Token | know |
Token ID | 760 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
yles | +0.016 |
spill | +0.016 |
yle | +0.016 |
cases | +0.016 |
hairc | +0.015 |
Neg logit contributions | |
age | -0.020 |
> | -0.018 |
amed | -0.017 |
Follow | -0.017 |
man | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -3.51e-04 |
Pos logit contributions | |
cases | +0.028 |
yles | +0.028 |
salon | +0.026 |
yle | +0.026 |
outing | +0.025 |
Neg logit contributions | |
age | -0.017 |
back | -0.016 |
right | -0.015 |
welcome | -0.015 |
est | -0.015 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
age | +0.001 |
back | +0.001 |
welcome | +0.001 |
right | +0.001 |
home | +0.001 |
Neg logit contributions | |
yles | -0.001 |
cases | -0.001 |
ls | -0.001 |
yle | -0.001 |
outing | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.91e-03 |
Pos logit contributions | |
cases | +0.021 |
yles | +0.021 |
ls | +0.021 |
yle | +0.019 |
salon | +0.019 |
Neg logit contributions | |
age | -0.024 |
amed | -0.020 |
> | -0.020 |
Follow | -0.019 |
welcome | -0.019 |
Token | Cater |
Token ID | 40742 |
Feature activation | +4.31e-03 |
Pos logit contributions | |
yles | +0.004 |
cases | +0.004 |
yle | +0.003 |
ls | +0.003 |
salon | +0.003 |
Neg logit contributions | |
age | -0.003 |
amed | -0.002 |
> | -0.002 |
home | -0.002 |
back | -0.002 |
Token | pill |
Token ID | 27215 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
yles | +0.005 |
ls | +0.005 |
cases | +0.005 |
yle | +0.005 |
salon | +0.004 |
Neg logit contributions | |
age | -0.010 |
back | -0.009 |
> | -0.009 |
home | -0.008 |
welcome | -0.008 |
Token | ars |
Token ID | 945 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
cases | +0.221 |
ls | +0.221 |
yles | +0.218 |
yle | +0.202 |
outing | +0.201 |
Neg logit contributions | |
age | -0.193 |
home | -0.170 |
gy | -0.168 |
back | -0.167 |
> | -0.167 |
Token | need |
Token ID | 761 |
Feature activation | -8.70e-04 |
Pos logit contributions | |
yles | +0.027 |
cases | +0.025 |
yle | +0.024 |
salon | +0.023 |
ries | +0.023 |
Neg logit contributions | |
age | -0.026 |
back | -0.023 |
welcome | -0.023 |
right | -0.023 |
est | -0.022 |
Token | leaves |
Token ID | 5667 |
Feature activation | +6.60e-03 |
Pos logit contributions | |
age | +0.001 |
> | +0.001 |
gy | +0.001 |
amed | +0.001 |
est | +0.001 |
Neg logit contributions | |
yles | -0.002 |
cases | -0.002 |
ls | -0.002 |
hairc | -0.001 |
yle | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -7.63e-04 |
Pos logit contributions | |
yles | +0.013 |
cases | +0.013 |
ls | +0.012 |
yle | +0.012 |
salon | +0.012 |
Neg logit contributions | |
age | -0.010 |
back | -0.008 |
> | -0.008 |
welcome | -0.008 |
home | -0.008 |
Token | air |
Token ID | 1633 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
age | +0.001 |
back | +0.001 |
welcome | +0.001 |
> | +0.001 |
home | +0.001 |
Neg logit contributions | |
yles | -0.001 |
cases | -0.001 |
yle | -0.001 |
ls | -0.001 |
salon | -0.001 |
Token | Did |
Token ID | 7731 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
age | +0.003 |
back | +0.003 |
home | +0.003 |
amed | +0.002 |
> | +0.002 |
Neg logit contributions | |
yles | -0.003 |
yle | -0.003 |
cases | -0.003 |
hairc | -0.003 |
salon | -0.003 |
Token | you |
Token ID | 345 |
Feature activation | -4.23e-03 |
Pos logit contributions | |
age | +0.013 |
back | +0.012 |
right | +0.012 |
welcome | +0.011 |
home | +0.011 |
Neg logit contributions | |
cases | -0.021 |
yles | -0.021 |
outing | -0.020 |
ls | -0.019 |
tant | -0.019 |
Token | know |
Token ID | 760 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
age | +0.007 |
back | +0.006 |
welcome | +0.005 |
> | +0.005 |
home | +0.005 |
Neg logit contributions | |
yles | -0.008 |
cases | -0.008 |
ls | -0.007 |
yle | -0.007 |
salon | -0.007 |
Token | that |
Token ID | 326 |
Feature activation | +6.17e-03 |
Pos logit contributions | |
cases | +0.021 |
yles | +0.021 |
yle | +0.019 |
ls | +0.019 |
salon | +0.019 |
Neg logit contributions | |
age | -0.019 |
back | -0.017 |
welcome | -0.017 |
home | -0.017 |
right | -0.016 |
Token | cater |
Token ID | 20825 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
yles | +0.011 |
cases | +0.010 |
ls | +0.010 |
yle | +0.010 |
salon | +0.010 |
Neg logit contributions | |
age | -0.011 |
> | -0.009 |
back | -0.009 |
welcome | -0.008 |
amed | -0.008 |
Token | pill |
Token ID | 27215 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
yles | +0.011 |
cases | +0.011 |
ls | +0.010 |
yle | +0.010 |
salon | +0.010 |
Neg logit contributions | |
age | -0.024 |
back | -0.021 |
> | -0.021 |
welcome | -0.021 |
home | -0.021 |
Token | ars |
Token ID | 945 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
cases | +0.214 |
ls | +0.211 |
yles | +0.211 |
else | +0.196 |
yle | +0.194 |
Neg logit contributions | |
age | -0.194 |
home | -0.176 |
back | -0.176 |
gy | -0.175 |
> | -0.170 |
Token | turn |
Token ID | 1210 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
yles | +0.027 |
cases | +0.026 |
yle | +0.025 |
salon | +0.025 |
hairc | +0.023 |
Neg logit contributions | |
age | -0.021 |
back | -0.019 |
welcome | -0.018 |
right | -0.017 |
home | -0.017 |
Token | into |
Token ID | 656 |
Feature activation | +1.35e-03 |
Pos logit contributions | |
yles | +0.036 |
cases | +0.036 |
ls | +0.034 |
yle | +0.033 |
salon | +0.033 |
Neg logit contributions | |
age | -0.023 |
back | -0.018 |
> | -0.018 |
welcome | -0.018 |
home | -0.017 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -8.50e-03 |
Pos logit contributions | |
yles | +0.003 |
cases | +0.003 |
ls | +0.002 |
yle | +0.002 |
salon | +0.002 |
Neg logit contributions | |
age | -0.002 |
back | -0.002 |
> | -0.002 |
welcome | -0.002 |
home | -0.001 |
Token | butterflies |
Token ID | 44571 |
Feature activation | -3.22e-03 |
Pos logit contributions | |
age | +0.015 |
back | +0.012 |
> | +0.012 |
welcome | +0.012 |
home | +0.012 |
Neg logit contributions | |
yles | -0.014 |
cases | -0.014 |
ls | -0.013 |
yle | -0.013 |
salon | -0.013 |
Token | careful |
Token ID | 8161 |
Feature activation | +3.33e-03 |
Pos logit contributions | |
eling | +0.044 |
outing | +0.041 |
else | +0.037 |
frowned | +0.036 |
ls | +0.036 |
Neg logit contributions | |
age | -0.047 |
est | -0.043 |
ney | -0.042 |
gy | -0.042 |
inea | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | -8.76e-04 |
Pos logit contributions | |
cases | +0.006 |
spill | +0.005 |
outing | +0.005 |
yles | +0.005 |
salon | +0.005 |
Neg logit contributions | |
age | -0.005 |
Follow | -0.004 |
amed | -0.004 |
> | -0.004 |
welcome | -0.004 |
Token | Lily |
Token ID | 20037 |
Feature activation | +9.98e-03 |
Pos logit contributions | |
age | +0.001 |
