069 |
promises | -0.068 |
wounds | -0.068 |
Token | ie |
Token ID | 494 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Jan | +0.116 |
contain | +0.113 |
stair | +0.109 |
J | +0.109 |
Jo | +0.109 |
Neg logit contributions | |
over | -0.098 |
promises | -0.098 |
dollars | -0.097 |
oster | -0.095 |
End | -0.095 |
Token | took |
Token ID | 1718 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
Jan | +0.033 |
Jos | +0.031 |
Sus | +0.030 |
od | +0.030 |
Suz | +0.030 |
Neg logit contributions | |
dollars | -0.035 |
over | -0.035 |
wounds | -0.035 |
oster | -0.034 |
vet | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
dollars | +0.009 |
over | +0.009 |
wounds | +0.009 |
oster | +0.009 |
vet | +0.009 |
Neg logit contributions | |
Jan | -0.011 |
Jos | -0.010 |
Sus | -0.010 |
Suz | -0.010 |
stair | -0.010 |
Token | bath |
Token ID | 7837 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Jan | +0.059 |
Jos | +0.057 |
od | +0.057 |
J | +0.054 |
Jo | +0.053 |
Neg logit contributions | |
oster | -0.046 |
pig | -0.046 |
vet | -0.046 |
dollars | -0.045 |
medicine | -0.044 |
Token | big |
Token ID | 1263 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
stair | +0.041 |
Jan | +0.040 |
tw | +0.040 |
Sus | +0.037 |
tr | +0.037 |
Neg logit contributions | |
wounds | -0.065 |
dollars | -0.064 |
over | -0.064 |
End | -0.063 |
oster | -0.063 |
Token | smile |
Token ID | 8212 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Jan | +0.045 |
Jos | +0.043 |
Sus | +0.042 |
Suz | +0.041 |
od | +0.041 |
Neg logit contributions | |
over | -0.037 |
dollars | -0.037 |
wounds | -0.037 |
oster | -0.036 |
vet | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
wounds | +0.034 |
oster | +0.033 |
dollars | +0.032 |
vet | +0.032 |
promises | +0.032 |
Neg logit contributions | |
Jan | -0.020 |
ous | -0.019 |
Jos | -0.018 |
od | -0.018 |
stair | -0.018 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
dollars | +0.079 |
oster | +0.077 |
over | +0.077 |
wounds | +0.077 |
vet | +0.074 |
Neg logit contributions | |
Jan | -0.065 |
Jos | -0.062 |
Sus | -0.061 |
Suz | -0.059 |
J | -0.058 |
Token | helping |
Token ID | 5742 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
oster | +0.053 |
over | +0.053 |
dollars | +0.053 |
wounds | +0.051 |
vet | +0.051 |
Neg logit contributions | |
Jan | -0.030 |
Jos | -0.028 |
Sus | -0.028 |
Jo | -0.027 |
J | -0.026 |
Token | people |
Token ID | 661 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
Jan | +0.024 |
Jos | +0.023 |
Sus | +0.022 |
Suz | +0.022 |
stair | +0.022 |
Neg logit contributions | |
dollars | -0.016 |
over | -0.016 |
wounds | -0.016 |
oster | -0.016 |
vet | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
Jan | +0.096 |
Jos | +0.092 |
Sus | +0.090 |
od | +0.090 |
stair | +0.088 |
Neg logit contributions | |
dollars | -0.091 |
over | -0.090 |
wounds | -0.090 |
oster | -0.089 |
vet | -0.088 |
Token | One |
Token ID | 1881 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
Jan | +0.020 |
Jos | +0.019 |
Sus | +0.019 |
Jo | +0.019 |
Suz | +0.019 |
Neg logit contributions | |
wounds | -0.021 |
dollars | -0.021 |
over | -0.021 |
oster | -0.021 |
injuries | -0.020 |
Token | morning |
Token ID | 3329 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
wounds | +0.024 |
dollars | +0.023 |
over | +0.023 |
oster | +0.022 |
injuries | +0.022 |
Neg logit contributions | |
Jan | -0.015 |
Jos | -0.013 |
stair | -0.013 |
Sus | -0.013 |
Suz | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
wounds | +0.027 |
dollars | +0.026 |
oster | +0.026 |
over | +0.025 |
promises | +0.025 |
Neg logit contributions | |
Jan | -0.015 |
Sus | -0.014 |
Jos | -0.014 |
J | -0.014 |
Suz | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Jan | +0.045 |
Jos | +0.042 |
Sus | +0.042 |
J | +0.040 |
Suz | +0.040 |
Neg logit contributions | |
dollars | -0.063 |
wounds | -0.062 |
over | -0.061 |
oster | -0.060 |
promises | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Jan | +0.009 |
Jos | +0.008 |
Sus | +0.008 |
Suz | +0.008 |
stair | +0.007 |
Neg logit contributions | |
over | -0.021 |
dollars | -0.021 |
wounds | -0.021 |
oster | -0.021 |
vet | -0.020 |
Token | wonderful |
Token ID | 7932 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
Jan | +0.045 |
Jos | +0.044 |
od | +0.042 |
Suz | +0.041 |
ous | +0.041 |
Neg logit contributions | |
over | -0.048 |
dollars | -0.048 |
oster | -0.047 |
vet | -0.047 |
pig | -0.046 |
Token | time |
Token ID | 640 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
over | +0.008 |
dollars | +0.007 |
oster | +0.007 |
wounds | +0.007 |
vet | +0.007 |
Neg logit contributions | |
Jan | -0.010 |
Jos | -0.009 |
Sus | -0.009 |
od | -0.009 |
Suz | -0.009 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Jan | +0.012 |
Jos | +0.011 |
Sus | +0.011 |
Suz | +0.011 |
stair | +0.011 |
Neg logit contributions | |
dollars | -0.015 |
over | -0.015 |
wounds | -0.015 |
oster | -0.015 |
vet | -0.014 |
Token | with |
Token ID | 351 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
over | +0.006 |
dollars | +0.006 |
wounds | +0.005 |
oster | +0.005 |
vet | +0.005 |
Neg logit contributions | |
Jan | -0.005 |
Jos | -0.005 |
Sus | -0.005 |
Suz | -0.005 |
stair | -0.005 |
Token | all |
Token ID | 477 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
Jan | +0.027 |
Jos | +0.026 |
Sus | +0.025 |
Suz | +0.025 |
Jo | +0.025 |
Neg logit contributions | |
dollars | -0.035 |
over | -0.034 |
oster | -0.034 |
wounds | -0.034 |
vet | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
Jan | +0.070 |
Jos | +0.068 |
od | +0.065 |
ous | +0.065 |
Sus | +0.065 |
Neg logit contributions | |
over | -0.071 |
dollars | -0.070 |
wounds | -0.068 |
oster | -0.067 |
promises | -0.067 |
Token | different |
Token ID | 1180 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Jan | +0.010 |
Jos | +0.010 |
Sus | +0.009 |
stair | +0.009 |
Suz | +0.009 |
Neg logit contributions | |
over | -0.009 |
oster | -0.009 |
dollars | -0.009 |
wounds | -0.009 |
vet | -0.009 |
Token | structures |
Token ID | 8573 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
Jan | +0.042 |
Jos | +0.040 |
Sus | +0.039 |
Suz | +0.038 |
od | +0.038 |
Neg logit contributions | |
dollars | -0.027 |
over | -0.027 |
wounds | -0.027 |
oster | -0.026 |
vet | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
Jan | +0.058 |
Jos | +0.056 |
Sus | +0.054 |
Suz | +0.054 |
stair | +0.052 |
Neg logit contributions | |
dollars | -0.045 |
over | -0.045 |
wounds | -0.043 |
vet | -0.042 |
oster | -0.042 |
Token | He |
Token ID | 679 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
Jan | +0.012 |
Jo | +0.011 |
Sus | +0.011 |
Jos | +0.011 |
Suz | +0.010 |
Neg logit contributions | |
dollars | -0.012 |
wounds | -0.012 |
oster | -0.011 |
over | -0.011 |
injuries | -0.011 |
Token | food |
Token ID | 2057 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
oster | +0.035 |
over | +0.033 |
dollars | +0.033 |
ages | +0.031 |
End | +0.031 |
Neg logit contributions | |
Jan | -0.023 |
Sus | -0.023 |
Suz | -0.022 |
Jo | -0.021 |
Jos | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
oster | +0.024 |
wounds | +0.023 |
over | +0.023 |
dollars | +0.023 |
End | +0.023 |
Neg logit contributions | |
Jan | -0.018 |
Sus | -0.017 |
Jos | -0.017 |
stair | -0.016 |
Suz | -0.016 |
Token | From |
Token ID | 3574 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Jan | +0.010 |
Sus | +0.010 |
Jos | +0.010 |
Suz | +0.009 |
J | +0.009 |
Neg logit contributions | |
oster | -0.018 |
over | -0.018 |
dollars | -0.018 |
wounds | -0.018 |
injuries | -0.017 |
Token | that |
Token ID | 326 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
dollars | +0.046 |
oster | +0.044 |
over | +0.043 |
ages | +0.042 |
cents | +0.042 |
Neg logit contributions | |
Jan | -0.038 |
Sus | -0.034 |
Suz | -0.034 |
J | -0.032 |
Jo | -0.032 |
Token | day |
Token ID | 1110 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
End | +0.000 |
over | +0.000 |
oster | +0.000 |
dollars | +0.000 |
vet | +0.000 |
Neg logit contributions | |
Jan | -0.000 |
Jos | -0.000 |
Sus | -0.000 |
Suz | -0.000 |
od | -0.000 |
Token | on |
Token ID | 319 |
Feature activation | -4.08e-03 |
Pos logit contributions | |
over | +0.040 |
dollars | +0.039 |
End | +0.037 |
oster | +0.036 |
vet | +0.036 |
Neg logit contributions | |
Jan | -0.049 |
Jos | -0.049 |
Sus | -0.048 |
Suz | -0.047 |
icated | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
dollars | +0.000 |
oster | +0.000 |
wounds | +0.000 |
over | +0.000 |
vet | +0.000 |
Neg logit contributions | |
Jan | -0.000 |
Sus | -0.000 |
Jos | -0.000 |
stair | -0.000 |
Suz | -0.000 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Jan | +0.058 |
Jos | +0.056 |
Sus | +0.056 |
Suz | +0.053 |
stair | +0.052 |
Neg logit contributions | |
oster | -0.082 |
over | -0.081 |
dollars | -0.081 |
wounds | -0.080 |
ages | -0.076 |
Token | always |
Token ID | 1464 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Jan | +0.031 |
Jos | +0.030 |
Sus | +0.029 |
Suz | +0.028 |
od | +0.028 |
Neg logit contributions | |
dollars | -0.031 |
over | -0.031 |
wounds | -0.030 |
oster | -0.030 |
vet | -0.029 |
Token | made |
Token ID | 925 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
dollars | +0.037 |
over | +0.037 |
wounds | +0.036 |
vet | +0.035 |
promises | +0.035 |
Neg logit contributions | |
Jan | -0.054 |
Jos | -0.052 |
stair | -0.051 |
od | -0.051 |
Sus | -0.050 |
Token | sure |
Token ID | 1654 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
Jan | +0.026 |
Jos | +0.025 |
od | +0.025 |
Sus | +0.024 |
Jo | +0.023 |
Neg logit contributions | |
dollars | -0.043 |
End | -0.042 |
oster | -0.042 |
over | -0.041 |
injuries | -0.040 |
Token | had |
Token ID | 550 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
over | +0.003 |
dollars | +0.003 |
oster | +0.003 |
wounds | +0.003 |
End | +0.003 |
Neg logit contributions | |
Jan | -0.002 |
Jos | -0.002 |
Sus | -0.002 |
Suz | -0.002 |
contain | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
Jan | +0.002 |
Sus | +0.002 |
Jos | +0.002 |
J | +0.002 |
Suz | +0.002 |
Neg logit contributions | |
over | -0.004 |
oster | -0.004 |
dollars | -0.004 |
End | -0.004 |
wounds | -0.004 |
Token | stop |
Token ID | 2245 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
dollars | +0.027 |
etchup | +0.026 |
over | +0.026 |
oster | +0.025 |
eros | +0.025 |
Neg logit contributions | |
Jan | -0.012 |
contain | -0.011 |
spin | -0.011 |
Sus | -0.011 |
Suz | -0.011 |
Token | him |
Token ID | 683 |
Feature activation | +9.07e-02 |
Pos logit contributions | |
Jan | +0.024 |
Jos | +0.023 |
Sus | +0.022 |
J | +0.022 |
Jo | +0.021 |
Neg logit contributions | |
oster | -0.038 |
dollars | -0.036 |
over | -0.036 |
vet | -0.035 |
aid | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
Jan | +0.002 |
Jos | +0.002 |
Sus | +0.002 |
Suz | +0.002 |
stair | +0.002 |
Neg logit contributions | |
dollars | -0.002 |
over | -0.002 |
wounds | -0.002 |
oster | -0.002 |
vet | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
Jan | +0.020 |
Jos | +0.019 |
Sus | +0.019 |
Jo | +0.018 |
Suz | +0.018 |
Neg logit contributions | |
dollars | -0.021 |
oster | -0.021 |
wounds | -0.020 |
over | -0.020 |
End | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
dollars | +0.001 |
over | +0.001 |
oster | +0.001 |
promises | +0.001 |
cents | +0.001 |
Neg logit contributions | |
Jan | -0.001 |
Jos | -0.001 |
Jo | -0.001 |
Suz | -0.001 |
Sus | -0.001 |
Token | They |
Token ID | 2990 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
thirst | +0.003 |
promises | +0.003 |
dollars | +0.003 |
over | +0.003 |
pig | +0.003 |
Neg logit contributions | |
Jan | -0.003 |
stair | -0.003 |
icated | -0.002 |
Jos | -0.002 |
Jo | -0.002 |
Token | jumped |
Token ID | 11687 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
Jan | +0.003 |
Jos | +0.003 |
Sus | +0.003 |
Suz | +0.003 |
Jo | +0.003 |
Neg logit contributions | |
over | -0.004 |
dollars | -0.004 |
oster | -0.004 |
wounds | -0.004 |
End | -0.004 |
Token | on |
Token ID | 319 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
Jan | +0.020 |
Jos | +0.019 |
od | +0.018 |
Sus | +0.018 |
Suz | +0.018 |
Neg logit contributions | |
over | -0.023 |
wounds | -0.023 |
dollars | -0.023 |
vet | -0.022 |
oster | -0.022 |
Token | Max |
Token ID | 5436 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