right | +0.001 |
back | +0.001 |
welcome | +0.001 |
ok | +0.001 |
Neg logit contributions | |
yles | -0.002 |
cases | -0.002 |
yle | -0.001 |
ls | -0.001 |
salon | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +5.07e-04 |
Pos logit contributions | |
cases | +0.017 |
yles | +0.017 |
ls | +0.016 |
salon | +0.016 |
spill | +0.015 |
Neg logit contributions | |
age | -0.016 |
amed | -0.013 |
Follow | -0.013 |
> | -0.013 |
back | -0.013 |
Token | Cater |
Token ID | 40742 |
Feature activation | +2.24e-03 |
Pos logit contributions | |
yles | +0.001 |
cases | +0.001 |
yle | +0.001 |
salon | +0.001 |
ls | +0.001 |
Neg logit contributions | |
age | -0.001 |
back | -0.001 |
home | -0.001 |
> | -0.001 |
est | -0.001 |
Token | pill |
Token ID | 27215 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
yles | +0.003 |
cases | +0.003 |
ls | +0.003 |
yle | +0.003 |
salon | +0.002 |
Neg logit contributions | |
age | -0.005 |
back | -0.004 |
> | -0.004 |
home | -0.004 |
welcome | -0.004 |
Token | ars |
Token ID | 945 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
ls | +0.208 |
cases | +0.206 |
yles | +0.195 |
else | +0.188 |
outing | +0.186 |
Neg logit contributions | |
age | -0.193 |
home | -0.184 |
gy | -0.181 |
back | -0.178 |
> | -0.173 |
Token | can |
Token ID | 460 |
Feature activation | +6.45e-03 |
Pos logit contributions | |
yles | +0.024 |
cases | +0.023 |
yle | +0.021 |
salon | +0.021 |
ls | +0.021 |
Neg logit contributions | |
age | -0.026 |
back | -0.023 |
welcome | -0.022 |
> | -0.022 |
home | -0.022 |
Token | be |
Token ID | 307 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
yles | +0.011 |
cases | +0.011 |
yle | +0.010 |
ls | +0.010 |
salon | +0.010 |
Neg logit contributions | |
age | -0.011 |
back | -0.009 |
welcome | -0.009 |
home | -0.009 |
> | -0.009 |
Token | tricky |
Token ID | 17198 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
yles | +0.038 |
cases | +0.037 |
ls | +0.036 |
spill | +0.035 |
ries | +0.034 |
Neg logit contributions | |
age | -0.042 |
> | -0.035 |
est | -0.034 |
Follow | -0.034 |
back | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +1.72e-03 |
Pos logit contributions | |
cases | +0.020 |
yles | +0.020 |
ls | +0.019 |
hairc | +0.019 |
spill | +0.018 |
Neg logit contributions | |
age | -0.019 |
> | -0.015 |
amed | -0.015 |
Follow | -0.015 |
gy | -0.015 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
yles | +0.005 |
cases | +0.005 |
ls | +0.005 |
yle | +0.005 |
ries | +0.005 |
Neg logit contributions | |
age | -0.005 |
back | -0.005 |
> | -0.005 |
home | -0.005 |
welcome | -0.004 |
Token | lots |
Token ID | 6041 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
age | +0.029 |
back | +0.023 |
home | +0.022 |
welcome | +0.022 |
> | +0.022 |
Neg logit contributions | |
yles | -0.052 |
cases | -0.051 |
ls | -0.049 |
yle | -0.048 |
salon | -0.048 |
Token | of |
Token ID | 286 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
yles | +0.121 |
cases | +0.113 |
yle | +0.110 |
salon | +0.109 |
outing | +0.108 |
Neg logit contributions | |
est | -0.057 |
welcome | -0.055 |
age | -0.055 |
back | -0.053 |
right | -0.052 |
Token | colourful |
Token ID | 44799 |
Feature activation | +9.71e-03 |
Pos logit contributions | |
yles | +0.057 |
cases | +0.056 |
salon | +0.052 |
yle | +0.052 |
outing | +0.050 |
Neg logit contributions | |
age | -0.047 |
welcome | -0.043 |
home | -0.042 |
right | -0.042 |
est | -0.042 |
Token | cater |
Token ID | 20825 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
yles | +0.019 |
cases | +0.019 |
salon | +0.018 |
yle | +0.018 |
outing | +0.018 |
Neg logit contributions | |
age | -0.013 |
est | -0.012 |
home | -0.012 |
back | -0.012 |
welcome | -0.011 |
Token | pill |
Token ID | 27215 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
yles | +0.008 |
cases | +0.008 |
yle | +0.006 |
ls | +0.006 |
salon | +0.006 |
Neg logit contributions | |
age | -0.036 |
back | -0.032 |
> | -0.032 |
welcome | -0.032 |
home | -0.031 |
Token | ars |
Token ID | 945 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
cases | +0.218 |
ls | +0.216 |
yles | +0.207 |
else | +0.191 |
l | +0.190 |
Neg logit contributions | |
age | -0.189 |
back | -0.173 |
est | -0.169 |
home | -0.169 |
gy | -0.169 |
Token | and |
Token ID | 290 |
Feature activation | +1.67e-03 |
Pos logit contributions | |
yles | +0.032 |
cases | +0.031 |
yle | +0.030 |
salon | +0.030 |
ls | +0.029 |
Neg logit contributions | |
age | -0.020 |
back | -0.017 |
home | -0.016 |
right | -0.016 |
across | -0.016 |
Token | an |
Token ID | 281 |
Feature activation | +4.84e-03 |
Pos logit contributions | |
yles | +0.003 |
cases | +0.003 |
yle | +0.003 |
outing | +0.003 |
salon | +0.003 |
Neg logit contributions | |
age | -0.003 |
back | -0.003 |
welcome | -0.002 |
home | -0.002 |
across | -0.002 |
Token | old |
Token ID | 1468 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
yles | +0.008 |
cases | +0.007 |
yle | +0.007 |
ries | +0.007 |
ls | +0.007 |
Neg logit contributions | |
age | -0.008 |
Follow | -0.007 |
back | -0.007 |
> | -0.007 |
amed | -0.006 |
Token | lady |
Token ID | 10846 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
yles | +0.036 |
salon | +0.036 |
cases | +0.035 |
ls | +0.035 |
yle | +0.034 |
Neg logit contributions | |
age | -0.042 |
> | -0.037 |
Follow | -0.036 |
amed | -0.036 |
back | -0.035 |
Token | We |
Token ID | 775 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
yles | +0.013 |
cases | +0.012 |
yle | +0.012 |
ls | +0.012 |
salon | +0.011 |
Neg logit contributions | |
age | -0.009 |
back | -0.008 |
> | -0.008 |
home | -0.007 |
est | -0.007 |
Token | have |
Token ID | 423 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
age | +0.023 |
right | +0.019 |
back | +0.019 |
welcome | +0.018 |
home | +0.018 |
Neg logit contributions | |
yles | -0.033 |
cases | -0.032 |
ries | -0.030 |
yle | -0.029 |
ls | -0.029 |
Token | different |
Token ID | 1180 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
yles | +0.042 |
cases | +0.041 |
yle | +0.039 |
ls | +0.038 |
outing | +0.037 |
Neg logit contributions | |
age | -0.024 |
back | -0.022 |
home | -0.021 |
right | -0.020 |
welcome | -0.020 |
Token | likes |
Token ID | 7832 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
age | +0.035 |
back | +0.031 |
welcome | +0.030 |
> | +0.030 |
est | +0.030 |
Neg logit contributions | |
yles | -0.025 |
cases | -0.025 |
yle | -0.023 |
ls | -0.023 |
salon | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e-03 |
Pos logit contributions | |
cases | +0.028 |
yles | +0.027 |
yle | +0.025 |
outing | +0.025 |
ls | +0.025 |
Neg logit contributions | |
age | -0.023 |
back | -0.021 |
home | -0.020 |
welcome | -0.020 |
> | -0.019 |