Jan | +0.010 |
stair | +0.009 |
Sus | +0.009 |
Jos | +0.009 |
Jo | +0.009 |
Neg logit contributions | |
oster | -0.018 |
dollars | -0.018 |
over | -0.017 |
ages | -0.017 |
aid | -0.016 |
Token | until |
Token ID | 1566 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
Jan | +0.026 |
Jos | +0.024 |
Sus | +0.024 |
Suz | +0.023 |
Jo | +0.023 |
Neg logit contributions | |
over | -0.032 |
oster | -0.032 |
dollars | -0.032 |
wounds | -0.032 |
vet | -0.031 |
Token | they |
Token ID | 484 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Jan | +0.012 |
Sus | +0.012 |
Jos | +0.012 |
Suz | +0.011 |
Jo | +0.011 |
Neg logit contributions | |
dollars | -0.017 |
wounds | -0.017 |
oster | -0.017 |
over | -0.017 |
promises | -0.016 |
Token | finally |
Token ID | 3443 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
Jan | +0.032 |
Jos | +0.031 |
Sus | +0.030 |
stair | +0.030 |
Suz | +0.029 |
Neg logit contributions | |
over | -0.035 |
dollars | -0.035 |
oster | -0.035 |
wounds | -0.035 |
vet | -0.034 |
Token | got |
Token ID | 1392 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
Jan | +0.016 |
Jos | +0.016 |
stair | +0.015 |
Sus | +0.015 |
ous | +0.015 |
Neg logit contributions | |
dollars | -0.013 |
over | -0.013 |
oster | -0.013 |
wounds | -0.013 |
vet | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Jan | +0.049 |
Sus | +0.048 |
Jos | +0.046 |
Suz | +0.045 |
J | +0.044 |
Neg logit contributions | |
over | -0.080 |
oster | -0.079 |
dollars | -0.077 |
wounds | -0.075 |
End | -0.074 |
Token | t |
Token ID | 256 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
Jan | +0.030 |
Jos | +0.029 |
Sus | +0.028 |
Suz | +0.028 |
od | +0.027 |
Neg logit contributions | |
dollars | -0.036 |
over | -0.035 |
wounds | -0.035 |
oster | -0.035 |
vet | -0.034 |
Token | eddy |
Token ID | 21874 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Jan | +0.024 |
Jos | +0.023 |
Sus | +0.023 |
ous | +0.023 |
Suz | +0.023 |
Neg logit contributions | |
dollars | -0.016 |
wounds | -0.015 |
over | -0.015 |
oster | -0.015 |
vet | -0.015 |
Token | bear |
Token ID | 6842 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
over | +0.051 |
cents | +0.051 |
dollars | +0.051 |
wounds | +0.050 |
oster | +0.049 |
Neg logit contributions | |
Jan | -0.040 |
tw | -0.040 |
Sus | -0.039 |
ous | -0.039 |
Jo | -0.038 |
Token | home |
Token ID | 1363 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
End | +0.018 |
oster | +0.018 |
wounds | +0.018 |
over | +0.017 |
dollars | +0.017 |
Neg logit contributions | |
Jan | -0.013 |
Sus | -0.012 |
Jos | -0.012 |
Suz | -0.012 |
ous | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
oster | +0.028 |
dollars | +0.028 |
over | +0.028 |
wounds | +0.028 |
vet | +0.027 |
Neg logit contributions | |
Jan | -0.031 |
Jos | -0.030 |
Sus | -0.030 |
Suz | -0.029 |
Jo | -0.029 |
Token | Tim |
Token ID | 5045 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
Jan | +0.019 |
Sus | +0.019 |
Jos | +0.019 |
Jo | +0.018 |
J | +0.018 |
Neg logit contributions | |
dollars | -0.022 |
wounds | -0.022 |
oster | -0.021 |
over | -0.021 |
injuries | -0.021 |
Token | didn |
Token ID | 1422 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
over | +0.053 |
wounds | +0.051 |
dollars | +0.050 |
injuries | +0.049 |
oster | +0.048 |
Neg logit contributions | |
Jan | -0.041 |
Jos | -0.037 |
Sus | -0.037 |
J | -0.036 |
Suz | -0.035 |
Token | 't |
Token ID | 470 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Jan | +0.016 |
Jos | +0.016 |
Sus | +0.015 |
Suz | +0.015 |
stair | +0.015 |
Neg logit contributions | |
vet | -0.019 |
oster | -0.019 |
over | -0.019 |
wounds | -0.019 |
dollars | -0.019 |
Token | want |
Token ID | 765 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Jan | +0.049 |
Jos | +0.047 |
Sus | +0.045 |
Suz | +0.044 |
stair | +0.044 |
Neg logit contributions | |
dollars | -0.060 |
over | -0.060 |
wounds | -0.059 |
oster | -0.059 |
vet | -0.057 |
Token | anyone |
Token ID | 2687 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
dollars | +0.032 |
vet | +0.032 |
wounds | +0.032 |
over | +0.031 |
oster | +0.031 |
Neg logit contributions | |
Jan | -0.022 |
Jos | -0.022 |
stair | -0.021 |
Suz | -0.021 |
Sus | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
Jan | +0.035 |
Jos | +0.033 |
Sus | +0.031 |
Suz | +0.031 |
stair | +0.031 |
Neg logit contributions | |
dollars | -0.058 |
over | -0.057 |
wounds | -0.057 |
oster | -0.056 |
vet | -0.056 |
Token | cross |
Token ID | 3272 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
dollars | +0.001 |
over | +0.001 |
oster | +0.001 |
wounds | +0.001 |
End | +0.001 |
Neg logit contributions | |
Jan | -0.001 |
Sus | -0.001 |
Jos | -0.001 |
Suz | -0.001 |
contain | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
oster | +0.003 |
dollars | +0.003 |
over | +0.003 |
wounds | +0.003 |
vet | +0.003 |
Neg logit contributions | |
Jan | -0.002 |
Sus | -0.002 |
Jos | -0.002 |
J | -0.002 |
Suz | -0.002 |
Token | wall |
Token ID | 3355 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Jan | +0.062 |
Jos | +0.059 |
Sus | +0.058 |
Suz | +0.057 |
Jo | +0.055 |
Neg logit contributions | |
over | -0.075 |
dollars | -0.074 |
wounds | -0.074 |
oster | -0.073 |
vet | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
Jan | +0.040 |
Jos | +0.039 |
Sus | +0.038 |
stair | +0.037 |
Suz | +0.037 |
Neg logit contributions | |
over | -0.032 |
dollars | -0.032 |
wounds | -0.032 |
oster | -0.032 |
vet | -0.031 |
Token | He |
Token ID | 679 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
Jan | +0.020 |
Jos | +0.019 |
Sus | +0.019 |
J | +0.018 |
Jo | +0.018 |
Neg logit contributions | |
dollars | -0.024 |
wounds | -0.024 |
over | -0.024 |
oster | -0.023 |
injuries | -0.023 |
Token | didn |
Token ID | 1422 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Jan | +0.013 |
Jos | +0.012 |
Sus | +0.012 |
Suz | +0.012 |
Jo | +0.012 |
Neg logit contributions | |
over | -0.016 |
dollars | -0.016 |
wounds | -0.015 |
oster | -0.015 |
etchup | -0.015 |
Token | that |
Token ID | 326 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
Jan | +0.001 |
Jos | +0.001 |
Sus | +0.001 |
Suz | +0.001 |
stair | +0.001 |