Token | disl |
Token ID | 19621 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
yles | +0.002 |
cases | +0.002 |
yle | +0.002 |
ls | +0.002 |
outing | +0.002 |
Neg logit contributions | |
age | -0.002 |
back | -0.002 |
welcome | -0.002 |
right | -0.001 |
home | -0.001 |
Token | ikes |
Token ID | 7938 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
yles | +0.187 |
cases | +0.185 |
ls | +0.177 |
salon | +0.177 |
yle | +0.174 |
Neg logit contributions | |
age | -0.221 |
est | -0.189 |
> | -0.185 |
back | -0.185 |
right | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | +5.62e-03 |
Pos logit contributions | |
age | +0.073 |
back | +0.060 |
welcome | +0.058 |
> | +0.058 |
home | +0.057 |
Neg logit contributions | |
yles | -0.102 |
cases | -0.100 |
yle | -0.094 |
ls | -0.094 |
salon | -0.092 |
Token | We |
Token ID | 775 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
yles | +0.011 |
cases | +0.010 |
yle | +0.010 |
ls | +0.009 |
salon | +0.009 |
Neg logit contributions | |
age | -0.009 |
home | -0.007 |
back | -0.007 |
> | -0.007 |
est | -0.007 |
Token | can |
Token ID | 460 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
age | +0.025 |
back | +0.021 |
right | +0.020 |
welcome | +0.020 |
home | +0.020 |
Neg logit contributions | |
yles | -0.033 |
cases | -0.032 |
ries | -0.030 |
yle | -0.029 |
ls | -0.029 |
Token | be |
Token ID | 307 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
yles | +0.021 |
cases | +0.021 |
ls | +0.019 |
yle | +0.019 |
ries | +0.019 |
Neg logit contributions | |
age | -0.017 |
back | -0.014 |
welcome | -0.014 |
home | -0.013 |
> | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +8.41e-04 |
Pos logit contributions | |
yles | +0.056 |
cases | +0.054 |
ls | +0.052 |
yle | +0.052 |
salon | +0.051 |
Neg logit contributions | |
age | -0.035 |
back | -0.028 |
> | -0.027 |
home | -0.027 |
welcome | -0.027 |
Token | watched |
Token ID | 7342 |
Feature activation | -2.07e-03 |
Pos logit contributions | |
yles | +0.002 |
cases | +0.002 |
ls | +0.002 |
outing | +0.002 |
yle | +0.002 |
Neg logit contributions | |
age | -0.001 |
back | -0.001 |
home | -0.001 |
right | -0.001 |
welcome | -0.001 |
Token | as |
Token ID | 355 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
age | +0.003 |
back | +0.003 |
> | +0.003 |
welcome | +0.003 |
home | +0.003 |
Neg logit contributions | |
yles | -0.004 |
cases | -0.004 |
ls | -0.003 |
yle | -0.003 |
salon | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
cases | +0.098 |
outing | +0.094 |
yles | +0.093 |
eling | +0.090 |
salon | +0.088 |
Neg logit contributions | |
home | -0.066 |
back | -0.065 |
right | -0.061 |
welcome | -0.059 |
across | -0.058 |
Token | cater |
Token ID | 20825 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
age | +0.023 |
back | +0.019 |
> | +0.019 |
welcome | +0.019 |
home | +0.018 |
Neg logit contributions | |
yles | -0.020 |
cases | -0.019 |
ls | -0.018 |
yle | -0.018 |
salon | -0.017 |
Token | pill |
Token ID | 27215 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
cases | +0.025 |
yles | +0.024 |
yle | +0.022 |
salon | +0.022 |
outing | +0.022 |
Neg logit contributions | |
age | -0.021 |
back | -0.016 |
est | -0.016 |
welcome | -0.016 |
> | -0.016 |
Token | ars |
Token ID | 945 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
cases | +0.235 |
yles | +0.231 |
ls | +0.223 |
yle | +0.213 |
salon | +0.210 |
Neg logit contributions | |
age | -0.173 |
back | -0.145 |
home | -0.144 |
> | -0.143 |
est | -0.141 |
Token | grew |
Token ID | 6348 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
yles | +0.026 |
yle | +0.024 |
cases | +0.024 |
hairc | +0.023 |
outing | +0.023 |
Neg logit contributions | |
age | -0.024 |
back | -0.023 |
across | -0.021 |
home | -0.021 |
right | -0.021 |
Token | bigger |
Token ID | 5749 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
yles | +0.033 |
cases | +0.033 |
ls | +0.032 |
ries | +0.030 |
yle | +0.030 |
Neg logit contributions | |
age | -0.023 |
> | -0.018 |
welcome | -0.017 |
Follow | -0.017 |
est | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +2.62e-04 |
Pos logit contributions | |
yles | +0.054 |
cases | +0.053 |
yle | +0.050 |
salon | +0.050 |
outing | +0.049 |
Neg logit contributions | |
age | -0.036 |
back | -0.030 |
home | -0.029 |
est | -0.028 |
right | -0.028 |
Token | bigger |
Token ID | 5749 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
yles | +0.001 |
cases | +0.001 |
ls | +0.001 |
yle | +0.001 |
salon | +0.001 |
Neg logit contributions | |
age | -0.000 |
back | -0.000 |
> | -0.000 |
welcome | -0.000 |
home | -0.000 |
Token | he |
Token ID | 339 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
yles | +0.005 |
cases | +0.005 |
ls | +0.004 |
salon | +0.004 |
yle | +0.004 |
Neg logit contributions | |
age | -0.006 |
back | -0.005 |
home | -0.005 |
welcome | -0.005 |
right | -0.005 |
Token | noticed |
Token ID | 6810 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
yles | +0.041 |
cases | +0.040 |
yle | +0.037 |
ls | +0.037 |
salon | +0.036 |
Neg logit contributions | |
age | -0.045 |
back | -0.040 |
> | -0.038 |
home | -0.038 |
right | -0.038 |
Token | some |
Token ID | 617 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
age | +0.054 |
back | +0.048 |
home | +0.046 |
right | +0.045 |
welcome | +0.043 |
Neg logit contributions | |
yles | -0.079 |
cases | -0.079 |
ls | -0.074 |
salon | -0.073 |
yle | -0.072 |
Token | other |
Token ID | 584 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
yles | +0.082 |
cases | +0.079 |
yle | +0.073 |
salon | +0.071 |
ls | +0.070 |
Neg logit contributions | |
age | -0.054 |
back | -0.053 |
right | -0.051 |
welcome | -0.051 |
est | -0.051 |
Token | cater |
Token ID | 20825 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
yles | +0.050 |
cases | +0.050 |
ls | +0.045 |
outing | +0.045 |
salon | +0.044 |
Neg logit contributions | |
age | -0.049 |
est | -0.046 |
back | -0.045 |
welcome | -0.045 |
home | -0.044 |
Token | pill |
Token ID | 27215 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
cases | +0.013 |
yles | +0.012 |
salon | +0.011 |
yle | +0.011 |
outing | +0.010 |
Neg logit contributions | |
age | -0.032 |
est | -0.028 |
back | -0.027 |
welcome | -0.027 |
> | -0.027 |
Token | ars |
Token ID | 945 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
cases | +0.225 |
yles | +0.220 |
ls | +0.216 |
yle | +0.202 |
outing | +0.199 |
Neg logit contributions | |
age | -0.178 |
back | -0.155 |
home | -0.155 |
> | -0.151 |
gy | -0.150 |
Token | stretching |
Token ID | 20880 |
Feature activation | -7.95e-03 |
Pos logit contributions | |
yles | +0.032 |
cases | +0.030 |
yle | +0.030 |
salon | +0.029 |
ls | +0.029 |