Neg logit contributions | |
dollars | -0.001 |
over | -0.001 |
oster | -0.001 |
wounds | -0.001 |
vet | -0.001 |
Token | he |
Token ID | 339 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
Jan | +0.003 |
Jos | +0.003 |
stair | +0.003 |
od | +0.003 |
ous | +0.003 |
Neg logit contributions | |
over | -0.002 |
dollars | -0.002 |
vet | -0.002 |
wounds | -0.002 |
End | -0.002 |
Token | gave |
Token ID | 2921 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
over | +0.007 |
dollars | +0.007 |
wounds | +0.006 |
oster | +0.006 |
vet | +0.006 |
Neg logit contributions | |
Jan | -0.006 |
Jos | -0.006 |
Sus | -0.006 |
Suz | -0.006 |
stair | -0.006 |
Token | Benny |
Token ID | 44275 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
dollars | +0.038 |
over | +0.037 |
oster | +0.037 |
wounds | +0.036 |
vet | +0.035 |
Neg logit contributions | |
Jan | -0.014 |
Sus | -0.012 |
Suz | -0.012 |
Jos | -0.012 |
J | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Jan | +0.023 |
Jos | +0.022 |
Sus | +0.021 |
Suz | +0.021 |
J | +0.020 |
Neg logit contributions | |
dollars | -0.030 |
over | -0.030 |
oster | -0.030 |
wounds | -0.030 |
vet | -0.029 |
Token | big |
Token ID | 1263 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Jan | +0.036 |
Jos | +0.036 |
od | +0.035 |
Sus | +0.034 |
Jo | +0.033 |
Neg logit contributions | |
vet | -0.032 |
oster | -0.032 |
dollars | -0.032 |
pig | -0.031 |
wounds | -0.031 |
Token | hug |
Token ID | 16225 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Jan | +0.029 |
Jos | +0.028 |
Sus | +0.027 |
od | +0.027 |
stair | +0.027 |
Neg logit contributions | |
dollars | -0.027 |
over | -0.027 |
wounds | -0.026 |
oster | -0.026 |
vet | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
wounds | +0.034 |
oster | +0.033 |
dollars | +0.033 |
over | +0.032 |
End | +0.032 |
Neg logit contributions | |
Jan | -0.030 |
Sus | -0.029 |
Jos | -0.029 |
ous | -0.028 |
Jo | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
Jan | +0.021 |
Jos | +0.020 |
Sus | +0.020 |
Suz | +0.020 |
J | +0.019 |
Neg logit contributions | |
dollars | -0.022 |
wounds | -0.022 |
over | -0.021 |
oster | -0.021 |
injuries | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
Jan | +0.020 |
Jos | +0.019 |
Sus | +0.019 |
Suz | +0.019 |
Jo | +0.018 |
Neg logit contributions | |
dollars | -0.017 |
wounds | -0.016 |
over | -0.016 |
promises | -0.015 |
oster | -0.015 |
Token | " |
Token ID | 1 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Jan | +0.015 |
Jos | +0.014 |
Suz | +0.014 |
Sus | +0.014 |
J | +0.014 |
Neg logit contributions | |
dollars | -0.014 |
wounds | -0.013 |
over | -0.013 |
promises | -0.013 |
injuries | -0.012 |
Token | abel |
Token ID | 9608 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
Jan | +0.017 |
Jos | +0.016 |
Sus | +0.015 |
od | +0.015 |
Jo | +0.015 |
Neg logit contributions | |
dollars | -0.027 |
wounds | -0.026 |
over | -0.026 |
oster | -0.026 |
vet | -0.026 |
Token | still |
Token ID | 991 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
od | +0.008 |
Jan | +0.008 |
Jos | +0.008 |
Sus | +0.008 |
tw | +0.008 |
Neg logit contributions | |
wounds | -0.013 |
dollars | -0.012 |
vet | -0.012 |
over | -0.012 |
handcuffs | -0.012 |
Token | loves |
Token ID | 10408 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
dollars | +0.022 |
over | +0.022 |
wounds | +0.021 |
oster | +0.021 |
vet | +0.021 |
Neg logit contributions | |
Jan | -0.021 |
Jos | -0.020 |
Sus | -0.019 |
Suz | -0.019 |
stair | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
oster | +0.011 |
over | +0.011 |
dollars | +0.011 |
wounds | +0.011 |
vet | +0.011 |
Neg logit contributions | |
Jan | -0.007 |
Jos | -0.007 |
Sus | -0.007 |
Suz | -0.006 |
od | -0.006 |
Token | fine |
Token ID | 3734 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
oster | +0.049 |
over | +0.048 |
dollars | +0.047 |
wounds | +0.046 |
vet | +0.045 |
Neg logit contributions | |
Jan | -0.038 |
Jos | -0.035 |
Sus | -0.035 |
stair | -0.035 |
od | -0.034 |
Token | mustache |
Token ID | 49303 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
oster | +0.025 |
wounds | +0.024 |
dollars | +0.024 |
vet | +0.023 |
over | +0.023 |
Neg logit contributions | |
Jan | -0.021 |
Sus | -0.020 |
Jos | -0.020 |
od | -0.019 |
stair | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
dollars | +0.047 |
wounds | +0.047 |
oster | +0.046 |
over | +0.046 |
vet | +0.045 |
Neg logit contributions | |
Jan | -0.044 |
Jos | -0.042 |
Sus | -0.041 |
stair | -0.040 |
od | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
Jan | +0.043 |
Jos | +0.041 |
Sus | +0.039 |
Suz | +0.038 |
stair | +0.038 |
Neg logit contributions | |
over | -0.069 |
dollars | -0.069 |
wounds | -0.068 |
oster | -0.068 |
vet | -0.066 |
Token | she |
Token ID | 673 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
over | +0.013 |
dollars | +0.013 |
oster | +0.013 |
wounds | +0.013 |
vet | +0.012 |
Neg logit contributions | |
Jan | -0.010 |
Jos | -0.010 |
Sus | -0.009 |
Suz | -0.009 |
stair | -0.009 |
Token | wears |
Token ID | 17326 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
Jan | +0.002 |
Jos | +0.002 |
Sus | +0.002 |
od | +0.002 |
Suz | +0.002 |
Neg logit contributions | |
over | -0.003 |
dollars | -0.003 |
wounds | -0.003 |
oster | -0.003 |
vet | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
dollars | +0.009 |
over | +0.009 |
oster | +0.009 |
wounds | +0.009 |
vet | +0.009 |
Neg logit contributions | |
Jan | -0.009 |
Jos | -0.009 |
Sus | -0.009 |
od | -0.008 |
Suz | -0.008 |
Token | he |
Token ID | 339 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
Jan | +0.008 |
Sus | +0.008 |
Jos | +0.007 |
Jo | +0.007 |
J | +0.007 |
Neg logit contributions | |
dollars | -0.013 |
oster | -0.013 |
wounds | -0.013 |
over | -0.013 |
cents | -0.012 |
Token | went |
Token ID | 1816 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
Jan | +0.012 |
Jos | +0.011 |
J | +0.011 |
sorts | +0.010 |
od | +0.010 |
Neg logit contributions | |
wounds | -0.019 |
dollars | -0.019 |
over | -0.018 |
oster | -0.018 |
ages | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
Jan | +0.040 |
Sus | +0.037 |
Jos | +0.036 |
stair | +0.036 |
Suz | +0.035 |