Neg logit contributions | |
age | -0.019 |
back | -0.018 |
right | -0.016 |
across | -0.016 |
home | -0.015 |
Token | towards |
Token ID | 3371 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
age | +0.011 |
> | +0.009 |
welcome | +0.009 |
back | +0.009 |
Follow | +0.009 |
Neg logit contributions | |
yles | -0.016 |
cases | -0.016 |
ls | -0.015 |
yle | -0.015 |
salon | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
age | +0.018 |
back | +0.016 |
home | +0.015 |
welcome | +0.015 |
right | +0.015 |
Neg logit contributions | |
cases | -0.017 |
yles | -0.017 |
ls | -0.016 |
salon | -0.015 |
yle | -0.015 |
Token | too |
Token ID | 1165 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
cases | +0.019 |
yles | +0.019 |
ls | +0.018 |
yle | +0.017 |
salon | +0.017 |
Neg logit contributions | |
age | -0.017 |
> | -0.014 |
welcome | -0.014 |
Follow | -0.013 |
amed | -0.013 |
Token | you |
Token ID | 345 |
Feature activation | -2.59e-03 |
Pos logit contributions | |
age | +0.004 |
back | +0.004 |
home | +0.004 |
right | +0.004 |
welcome | +0.003 |
Neg logit contributions | |
yles | -0.006 |
cases | -0.006 |
ls | -0.005 |
salon | -0.005 |
outing | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +1.10e-03 |
Pos logit contributions | |
age | +0.004 |
back | +0.003 |
welcome | +0.003 |
> | +0.003 |
home | +0.003 |
Neg logit contributions | |
yles | -0.005 |
cases | -0.005 |
yle | -0.004 |
ls | -0.004 |
salon | -0.004 |
Token | Lily |
Token ID | 20037 |
Feature activation | +7.03e-03 |
Pos logit contributions | |
yles | +0.002 |
cases | +0.002 |
ls | +0.002 |
yle | +0.002 |
outing | +0.002 |
Neg logit contributions | |
age | -0.002 |
right | -0.001 |
welcome | -0.001 |
back | -0.001 |
home | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +4.36e-03 |
Pos logit contributions | |
cases | +0.011 |
yles | +0.011 |
ls | +0.011 |
salon | +0.010 |
yle | +0.010 |
Neg logit contributions | |
age | -0.012 |
amed | -0.010 |
Follow | -0.010 |
> | -0.010 |
est | -0.009 |
Token | Cater |
Token ID | 40742 |
Feature activation | +3.13e-03 |
Pos logit contributions | |
yles | +0.008 |
cases | +0.008 |
yle | +0.008 |
salon | +0.008 |
hairc | +0.007 |
Neg logit contributions | |
age | -0.006 |
back | -0.005 |
amed | -0.005 |
home | -0.005 |
> | -0.005 |
Token | pill |
Token ID | 27215 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
yles | +0.002 |
cases | +0.002 |
ls | +0.002 |
yle | +0.002 |
salon | +0.001 |
Neg logit contributions | |
age | -0.009 |
back | -0.008 |
> | -0.008 |
home | -0.008 |
welcome | -0.008 |
Token | ars |
Token ID | 945 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
ls | +0.190 |
cases | +0.188 |
else | +0.176 |
yles | +0.172 |
l | +0.169 |
Neg logit contributions | |
age | -0.185 |
gy | -0.183 |
home | -0.178 |
wood | -0.175 |
back | -0.170 |
Token | can |
Token ID | 460 |
Feature activation | +8.04e-03 |
Pos logit contributions | |
yles | +0.021 |
cases | +0.020 |
yle | +0.019 |
ls | +0.019 |
salon | +0.019 |
Neg logit contributions | |
age | -0.024 |
back | -0.021 |
welcome | -0.021 |
right | -0.020 |
> | -0.020 |
Token | leave |
Token ID | 2666 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
yles | +0.016 |
cases | +0.016 |
ls | +0.015 |
yle | +0.015 |
salon | +0.014 |
Neg logit contributions | |
age | -0.012 |
back | -0.010 |
welcome | -0.010 |
> | -0.010 |
home | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +1.95e-04 |
Pos logit contributions | |
yles | +0.027 |
cases | +0.026 |
ls | +0.024 |
yle | +0.024 |
salon | +0.024 |
Neg logit contributions | |
age | -0.023 |
back | -0.020 |
welcome | -0.019 |
home | -0.019 |
> | -0.019 |
Token | never |
Token ID | 1239 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
yles | +0.000 |
cases | +0.000 |
ls | +0.000 |
yle | +0.000 |
salon | +0.000 |
Neg logit contributions | |
age | -0.000 |
back | -0.000 |
welcome | -0.000 |
home | -0.000 |
> | -0.000 |
Token | but |
Token ID | 475 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
yles | +0.000 |
cases | +0.000 |
ls | +0.000 |
yle | +0.000 |
salon | +0.000 |
Neg logit contributions | |
age | -0.000 |
right | -0.000 |
back | -0.000 |
welcome | -0.000 |
home | -0.000 |
Token | he |
Token ID | 339 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
right | +0.020 |
back | +0.019 |
age | +0.019 |
welcome | +0.019 |
home | +0.018 |
Neg logit contributions | |
cases | -0.019 |
yles | -0.019 |
yle | -0.017 |
ls | -0.017 |
outing | -0.017 |
Token | also |
Token ID | 635 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
yles | +0.048 |
cases | +0.046 |
yle | +0.042 |
ries | +0.041 |
salon | +0.041 |
Neg logit contributions | |
age | -0.040 |
back | -0.035 |
right | -0.033 |
ney | -0.032 |
man | -0.032 |
Token | knew |
Token ID | 2993 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
yles | +0.032 |
cases | +0.031 |
ries | +0.029 |
ls | +0.028 |
yle | +0.028 |
Neg logit contributions | |
age | -0.022 |
back | -0.020 |
right | -0.020 |
welcome | -0.019 |
amed | -0.018 |
Token | cater |
Token ID | 20825 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
age | +0.010 |
back | +0.010 |
right | +0.009 |
home | +0.009 |
best | +0.009 |
Neg logit contributions | |
cases | -0.011 |
yles | -0.011 |
outing | -0.010 |
yle | -0.010 |
spill | -0.010 |
Token | pill |
Token ID | 27215 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
cases | +0.012 |
yles | +0.011 |
salon | +0.010 |
yle | +0.010 |
hairc | +0.009 |
Neg logit contributions | |
age | -0.026 |
est | -0.022 |
welcome | -0.022 |
Follow | -0.022 |
back | -0.022 |
Token | ars |
Token ID | 945 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
yles | +0.241 |
cases | +0.238 |
ls | +0.226 |
yle | +0.223 |
salon | +0.219 |
Neg logit contributions | |
age | -0.167 |
back | -0.134 |
> | -0.132 |
home | -0.130 |
welcome | -0.130 |
Token | were |
Token ID | 547 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
yles | +0.029 |
yle | +0.027 |
cases | +0.027 |
salon | +0.026 |
ls | +0.025 |
Neg logit contributions | |
age | -0.015 |
back | -0.015 |
right | -0.013 |
home | -0.012 |
est | -0.012 |
Token | not |
Token ID | 407 |
Feature activation | +4.78e-04 |
Pos logit contributions | |
yles | +0.069 |
cases | +0.068 |
yle | +0.064 |
salon | +0.063 |
ls | +0.062 |
Neg logit contributions | |
age | -0.044 |
back | -0.040 |
right | -0.038 |
welcome | -0.038 |
home | -0.036 |
Token | pets |
Token ID | 17252 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
yles | +0.001 |
cases | +0.001 |
yle | +0.001 |
ls | +0.001 |
salon | +0.001 |
Neg logit contributions | |
age | -0.001 |
back | -0.001 |
welcome | -0.001 |
home | -0.001 |
right | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +3.55e-03 |
Pos logit contributions | |
yles | +0.033 |
cases | +0.032 |
yle | +0.030 |
salon | +0.030 |
ls | +0.029 |
Neg logit contributions | |
age | -0.020 |
back | -0.018 |
welcome | -0.017 |
right | -0.017 |
home | -0.016 |
Token | ily |
Token ID | 813 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
yles | +0.031 |
cases | +0.031 |
yle | +0.028 |
ls | +0.028 |
salon | +0.028 |
Neg logit contributions | |
age | -0.029 |
back | -0.025 |
home | -0.025 |
> | -0.025 |
welcome | -0.025 |
Token | liked |
Token ID | 8288 |
Feature activation | +7.38e-03 |
Pos logit contributions | |
yles | +0.020 |
cases | +0.020 |
ls | +0.019 |
yle | +0.018 |
salon | +0.018 |
Neg logit contributions | |
age | -0.023 |
back | -0.019 |
> | -0.019 |
welcome | -0.019 |
est | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
cases | +0.017 |
yles | +0.017 |
yle | +0.016 |
outing | +0.016 |
ls | +0.016 |
Neg logit contributions | |
age | -0.007 |
home | -0.007 |
back | -0.007 |
welcome | -0.006 |
right | -0.006 |
Token | keep |
Token ID | 1394 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
yles | +0.029 |
cases | +0.028 |
ls | +0.027 |
outing | +0.026 |
yle | +0.026 |
Neg logit contributions | |
age | -0.021 |
welcome | -0.018 |
back | -0.017 |
home | -0.017 |
> | -0.017 |
Token | cater |
Token ID | 20825 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
cases | +0.028 |
outing | +0.025 |
yles | +0.025 |
salon | +0.025 |
yle | +0.025 |
Neg logit contributions | |
home | -0.016 |
back | -0.016 |
age | -0.016 |
right | -0.015 |
welcome | -0.014 |
Token | pill |
Token ID | 27215 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
cases | +0.008 |
yles | +0.008 |
salon | +0.007 |
spill | +0.006 |
yle | +0.006 |
Neg logit contributions | |
age | -0.018 |
welcome | -0.016 |
est | -0.016 |
back | -0.015 |
Follow | -0.015 |
Token | ars |
Token ID | 945 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ls | +0.203 |
cases | +0.203 |
yles | +0.191 |
else | +0.185 |
l | +0.182 |
Neg logit contributions | |
age | -0.182 |
gy | -0.167 |
back | -0.165 |
home | -0.164 |
est | -0.164 |
Token | in |
Token ID | 287 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
cases | +0.022 |
yles | +0.022 |
ls | +0.022 |
yle | +0.021 |
salon | +0.020 |
Neg logit contributions | |
age | -0.018 |
welcome | -0.014 |
Follow | -0.014 |
> | -0.014 |
est | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +5.97e-04 |
Pos logit contributions | |
age | +0.022 |
welcome | +0.021 |
back | +0.021 |
home | +0.021 |
right | +0.020 |
Neg logit contributions | |
cases | -0.026 |
yles | -0.025 |
ls | -0.024 |
outing | -0.023 |
yle | -0.022 |
Token | jar |
Token ID | 17379 |
Feature activation | +5.81e-03 |
Pos logit contributions | |
yles | +0.001 |
cases | +0.001 |
ls | +0.001 |
salon | +0.001 |
yle | +0.001 |
Neg logit contributions | |
age | -0.001 |
est | -0.001 |
> | -0.001 |
amed | -0.001 |
welcome | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.81e-03 |
Pos logit contributions | |
cases | +0.010 |
yles | +0.009 |
ls | +0.009 |
salon | +0.009 |
yle | +0.009 |
Neg logit contributions | |
age | -0.010 |
> | -0.008 |
welcome | -0.008 |
Follow | -0.008 |
est | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +2.74e-03 |
Pos logit contributions | |
yles | +0.009 |
cases | +0.009 |
yle | +0.009 |
ls | +0.009 |
salon | +0.009 |
Neg logit contributions | |
age | -0.005 |
back | -0.004 |
welcome | -0.004 |
> | -0.004 |
home | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
yles | +0.006 |
cases | +0.005 |
ls | +0.005 |
yle | +0.005 |
salon | +0.005 |
Neg logit contributions | |
age | -0.004 |
back | -0.003 |
> | -0.003 |
welcome | -0.003 |
home | -0.003 |
Token | I |
Token ID | 40 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
yles | +0.024 |
cases | +0.023 |
yle | +0.022 |
ls | +0.022 |
salon | +0.022 |
Neg logit contributions | |
age | -0.029 |
back | -0.025 |
welcome | -0.024 |
> | -0.024 |
home | -0.024 |
Token | love |
Token ID | 1842 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
age | +0.028 |
back | +0.024 |
> | +0.024 |
welcome | +0.023 |
est | +0.023 |
Neg logit contributions | |
yles | -0.026 |
cases | -0.026 |
ls | -0.024 |
yle | -0.024 |
salon | -0.024 |
Token | cater |
Token ID | 20825 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
age | +0.032 |
back | +0.026 |
> | +0.026 |
welcome | +0.026 |
home | +0.025 |
Neg logit contributions | |
yles | -0.035 |
cases | -0.034 |
ls | -0.032 |
yle | -0.032 |
salon | -0.031 |
Token | pill |
Token ID | 27215 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
yles | +0.009 |
cases | +0.008 |
yle | +0.007 |
salon | +0.007 |
ls | +0.007 |
Neg logit contributions | |
age | -0.030 |
back | -0.027 |
welcome | -0.026 |
> | -0.026 |
est | -0.026 |
Token | ars |
Token ID | 945 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
ls | +0.194 |
cases | +0.194 |
yles | +0.185 |
else | +0.175 |
yle | +0.174 |
Neg logit contributions | |
age | -0.190 |
gy | -0.171 |
back | -0.171 |
home | -0.170 |
> | -0.169 |
Token | ! |
Token ID | 0 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
cases | +0.027 |
yles | +0.027 |
ls | +0.026 |
yle | +0.025 |
salon | +0.025 |
Neg logit contributions | |
age | -0.019 |
> | -0.015 |
Follow | -0.014 |
amed | -0.014 |
back | -0.014 |
Token | You |
Token ID | 921 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
age | +0.020 |
amed | +0.018 |
home | +0.018 |
back | +0.017 |
> | +0.017 |
Neg logit contributions | |
yles | -0.015 |
cases | -0.015 |
yle | -0.013 |
salon | -0.013 |
hairc | -0.013 |
Token | can |
Token ID | 460 |
Feature activation | +9.53e-03 |
Pos logit contributions | |
age | +0.045 |
> | +0.039 |
back | +0.037 |
home | +0.037 |
amed | +0.037 |
Neg logit contributions | |
cases | -0.032 |
yles | -0.032 |
ls | -0.030 |
yle | -0.029 |
spill | -0.029 |
Token | be |
Token ID | 307 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
yles | +0.016 |
cases | +0.016 |
yle | +0.015 |
ls | +0.015 |
salon | +0.015 |
Neg logit contributions | |
age | -0.016 |
> | -0.013 |
back | -0.013 |
est | -0.013 |
amed | -0.013 |
Token | put |
Token ID | 1234 |
Feature activation | -7.81e-03 |
Pos logit contributions | |
spill | +0.023 |
salon | +0.022 |
yles | +0.022 |
yle | +0.022 |
cases | +0.022 |
Neg logit contributions | |
age | -0.024 |
amed | -0.020 |
Follow | -0.020 |
> | -0.020 |
est | -0.020 |
Token | it |
Token ID | 340 |
Feature activation | +8.90e-03 |
Pos logit contributions | |
age | +0.017 |
> | +0.014 |
est | +0.014 |
ney | +0.014 |
Follow | +0.014 |
Neg logit contributions | |
yles | -0.010 |
ls | -0.009 |
ries | -0.009 |
yle | -0.009 |
cases | -0.009 |
Token | back |