Neg logit contributions | |
oster | -0.043 |
dollars | -0.043 |
wounds | -0.042 |
over | -0.040 |
End | -0.040 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
Jan | +0.020 |
Jos | +0.019 |
Sus | +0.018 |
Suz | +0.018 |
J | +0.018 |
Neg logit contributions | |
dollars | -0.016 |
wounds | -0.016 |
oster | -0.016 |
over | -0.015 |
vet | -0.015 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
dollars | +0.074 |
wounds | +0.074 |
oster | +0.069 |
vet | +0.067 |
over | +0.067 |
Neg logit contributions | |
Jan | -0.074 |
Sus | -0.071 |
Jos | -0.070 |
Jo | -0.070 |
Suz | -0.068 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
Jan | +0.025 |
Jos | +0.024 |
od | +0.023 |
stair | +0.023 |
icated | +0.022 |
Neg logit contributions | |
over | -0.036 |
dollars | -0.035 |
End | -0.035 |
promises | -0.034 |
wounds | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
dollars | +0.052 |
oster | +0.050 |
wounds | +0.050 |
over | +0.050 |
vet | +0.048 |
Neg logit contributions | |
Jan | -0.035 |
Jos | -0.034 |
Sus | -0.033 |
od | -0.032 |
Suz | -0.032 |
Token | time |
Token ID | 640 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
Jan | +0.005 |
Jos | +0.005 |
Sus | +0.004 |
stair | +0.004 |
Suz | +0.004 |
Neg logit contributions | |
dollars | -0.004 |
wounds | -0.004 |
oster | -0.004 |
over | -0.004 |
vet | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
over | +0.006 |
End | +0.005 |
dollars | +0.005 |
pig | +0.005 |
promises | +0.005 |
Neg logit contributions | |
contain | -0.009 |
sorts | -0.009 |
icated | -0.009 |
Jos | -0.009 |
Jan | -0.009 |
Token | there |
Token ID | 612 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Jan | +0.053 |
Jos | +0.050 |
Sus | +0.050 |
Suz | +0.049 |
stair | +0.048 |
Neg logit contributions | |
dollars | -0.047 |
wounds | -0.046 |
over | -0.046 |
oster | -0.045 |
vet | -0.044 |
Token | was |
Token ID | 373 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
over | +0.002 |
End | +0.002 |
vet | +0.002 |
oster | +0.002 |
pig | +0.002 |
Neg logit contributions | |
Jan | -0.003 |
Jos | -0.003 |
contain | -0.003 |
ous | -0.003 |
icated | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
oster | +0.002 |
over | +0.002 |
dollars | +0.002 |
wounds | +0.002 |
vet | +0.002 |
Neg logit contributions | |
Jan | -0.001 |
Sus | -0.001 |
Jos | -0.001 |
Suz | -0.001 |
Jo | -0.001 |
Token | belonged |
Token ID | 19611 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Jan | +0.017 |
Jos | +0.016 |
Sus | +0.015 |
Suz | +0.015 |
Jo | +0.015 |
Neg logit contributions | |
over | -0.024 |
dollars | -0.023 |
wounds | -0.023 |
oster | -0.023 |
vet | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Jan | +0.025 |
Jos | +0.024 |
Sus | +0.023 |
stair | +0.023 |
Suz | +0.023 |
Neg logit contributions | |
over | -0.028 |
dollars | -0.028 |
wounds | -0.027 |
oster | -0.027 |
vet | -0.027 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
Jan | +0.028 |
Sus | +0.028 |
Jos | +0.026 |
Suz | +0.026 |
Jo | +0.026 |
Neg logit contributions | |
wounds | -0.031 |
dollars | -0.031 |
oster | -0.029 |
injuries | -0.028 |
over | -0.027 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
wounds | +0.079 |
dollars | +0.078 |
oster | +0.073 |
injuries | +0.071 |
promises | +0.071 |
Neg logit contributions | |
Jan | -0.075 |
Sus | -0.071 |
Jo | -0.070 |
Jos | -0.070 |
Suz | -0.068 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
Jan | +0.027 |
Jos | +0.026 |
od | +0.024 |
icated | +0.024 |
stair | +0.024 |
Neg logit contributions | |
over | -0.040 |
dollars | -0.040 |
End | -0.039 |
oster | -0.039 |
wounds | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
dollars | +0.061 |
oster | +0.059 |
wounds | +0.058 |
over | +0.058 |
vet | +0.056 |
Neg logit contributions | |
Jan | -0.040 |
Jos | -0.038 |
Sus | -0.037 |
Suz | -0.036 |
Jo | -0.036 |
Token | time |
Token ID | 640 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
Jan | +0.000 |
Jos | +0.000 |
Sus | +0.000 |
stair | +0.000 |
Suz | +0.000 |
Neg logit contributions | |
wounds | -0.000 |
dollars | -0.000 |
oster | -0.000 |
over | -0.000 |
vet | -0.000 |
Token | there |
Token ID | 612 |
Feature activation | -9.17e-02 |
Pos logit contributions | |
over | +0.012 |
End | +0.011 |
dollars | +0.011 |
pig | +0.010 |
oster | +0.010 |
Neg logit contributions | |
contain | -0.017 |
Jos | -0.016 |
sorts | -0.016 |
icated | -0.016 |
Jan | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
over | +0.002 |
dollars | +0.002 |
oster | +0.002 |
wounds | +0.002 |
vet | +0.002 |
Neg logit contributions | |
Jan | -0.002 |
Jos | -0.002 |
Sus | -0.002 |
stair | -0.002 |
od | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
dollars | +0.017 |
over | +0.017 |
wounds | +0.017 |
oster | +0.017 |
vet | +0.017 |
Neg logit contributions | |
Jan | -0.016 |
Jos | -0.015 |
Sus | -0.015 |
Suz | -0.015 |
stair | -0.015 |
Token | Her |
Token ID | 9360 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
dollars | +0.001 |
wounds | +0.001 |
pig | +0.001 |
promises | +0.001 |
eros | +0.001 |
Neg logit contributions | |
Jan | -0.001 |
stair | -0.001 |
Jos | -0.001 |
Jo | -0.001 |
Suz | -0.001 |
Token | mom |
Token ID | 1995 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
over | +0.057 |
oster | +0.055 |
dollars | +0.052 |
being | +0.051 |
etchup | +0.050 |
Neg logit contributions | |
Jan | -0.062 |
Jos | -0.061 |
stair | -0.060 |
Jo | -0.058 |
Sus | -0.057 |
Token | smiles |
Token ID | 21845 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
Jan | +0.015 |
Jos | +0.015 |
Jo | +0.014 |
stair | +0.014 |
Sus | +0.014 |
Neg logit contributions | |
over | -0.019 |
oster | -0.018 |
dollars | -0.018 |
ages | -0.017 |
wounds | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
oster | +0.014 |
wounds | +0.013 |
dollars | +0.013 |
over | +0.013 |
vet | +0.013 |
Neg logit contributions | |
Jan | -0.010 |
Jos | -0.010 |
ous | -0.010 |
od | -0.010 |
Sus | -0.010 |
Token | She |
Token ID | 1375 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
Jan | +0.005 |
Jos | +0.004 |
Sus | +0.004 |
Suz | +0.004 |
Jo | +0.004 |
Neg logit contributions | |
dollars | -0.007 |
oster | -0.007 |
over | -0.007 |
wounds | -0.007 |
promises | -0.007 |
Token | hugs |
Token ID | 40657 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
over | +0.065 |
oster | +0.061 |
dollars | +0.060 |
injuries | +0.058 |
wounds | +0.058 |
Neg logit contributions | |
Jan | -0.060 |
Jos | -0.057 |
od | -0.055 |
sorts | -0.055 |
Jo | -0.055 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
dollars | +0.049 |
over | +0.048 |
oster | +0.048 |
wounds | +0.047 |
ages | +0.046 |
Neg logit contributions | |
Jan | -0.027 |
Jos | -0.025 |
Sus | -0.024 |
Suz | -0.023 |
Jo | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
over | +0.004 |
tw | +0.003 |
all | +0.003 |
Jan | +0.003 |
out | +0.003 |
Neg logit contributions | |
oster | -0.009 |
over | -0.008 |
injuries | -0.008 |
cents | -0.008 |
vet | -0.008 |
Token | She |
Token ID | 1375 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
Jan | +0.005 |
Jos | +0.005 |
Sus | +0.005 |
Suz | +0.005 |
Jo | +0.005 |
Neg logit contributions | |
dollars | -0.007 |
oster | -0.007 |
over | -0.007 |
wounds | -0.007 |
vet | -0.007 |
Token | signs |
Token ID | 5895 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
over | +0.061 |
oster | +0.058 |
dollars | +0.057 |
wounds | +0.055 |
injuries | +0.054 |
Neg logit contributions | |
Jan | -0.062 |
Jos | -0.059 |
Sus | -0.057 |
od | -0.057 |
Jo | -0.056 |
Token | to |
Token ID | 284 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Jan | +0.013 |
Jos | +0.012 |
ous | +0.012 |
Jo | +0.011 |
Sus | +0.011 |
Neg logit contributions | |
over | -0.020 |
oster | -0.020 |
dollars | -0.019 |
wounds | -0.019 |
ages | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
dollars | +0.063 |
oster | +0.061 |
wounds | +0.060 |
over | +0.060 |
vet | +0.058 |
Neg logit contributions | |
Jan | -0.044 |
Jos | -0.042 |
Sus | -0.041 |
od | -0.040 |
icated | -0.040 |
Token | time |
Token ID | 640 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
dollars | +0.001 |
wounds | +0.001 |
over | +0.001 |
oster | +0.001 |
vet | +0.001 |
Neg logit contributions | |
Jan | -0.001 |
Jos | -0.001 |
Sus | -0.001 |
stair | -0.001 |
Suz | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
End | +0.007 |
over | +0.007 |
promises | +0.006 |
dollars | +0.006 |
pig | +0.006 |
Neg logit contributions | |
contain | -0.011 |
sorts | -0.011 |
icated | -0.011 |
Jos | -0.011 |
Jan | -0.011 |
Token | there |
Token ID | 612 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Jan | +0.041 |
Jos | +0.039 |
Sus | +0.038 |
Suz | +0.038 |
stair | +0.037 |
Neg logit contributions | |
dollars | -0.039 |
wounds | -0.039 |
over | -0.038 |
oster | -0.038 |
vet | -0.037 |
Token | was |
Token ID | 373 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
over | +0.003 |
oster | +0.003 |
dollars | +0.003 |
End | +0.003 |
vet | +0.003 |
Neg logit contributions | |
Jan | -0.003 |
Jos | -0.003 |
ous | -0.003 |
Sus | -0.003 |
stair | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
over | +0.015 |
dollars | +0.015 |
wounds | +0.015 |
oster | +0.015 |
vet | +0.015 |
Neg logit contributions | |
Jan | -0.016 |
Jos | -0.015 |
Sus | -0.014 |
stair | -0.014 |
Suz | -0.014 |
Token | little |
Token ID | 1310 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
wounds | +0.030 |
dollars | +0.030 |
over | +0.029 |
ages | +0.028 |
promises | +0.028 |
Neg logit contributions | |
Jan | -0.029 |
Jos | -0.029 |
stair | -0.029 |
Sus | -0.028 |
J | -0.027 |
Token | bird |
Token ID | 6512 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
wounds | +0.065 |
dollars | +0.062 |
over | +0.061 |
oster | +0.060 |
injuries | +0.059 |
Neg logit contributions | |
Jan | -0.097 |
Jos | -0.094 |
Sus | -0.094 |
stair | -0.093 |
Suz | -0.092 |
Token | named |
Token ID | 3706 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
dollars | +0.006 |
wounds | +0.006 |
over | +0.006 |
oster | +0.006 |
vet | +0.006 |
Neg logit contributions | |
Jan | -0.009 |
Jos | -0.008 |
Suz | -0.008 |
od | -0.008 |
Sus | -0.008 |
Token | Tweet |
Token ID | 18752 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
over | +0.049 |
dollars | +0.049 |
wounds | +0.048 |
oster | +0.048 |
vet | +0.047 |
Neg logit contributions | |
Jan | -0.041 |
Jos | -0.039 |
Sus | -0.037 |
Suz | -0.037 |
stair | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
dollars | +0.004 |
over | +0.004 |
wounds | +0.004 |
oster | +0.004 |
vet | +0.004 |
Neg logit contributions | |
Jan | -0.003 |
Jos | -0.002 |
od | -0.002 |
Suz | -0.002 |
icated | -0.002 |
Token | man |
Token ID | 805 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
dollars | +0.052 |
wounds | +0.051 |
over | +0.050 |
oster | +0.050 |
vet | +0.049 |
Neg logit contributions | |
Jan | -0.057 |
Jos | -0.055 |
stair | -0.054 |
Sus | -0.053 |
ous | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
od | +0.002 |
Jan | +0.002 |
Sus | +0.002 |
Jos | +0.002 |
J | +0.002 |
Neg logit contributions | |
wounds | -0.005 |
oster | -0.005 |
End | -0.004 |
aid | -0.004 |
injuries | -0.004 |
Token | They |
Token ID | 1119 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
Jan | +0.008 |
Jos | +0.007 |
Sus | +0.007 |
Suz | +0.007 |
Jo | +0.007 |
Neg logit contributions | |
dollars | -0.009 |
oster | -0.009 |
wounds | -0.009 |
over | -0.009 |
End | -0.009 |
Token | both |
Token ID | 1111 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Jan | +0.015 |
Jos | +0.014 |
Sus | +0.013 |
Suz | +0.013 |
J | +0.013 |
Neg logit contributions | |
over | -0.018 |
dollars | -0.017 |
wounds | -0.017 |
oster | -0.017 |
vet | -0.017 |
Token | laughed |
Token ID | 13818 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
Jan | +0.005 |
Jos | +0.005 |
Sus | +0.004 |
Suz | +0.004 |
od | +0.004 |
Neg logit contributions | |
over | -0.005 |
wounds | -0.005 |
dollars | -0.005 |
vet | -0.005 |
oster | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
Jan | +0.015 |
Jos | +0.014 |
Sus | +0.014 |
Suz | +0.013 |
stair | +0.013 |
Neg logit contributions | |
over | -0.012 |
dollars | -0.012 |
wounds | -0.012 |
oster | -0.012 |
vet | -0.012 |
Token | c |
Token ID | 269 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
dollars | +0.101 |
over | +0.100 |
oster | +0.100 |
wounds | +0.098 |