Token ID | 736 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
cases | +0.017 |
ls | +0.017 |
spill | +0.016 |
yles | +0.016 |
outing | +0.015 |
Neg logit contributions | |
age | -0.013 |
est | -0.010 |
Follow | -0.010 |
impact | -0.010 |
effect | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +3.72e-03 |
Pos logit contributions | |
age | +0.062 |
> | +0.047 |
welcome | +0.047 |
back | +0.047 |
est | +0.046 |
Neg logit contributions | |
yles | -0.096 |
cases | -0.095 |
ls | -0.090 |
yle | -0.089 |
salon | -0.088 |
Token | Cater |
Token ID | 40742 |
Feature activation | +2.07e-03 |
Pos logit contributions | |
yles | +0.007 |
yle | +0.006 |
cases | +0.006 |
hairc | +0.006 |
salon | +0.006 |
Neg logit contributions | |
age | -0.006 |
amed | -0.005 |
back | -0.005 |
> | -0.005 |
sy | -0.005 |
Token | pill |
Token ID | 27215 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
yles | +0.002 |
ls | +0.001 |
cases | +0.001 |
yle | +0.001 |
salon | +0.001 |
Neg logit contributions | |
age | -0.006 |
back | -0.005 |
> | -0.005 |
home | -0.005 |
welcome | -0.005 |
Token | ars |
Token ID | 945 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
ls | +0.193 |
cases | +0.187 |
yles | +0.179 |
else | +0.176 |
l | +0.170 |
Neg logit contributions | |
age | -0.184 |
gy | -0.178 |
home | -0.168 |
est | -0.166 |
wood | -0.165 |
Token | need |
Token ID | 761 |
Feature activation | +8.65e-06 |
Pos logit contributions | |
yles | +0.022 |
cases | +0.021 |
yle | +0.020 |
salon | +0.019 |
ries | +0.019 |
Neg logit contributions | |
age | -0.021 |
back | -0.019 |
welcome | -0.018 |
right | -0.018 |
home | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +1.32e-02 |
Token | eat |
Token ID | 4483 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
yles | +0.026 |
cases | +0.025 |
ls | +0.024 |
yle | +0.023 |
salon | +0.023 |
Neg logit contributions | |
age | -0.020 |
back | -0.017 |
welcome | -0.017 |
> | -0.016 |
home | -0.016 |
Token | leaves |
Token ID | 5667 |
Feature activation | +4.49e-03 |
Pos logit contributions | |
yles | +0.021 |
cases | +0.021 |
ls | +0.020 |
yle | +0.020 |
salon | +0.019 |
Neg logit contributions | |
age | -0.019 |
> | -0.015 |
back | -0.015 |
welcome | -0.014 |
est | -0.014 |
Token | Lily |
Token ID | 20037 |
Feature activation | +8.09e-03 |
Pos logit contributions | |
age | +0.002 |
back | +0.002 |
welcome | +0.002 |
right | +0.002 |
home | +0.002 |
Neg logit contributions | |
cases | -0.003 |
yles | -0.003 |
ls | -0.003 |
outing | -0.003 |
yle | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -1.61e-03 |
Pos logit contributions | |
cases | +0.014 |
ls | +0.014 |
yles | +0.014 |
wra | +0.013 |
yle | +0.013 |
Neg logit contributions | |
age | -0.013 |
amed | -0.011 |
> | -0.011 |
Follow | -0.010 |
welcome | -0.010 |
Token | no |
Token ID | 645 |
Feature activation | -1.80e-03 |
Pos logit contributions | |
age | +0.003 |
back | +0.002 |
welcome | +0.002 |
right | +0.002 |
home | +0.002 |
Neg logit contributions | |
cases | -0.003 |
yles | -0.003 |
ls | -0.003 |
yle | -0.003 |
outing | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +3.03e-03 |
Pos logit contributions | |
age | +0.003 |
> | +0.002 |
back | +0.002 |
amed | +0.002 |
Follow | +0.002 |
Neg logit contributions | |
yles | -0.004 |
cases | -0.004 |
ls | -0.003 |
salon | -0.003 |
yle | -0.003 |
Token | Cater |
Token ID | 40742 |
Feature activation | +1.64e-03 |
Pos logit contributions | |
yles | +0.006 |
cases | +0.006 |
yle | +0.006 |
ls | +0.006 |
salon | +0.006 |
Neg logit contributions | |
age | -0.004 |
amed | -0.003 |
> | -0.003 |
home | -0.003 |
back | -0.003 |
Token | pill |
Token ID | 27215 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
yles | +0.001 |
ls | +0.001 |
cases | +0.001 |
yle | +0.001 |
salon | +0.001 |
Neg logit contributions | |
age | -0.005 |
back | -0.004 |
> | -0.004 |
home | -0.004 |
welcome | -0.004 |
Token | ars |
Token ID | 945 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
yles | +0.242 |
cases | +0.239 |
ls | +0.226 |
yle | +0.224 |
salon | +0.221 |
Neg logit contributions | |
age | -0.160 |
back | -0.127 |
> | -0.125 |
welcome | -0.124 |
home | -0.122 |
Token | are |
Token ID | 389 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
yles | +0.022 |
cases | +0.020 |
yle | +0.019 |
salon | +0.019 |
ries | +0.018 |
Neg logit contributions | |
age | -0.019 |
back | -0.017 |
welcome | -0.017 |
right | -0.016 |
est | -0.015 |
Token | not |
Token ID | 407 |
Feature activation | -5.29e-04 |
Pos logit contributions | |
yles | +0.046 |
cases | +0.046 |
yle | +0.043 |
salon | +0.042 |
ls | +0.042 |
Neg logit contributions | |
age | -0.035 |
back | -0.030 |
welcome | -0.029 |
right | -0.028 |
home | -0.028 |
Token | for |
Token ID | 329 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
age | +0.001 |
> | +0.001 |
back | +0.001 |
welcome | +0.001 |
Follow | +0.001 |
Neg logit contributions | |
yles | -0.001 |
cases | -0.001 |
ls | -0.001 |
yle | -0.001 |
salon | -0.001 |
Token | keeping |
Token ID | 5291 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
home | +0.030 |
welcome | +0.029 |
age | +0.029 |
back | +0.029 |
right | +0.028 |
Neg logit contributions | |
cases | -0.050 |
yles | -0.046 |
salon | -0.043 |
yle | -0.042 |
ls | -0.041 |
Token | was |
Token ID | 373 |
Feature activation | +7.38e-03 |
Pos logit contributions | |
yles | +0.030 |
cases | +0.030 |
ls | +0.028 |
yle | +0.027 |
salon | +0.027 |
Neg logit contributions | |
age | -0.037 |
back | -0.031 |
> | -0.031 |
welcome | -0.031 |
home | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | +4.90e-04 |
Pos logit contributions | |
yles | +0.014 |
cases | +0.014 |
ls | +0.014 |
yle | +0.013 |
salon | +0.013 |
Neg logit contributions | |
age | -0.011 |
> | -0.009 |
est | -0.008 |
back | -0.008 |
welcome | -0.008 |
Token | box |
Token ID | 3091 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
yles | +0.001 |
cases | +0.001 |
salon | +0.001 |
ls | +0.001 |
spill | +0.001 |
Neg logit contributions | |
age | -0.001 |
> | -0.001 |
est | -0.001 |
amed | -0.001 |
Follow | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
age | +0.072 |
> | +0.058 |
welcome | +0.057 |
Follow | +0.057 |
back | +0.056 |
Neg logit contributions | |
cases | -0.088 |
yles | -0.084 |
ls | -0.081 |
yle | -0.081 |
salon | -0.080 |
Token | ch |
Token ID | 442 |
Feature activation | +9.07e-03 |
Pos logit contributions | |
yles | +0.048 |
cases | +0.047 |
yle | +0.043 |
ls | +0.043 |
salon | +0.042 |
Neg logit contributions | |
age | -0.053 |
back | -0.046 |
welcome | -0.046 |
home | -0.045 |
> | -0.044 |
Token | ocol |
Token ID | 4668 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
yles | +0.008 |