vet | +0.097 |
Neg logit contributions | |
Jan | -0.074 |
Jos | -0.070 |
Sus | -0.070 |
Suz | -0.068 |
J | -0.067 |
Token | uddled |
Token ID | 32745 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
vet | +0.076 |
End | +0.075 |
dollars | +0.070 |
handcuffs | +0.070 |
wounds | +0.069 |
Neg logit contributions | |
cast | -0.052 |
ous | -0.047 |
od | -0.043 |
Sus | -0.041 |
Jan | -0.039 |
Token | on |
Token ID | 319 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
dollars | +0.034 |
oster | +0.034 |
vet | +0.033 |
over | +0.032 |
End | +0.032 |
Neg logit contributions | |
Jan | -0.024 |
Sus | -0.023 |
Jos | -0.022 |
Suz | -0.022 |
Jo | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Jan | +0.015 |
Sus | +0.014 |
Jo | +0.014 |
stair | +0.014 |
Jos | +0.014 |
Neg logit contributions | |
oster | -0.027 |
dollars | -0.026 |
over | -0.026 |
End | -0.025 |
aid | -0.025 |
Token | couch |
Token ID | 18507 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Jan | +0.033 |
stair | +0.032 |
Jos | +0.032 |
Sus | +0.031 |
Suz | +0.030 |
Neg logit contributions | |
over | -0.046 |
dollars | -0.046 |
oster | -0.044 |
wounds | -0.044 |
vet | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Jan | +0.049 |
Jos | +0.047 |
Sus | +0.046 |
Suz | +0.044 |
J | +0.043 |
Neg logit contributions | |
over | -0.058 |
dollars | -0.057 |
oster | -0.057 |
wounds | -0.055 |
vet | -0.053 |
Token | big |
Token ID | 1263 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Jan | +0.023 |
Jos | +0.022 |
stair | +0.022 |
Sus | +0.021 |
Suz | +0.021 |
Neg logit contributions | |
dollars | -0.025 |
over | -0.025 |
wounds | -0.024 |
oster | -0.024 |
vet | -0.023 |
Token | fish |
Token ID | 5916 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
Jan | +0.041 |
Jos | +0.039 |
Sus | +0.038 |
od | +0.038 |
Suz | +0.038 |
Neg logit contributions | |
dollars | -0.029 |
over | -0.029 |
wounds | -0.029 |
oster | -0.028 |
vet | -0.028 |
Token | again |
Token ID | 757 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
Jan | +0.021 |
Jos | +0.020 |
Sus | +0.020 |
Suz | +0.019 |
stair | +0.019 |
Neg logit contributions | |
over | -0.019 |
dollars | -0.019 |
wounds | -0.019 |
oster | -0.019 |
vet | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
oster | +0.009 |
dollars | +0.009 |
wounds | +0.009 |
over | +0.009 |
vet | +0.009 |
Neg logit contributions | |
Jan | -0.010 |
Jos | -0.009 |
Sus | -0.009 |
J | -0.009 |
Suz | -0.009 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
Jan | +0.016 |
Jos | +0.015 |
Sus | +0.015 |
Suz | +0.015 |
stair | +0.015 |
Neg logit contributions | |
over | -0.010 |
dollars | -0.010 |
wounds | -0.010 |
oster | -0.010 |
vet | -0.010 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
dollars | +0.083 |
wounds | +0.081 |
over | +0.081 |
oster | +0.080 |
vet | +0.077 |
Neg logit contributions | |
Jan | -0.113 |
Jos | -0.108 |
Sus | -0.106 |
Suz | -0.105 |
stair | -0.104 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
Jan | +0.018 |
Jos | +0.018 |
od | +0.017 |
Sus | +0.017 |
stair | +0.017 |
Neg logit contributions | |
dollars | -0.025 |
over | -0.025 |
End | -0.025 |
promises | -0.025 |
wounds | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
dollars | +0.061 |
oster | +0.059 |
wounds | +0.059 |
over | +0.059 |
vet | +0.057 |
Neg logit contributions | |
Jan | -0.045 |
Jos | -0.043 |
Sus | -0.042 |
Suz | -0.041 |
stair | -0.041 |
Token | time |
Token ID | 640 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
Jan | +0.002 |
Jos | +0.002 |
Sus | +0.002 |
Suz | +0.002 |
stair | +0.002 |
Neg logit contributions | |
dollars | -0.001 |
over | -0.001 |
wounds | -0.001 |
oster | -0.001 |
vet | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
over | +0.010 |
End | +0.010 |
dollars | +0.009 |
promises | +0.009 |
pig | +0.009 |
Neg logit contributions | |
Jos | -0.016 |
contain | -0.016 |
Jan | -0.016 |
sorts | -0.016 |
icated | -0.016 |
Token | said |
Token ID | 531 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Jan | +0.021 |
Jos | +0.020 |
Sus | +0.019 |
Suz | +0.019 |
Jo | +0.018 |
Neg logit contributions | |
over | -0.025 |
wounds | -0.025 |
oster | -0.025 |
dollars | -0.025 |
End | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
oster | +0.037 |
dollars | +0.037 |
wounds | +0.037 |
over | +0.037 |
vet | +0.036 |
Neg logit contributions | |
Jan | -0.022 |
Jos | -0.021 |
Sus | -0.021 |
Suz | -0.020 |
Jo | -0.019 |
Token | as |
Token ID | 355 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Jan | +0.023 |
Jos | +0.022 |
Sus | +0.021 |
Suz | +0.020 |
stair | +0.020 |
Neg logit contributions | |
dollars | -0.039 |
over | -0.038 |
oster | -0.038 |
wounds | -0.037 |
cents | -0.036 |
Token | she |
Token ID | 673 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
dollars | +0.039 |
over | +0.038 |
wounds | +0.038 |
oster | +0.038 |
vet | +0.037 |
Neg logit contributions | |
Jan | -0.029 |
Jos | -0.028 |
Sus | -0.027 |
Suz | -0.026 |
Jo | -0.026 |
Token | smiled |
Token ID | 13541 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
over | +0.044 |
dollars | +0.043 |
wounds | +0.043 |
oster | +0.042 |
End | +0.041 |
Neg logit contributions | |
Jan | -0.041 |
Jos | -0.039 |
Sus | -0.037 |
Jo | -0.037 |
Suz | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
oster | +0.007 |
dollars | +0.007 |
wounds | +0.006 |
over | +0.006 |
vet | +0.006 |
Neg logit contributions | |
Jan | -0.006 |
Jos | -0.005 |
Sus | -0.005 |
J | -0.005 |
Suz | -0.005 |
Token | took |
Token ID | 1718 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
dollars | +0.104 |
over | +0.102 |
oster | +0.101 |
wounds | +0.100 |
End | +0.096 |
Neg logit contributions | |
Jan | -0.120 |
Jos | -0.115 |
Sus | -0.114 |
Suz | -0.112 |
Jo | -0.110 |
Token | them |
Token ID | 606 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
dollars | +0.029 |
over | +0.029 |
wounds | +0.028 |
oster | +0.028 |
vet | +0.027 |
Neg logit contributions | |
Jan | -0.024 |
Jos | -0.023 |
Sus | -0.022 |
Suz | -0.021 |
Jo | -0.021 |
Token | back |
Token ID | 736 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
Jan | +0.014 |
Jos | +0.014 |
Sus | +0.013 |
Suz | +0.013 |
stair | +0.013 |