cases | +0.008 |
salon | +0.007 |
yle | +0.006 |
ls | +0.006 |
Neg logit contributions | |
age | -0.024 |
back | -0.021 |
> | -0.021 |
welcome | -0.021 |
home | -0.021 |
Token | ates |
Token ID | 689 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
yles | +0.261 |
cases | +0.253 |
ls | +0.243 |
ries | +0.243 |
yle | +0.241 |
Neg logit contributions | |
age | -0.135 |
back | -0.105 |
welcome | -0.105 |
> | -0.101 |
est | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-03 |
Pos logit contributions | |
age | +0.063 |
back | +0.053 |
home | +0.050 |
right | +0.049 |
> | +0.049 |
Neg logit contributions | |
yles | -0.099 |
cases | -0.095 |
yle | -0.091 |
salon | -0.091 |
ls | -0.090 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
yles | +0.002 |
cases | +0.002 |
yle | +0.002 |
ls | +0.002 |
salon | +0.002 |
Neg logit contributions | |
age | -0.002 |
est | -0.002 |
amed | -0.002 |
home | -0.002 |
> | -0.002 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.60e-03 |
Pos logit contributions | |
yles | +0.022 |
cases | +0.020 |
yle | +0.020 |
ls | +0.020 |
outing | +0.019 |
Neg logit contributions | |
age | -0.024 |
back | -0.021 |
> | -0.021 |
right | -0.020 |
gy | -0.020 |
Token | ch |
Token ID | 442 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
home | +0.002 |
back | +0.002 |
right | +0.002 |
welcome | +0.002 |
for | +0.002 |
Neg logit contributions | |
cases | -0.003 |
outing | -0.003 |
ls | -0.003 |
yles | -0.003 |
yle | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +9.88e-03 |
Pos logit contributions | |
yles | +0.027 |
cases | +0.026 |
yle | +0.024 |
outing | +0.024 |
salon | +0.024 |
Neg logit contributions | |
age | -0.021 |
back | -0.019 |
home | -0.018 |
welcome | -0.018 |
est | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -7.67e-05 |
Pos logit contributions | |
yles | +0.023 |
cases | +0.023 |
ls | +0.022 |
yle | +0.022 |
salon | +0.021 |
Neg logit contributions | |
age | -0.011 |
back | -0.008 |
welcome | -0.008 |
> | -0.008 |
home | -0.008 |
Token | box |
Token ID | 3091 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
age | +0.000 |
> | +0.000 |
back | +0.000 |
welcome | +0.000 |
est | +0.000 |
Neg logit contributions | |
yles | -0.000 |
cases | -0.000 |
ls | -0.000 |
salon | -0.000 |
yle | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
age | +0.068 |
back | +0.055 |
> | +0.055 |
welcome | +0.055 |
home | +0.054 |
Neg logit contributions | |
yles | -0.081 |
cases | -0.080 |
ls | -0.075 |
yle | -0.075 |
salon | -0.073 |
Token | ch |
Token ID | 442 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
yles | +0.051 |
cases | +0.050 |
ls | +0.046 |
yle | +0.046 |
outing | +0.045 |
Neg logit contributions | |
age | -0.052 |
welcome | -0.047 |
back | -0.047 |
home | -0.046 |
right | -0.045 |
Token | ocol |
Token ID | 4668 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
cases | +0.017 |
yles | +0.017 |
salon | +0.015 |
yle | +0.013 |
wra | +0.012 |
Neg logit contributions | |
age | -0.039 |
back | -0.035 |
home | -0.035 |
welcome | -0.035 |
est | -0.034 |
Token | ates |
Token ID | 689 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
yles | +0.259 |
cases | +0.253 |
ls | +0.241 |
yle | +0.240 |
ries | +0.238 |
Neg logit contributions | |
age | -0.137 |
back | -0.106 |
welcome | -0.105 |
> | -0.103 |
home | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | +2.68e-03 |
Pos logit contributions | |
age | +0.058 |
back | +0.050 |
home | +0.047 |
right | +0.046 |
across | +0.044 |
Neg logit contributions | |
yles | -0.106 |
cases | -0.100 |
salon | -0.097 |
yle | -0.097 |
ls | -0.096 |
Token | " |
Token ID | 366 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
yles | +0.006 |
cases | +0.006 |
yle | +0.005 |
ls | +0.005 |
salon | +0.005 |
Neg logit contributions | |
age | -0.004 |
back | -0.003 |
> | -0.003 |
welcome | -0.003 |
est | -0.003 |
Token | For |
Token ID | 1890 |
Feature activation | +1.48e-04 |
Pos logit contributions | |
yles | +0.028 |
cases | +0.028 |
yle | +0.026 |
ls | +0.026 |
salon | +0.025 |
Neg logit contributions | |
age | -0.033 |
back | -0.028 |
> | -0.027 |
welcome | -0.027 |
home | -0.027 |
Token | me |
Token ID | 502 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
yles | +0.000 |
cases | +0.000 |
ls | +0.000 |
yle | +0.000 |
salon | +0.000 |
Neg logit contributions | |
age | -0.000 |
back | -0.000 |
welcome | -0.000 |
> | -0.000 |
home | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -2.35e-04 |
Pos logit contributions | |
age | +0.064 |
back | +0.053 |
home | +0.051 |
> | +0.050 |
welcome | +0.050 |
Neg logit contributions | |
yles | -0.091 |
cases | -0.087 |
yle | -0.083 |
ls | -0.083 |
salon | -0.081 |
Token | started |
Token ID | 2067 |
Feature activation | +8.13e-03 |
Pos logit contributions | |
age | +0.000 |
back | +0.000 |
home | +0.000 |
right | +0.000 |
> | +0.000 |
Neg logit contributions | |
yles | -0.000 |
cases | -0.000 |
outing | -0.000 |
ls | -0.000 |
yle | -0.000 |
Token | eating |
Token ID | 6600 |
Feature activation | +2.27e-03 |
Pos logit contributions | |
yles | +0.018 |
cases | +0.018 |
ls | +0.018 |
yle | +0.017 |
outing | +0.017 |
Neg logit contributions | |
age | -0.009 |
back | -0.009 |
home | -0.009 |
right | -0.008 |
across | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
yles | +0.005 |
cases | +0.005 |
yle | +0.004 |
salon | +0.004 |
outing | +0.004 |
Neg logit contributions | |
back | -0.003 |
age | -0.003 |
right | -0.003 |
home | -0.003 |
welcome | -0.003 |
Token | ch |
Token ID | 442 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
age | +0.023 |
> | +0.019 |
amed | +0.019 |
Follow | +0.019 |
welcome | +0.018 |
Neg logit contributions | |
cases | -0.019 |
yles | -0.017 |
ls | -0.017 |
wra | -0.017 |
spill | -0.016 |
Token | ocol |
Token ID | 4668 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
yles | +0.014 |
cases | +0.013 |
salon | +0.011 |
yle | +0.010 |
ls | +0.010 |
Neg logit contributions | |
age | -0.044 |
est | -0.039 |
welcome | -0.039 |
back | -0.039 |
home | -0.038 |
Token | ates |
Token ID | 689 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
yles | +0.268 |
cases | +0.263 |
ls | +0.251 |
yle | +0.249 |
salon | +0.245 |
Neg logit contributions | |
age | -0.126 |
back | -0.095 |
welcome | -0.093 |
> | -0.092 |
home | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | +2.17e-03 |
Pos logit contributions | |
age | +0.061 |
back | +0.053 |
home | +0.051 |
right | +0.050 |
est | +0.047 |
Neg logit contributions | |
yles | -0.103 |
cases | -0.098 |
yle | -0.094 |
salon | -0.093 |
ls | -0.092 |
Token | The |
Token ID | 383 |
Feature activation | -5.96e-04 |
Pos logit contributions | |
yles | +0.005 |