Neg logit contributions | |
over | -0.024 |
dollars | -0.023 |
oster | -0.023 |
wounds | -0.023 |
vet | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
over | +0.013 |
dollars | +0.013 |
wounds | +0.013 |
oster | +0.012 |
vet | +0.012 |
Neg logit contributions | |
Jan | -0.012 |
Jos | -0.011 |
od | -0.011 |
Sus | -0.011 |
stair | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
Jan | +0.002 |
Jos | +0.002 |
Sus | +0.002 |
Suz | +0.002 |
Jo | +0.002 |
Neg logit contributions | |
dollars | -0.003 |
oster | -0.003 |
over | -0.003 |
wounds | -0.002 |
ages | -0.002 |
Token | been |
Token ID | 587 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
Jan | +0.053 |
Jos | +0.050 |
Sus | +0.049 |
Suz | +0.048 |
od | +0.047 |
Neg logit contributions | |
over | -0.055 |
dollars | -0.054 |
oster | -0.054 |
wounds | -0.054 |
vet | -0.052 |
Token | mad |
Token ID | 8805 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Jan | +0.015 |
Jos | +0.014 |
Sus | +0.014 |
Suz | +0.013 |
stair | +0.013 |
Neg logit contributions | |
over | -0.021 |
dollars | -0.021 |
wounds | -0.020 |
oster | -0.020 |
vet | -0.020 |
Token | at |
Token ID | 379 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Jan | +0.003 |
Jos | +0.003 |
Suz | +0.003 |
stair | +0.003 |
icated | +0.003 |
Neg logit contributions | |
over | -0.003 |
dollars | -0.003 |
vet | -0.003 |
wounds | -0.003 |
promises | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
over | +0.004 |
oster | +0.004 |
dollars | +0.004 |
wounds | +0.004 |
ages | +0.004 |
Neg logit contributions | |
Jan | -0.002 |
Sus | -0.002 |
Jos | -0.002 |
stair | -0.002 |
Jo | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
oster | +0.018 |
over | +0.018 |
dollars | +0.017 |
wounds | +0.017 |
vet | +0.017 |
Neg logit contributions | |
Jan | -0.016 |
Jos | -0.015 |
Sus | -0.015 |
stair | -0.015 |
od | -0.015 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
Jan | +0.005 |
Sus | +0.004 |
Jo | +0.004 |
Jos | +0.004 |
J | +0.004 |
Neg logit contributions | |
oster | -0.007 |
wounds | -0.006 |
dollars | -0.006 |
over | -0.006 |
injuries | -0.006 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
wounds | +0.083 |
dollars | +0.083 |
oster | +0.078 |
injuries | +0.076 |
vet | +0.075 |
Neg logit contributions | |
Jan | -0.081 |
Sus | -0.077 |
Jo | -0.076 |
Jos | -0.076 |
stair | -0.075 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
Jan | +0.018 |
Jos | +0.017 |
od | +0.017 |
Sus | +0.016 |
stair | +0.016 |
Neg logit contributions | |
dollars | -0.028 |
over | -0.028 |
End | -0.027 |
wounds | -0.027 |
oster | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
dollars | +0.061 |
oster | +0.060 |
wounds | +0.059 |
over | +0.058 |
vet | +0.057 |
Neg logit contributions | |
Jan | -0.041 |
Jos | -0.039 |
Sus | -0.038 |
Jo | -0.037 |
stair | -0.037 |
Token | time |
Token ID | 640 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
Jan | +0.004 |
Jos | +0.004 |
Sus | +0.004 |
stair | +0.003 |
Suz | +0.003 |
Neg logit contributions | |
wounds | -0.004 |
dollars | -0.004 |
oster | -0.003 |
over | -0.003 |
vet | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
over | +0.011 |
End | +0.011 |
dollars | +0.010 |
pig | +0.010 |
promises | +0.010 |
Neg logit contributions | |
contain | -0.016 |
icated | -0.016 |
sorts | -0.016 |
Jos | -0.016 |
Jan | -0.016 |
Token | dad |
Token ID | 9955 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
dollars | +0.009 |
oster | +0.009 |
over | +0.009 |
vet | +0.008 |
wounds | +0.008 |
Neg logit contributions | |
Jan | -0.013 |
Jos | -0.013 |
stair | -0.013 |
Sus | -0.013 |
Suz | -0.012 |
Token | fix |
Token ID | 4259 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Jan | +0.060 |
Jos | +0.058 |
Sus | +0.055 |
od | +0.055 |
stair | +0.054 |
Neg logit contributions | |
oster | -0.083 |
over | -0.082 |
dollars | -0.082 |
vet | -0.081 |
wounds | -0.080 |
Token | the |
Token ID | 262 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Jan | +0.036 |
Jos | +0.034 |
Sus | +0.033 |
Suz | +0.032 |
stair | +0.032 |
Neg logit contributions | |
dollars | -0.037 |
over | -0.037 |
wounds | -0.037 |
oster | -0.036 |
vet | -0.036 |
Token | track |
Token ID | 2610 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Jan | +0.037 |
Jos | +0.035 |
stair | +0.034 |
Sus | +0.033 |
Suz | +0.032 |
Neg logit contributions | |
over | -0.063 |
dollars | -0.063 |
oster | -0.062 |
wounds | -0.062 |
vet | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
Jan | +0.005 |
Jos | +0.005 |
Sus | +0.005 |
Suz | +0.005 |
od | +0.004 |
Neg logit contributions | |
over | -0.004 |
dollars | -0.004 |
wounds | -0.004 |
oster | -0.004 |
vet | -0.004 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
Jan | +0.013 |
Jos | +0.013 |
stair | +0.012 |
Sus | +0.012 |
Suz | +0.012 |
Neg logit contributions | |
over | -0.007 |
dollars | -0.007 |
vet | -0.007 |
wounds | -0.007 |
oster | -0.007 |
Token | Once |
Token ID | 7454 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
dollars | +0.094 |
wounds | +0.091 |
oster | +0.088 |
over | +0.087 |
vet | +0.084 |
Neg logit contributions | |
Jan | -0.098 |
Jos | -0.093 |
Sus | -0.092 |
Jo | -0.090 |
Suz | -0.089 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Jan | +0.013 |
Jos | +0.012 |
Sus | +0.012 |
od | +0.011 |
stair | +0.011 |
Neg logit contributions | |
dollars | -0.019 |
over | -0.019 |
wounds | -0.019 |
End | -0.019 |
oster | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
dollars | +0.063 |
oster | +0.060 |
wounds | +0.060 |
over | +0.059 |
cents | +0.058 |
Neg logit contributions | |
Jan | -0.038 |
Jos | -0.036 |
Sus | -0.036 |
icated | -0.035 |
od | -0.035 |
Token | time |
Token ID | 640 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
Jan | +0.004 |
Jos | +0.004 |
Sus | +0.004 |
stair | +0.004 |
Suz | +0.004 |
Neg logit contributions | |
dollars | -0.003 |
wounds | -0.003 |
oster | -0.003 |
over | -0.003 |
vet | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
over | +0.008 |
End | +0.008 |
dollars | +0.008 |
promises | +0.008 |
pig | +0.008 |
Neg logit contributions | |
Jos | -0.011 |
Jan | -0.011 |
contain | -0.011 |
sorts | -0.011 |
icated | -0.011 |