cases | +0.005 |
ls | +0.005 |
yle | +0.005 |
salon | +0.005 |
Neg logit contributions | |
age | -0.002 |
back | -0.002 |
welcome | -0.002 |
> | -0.002 |
home | -0.002 |
Token | shop |
Token ID | 6128 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
age | +0.001 |
back | +0.001 |
welcome | +0.001 |
right | +0.001 |
home | +0.001 |
Neg logit contributions | |
yles | -0.001 |
cases | -0.001 |
ls | -0.001 |
yle | -0.001 |
outing | -0.001 |
Token | keeper |
Token ID | 13884 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
yles | +0.062 |
cases | +0.056 |
ls | +0.055 |
yle | +0.055 |
spill | +0.053 |
Neg logit contributions | |
age | -0.048 |
back | -0.042 |
home | -0.039 |
man | -0.039 |
right | -0.039 |
Token | not |
Token ID | 407 |
Feature activation | +9.27e-05 |
Pos logit contributions | |
age | +0.033 |
back | +0.027 |
> | +0.027 |
welcome | +0.026 |
home | +0.026 |
Neg logit contributions | |
yles | -0.043 |
cases | -0.042 |
ls | -0.040 |
yle | -0.040 |
salon | -0.039 |
Token | eat |
Token ID | 4483 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
yles | +0.000 |
cases | +0.000 |
ls | +0.000 |
yle | +0.000 |
ries | +0.000 |
Neg logit contributions | |
age | -0.000 |
back | -0.000 |
welcome | -0.000 |
home | -0.000 |
right | -0.000 |
Token | too |
Token ID | 1165 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
yles | +0.022 |
cases | +0.022 |
yle | +0.020 |
salon | +0.020 |
outing | +0.020 |
Neg logit contributions | |
back | -0.016 |
home | -0.015 |
age | -0.015 |
right | -0.015 |
welcome | -0.015 |
Token | many |
Token ID | 867 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
yles | +0.084 |
cases | +0.079 |
yle | +0.078 |
salon | +0.077 |
outing | +0.072 |
Neg logit contributions | |
age | -0.028 |
home | -0.026 |
welcome | -0.024 |
back | -0.023 |
right | -0.021 |
Token | ch |
Token ID | 442 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
cases | +0.110 |
yles | +0.109 |
outing | +0.105 |
salon | +0.105 |
yle | +0.103 |
Neg logit contributions | |
est | -0.066 |
back | -0.064 |
age | -0.063 |
welcome | -0.063 |
home | -0.063 |
Token | ocol |
Token ID | 4668 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
cases | +0.015 |
yles | +0.014 |
salon | +0.012 |
wra | +0.011 |
yle | +0.011 |
Neg logit contributions | |
age | -0.028 |
welcome | -0.026 |
home | -0.026 |
back | -0.026 |
advantage | -0.025 |
Token | ates |
Token ID | 689 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
yles | +0.264 |
cases | +0.256 |
ls | +0.246 |
yle | +0.245 |
ries | +0.243 |
Neg logit contributions | |
age | -0.130 |
back | -0.099 |
welcome | -0.099 |
> | -0.097 |
Follow | -0.093 |
Token | and |
Token ID | 290 |
Feature activation | -2.93e-03 |
Pos logit contributions | |
age | +0.062 |
back | +0.056 |
home | +0.052 |
right | +0.051 |
welcome | +0.049 |
Neg logit contributions | |
yles | -0.106 |
cases | -0.101 |
salon | -0.096 |
yle | -0.096 |
ls | -0.094 |
Token | his |
Token ID | 465 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
age | +0.005 |
back | +0.004 |
home | +0.004 |
welcome | +0.004 |
right | +0.004 |
Neg logit contributions | |
yles | -0.005 |
cases | -0.005 |
yle | -0.005 |
ls | -0.005 |
outing | -0.005 |
Token | friend |
Token ID | 1545 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
yles | +0.047 |
cases | +0.046 |
ls | +0.043 |
yle | +0.043 |
salon | +0.042 |
Neg logit contributions | |
age | -0.044 |
back | -0.037 |
welcome | -0.036 |
> | -0.036 |
home | -0.036 |
Token | learned |
Token ID | 4499 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
age | +0.034 |
> | +0.028 |
back | +0.028 |
welcome | +0.028 |
home | +0.028 |
Neg logit contributions | |
yles | -0.030 |
cases | -0.029 |
ls | -0.027 |
yle | -0.027 |
salon | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -8.68e-04 |
Pos logit contributions | |
age | +0.033 |
back | +0.028 |
home | +0.026 |
right | +0.025 |
welcome | +0.025 |
Neg logit contributions | |
yles | -0.064 |
cases | -0.062 |
ls | -0.060 |
yle | -0.059 |
salon | -0.058 |
Token | big |
Token ID | 1263 |
Feature activation | -5.33e-03 |
Pos logit contributions | |
age | +0.001 |
back | +0.001 |
welcome | +0.001 |
home | +0.001 |
right | +0.001 |
Neg logit contributions | |
yles | -0.002 |
cases | -0.002 |
ls | -0.001 |
yle | -0.001 |
ries | -0.001 |
Token | box |
Token ID | 3091 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
age | +0.009 |
> | +0.007 |
back | +0.007 |
welcome | +0.007 |
Follow | +0.007 |
Neg logit contributions | |
yles | -0.010 |
cases | -0.010 |
ls | -0.009 |
salon | -0.009 |
yle | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
age | +0.065 |
back | +0.054 |
right | +0.051 |
home | +0.051 |
> | +0.050 |
Neg logit contributions | |
yles | -0.098 |
cases | -0.094 |
ls | -0.090 |
yle | -0.089 |
salon | -0.087 |
Token | ch |
Token ID | 442 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
yles | +0.052 |
cases | +0.051 |
outing | +0.046 |
yle | +0.046 |
ls | +0.046 |
Neg logit contributions | |
age | -0.048 |
back | -0.044 |
welcome | -0.044 |
home | -0.043 |
right | -0.043 |
Token | ocol |
Token ID | 4668 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
cases | +0.013 |
yles | +0.012 |
salon | +0.011 |
yle | +0.010 |
hairc | +0.009 |
Neg logit contributions | |
age | -0.026 |
home | -0.023 |
back | -0.023 |
> | -0.023 |
welcome | -0.023 |
Token | ates |
Token ID | 689 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
yles | +0.260 |
cases | +0.252 |
ls | +0.242 |
ries | +0.240 |
yle | +0.240 |
Neg logit contributions | |
age | -0.133 |
welcome | -0.103 |
back | -0.103 |
> | -0.099 |
est | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | +1.92e-03 |
Pos logit contributions | |
age | +0.060 |
back | +0.053 |
right | +0.050 |
home | +0.050 |
across | +0.046 |
Neg logit contributions | |
yles | -0.108 |
cases | -0.101 |
yle | -0.098 |
salon | -0.098 |
ls | -0.097 |
Token | It |
Token ID | 632 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
cases | +0.004 |
yles | +0.004 |
yle | +0.004 |
salon | +0.004 |
ls | +0.003 |
Neg logit contributions | |
age | -0.003 |
back | -0.002 |
> | -0.002 |
welcome | -0.002 |
est | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +9.01e-03 |
Pos logit contributions | |
yles | +0.037 |
cases | +0.035 |
yle | +0.034 |
salon | +0.033 |
outing | +0.033 |
Neg logit contributions | |
age | -0.032 |
back | -0.027 |
right | -0.026 |
est | -0.026 |
gy | -0.025 |
Token | so |
Token ID | 523 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
yles | +0.019 |
cases | +0.019 |
ls | +0.018 |
yle | +0.018 |
salon | +0.018 |
Neg logit contributions | |
age | -0.012 |
back | -0.009 |
welcome | -0.009 |
> | -0.009 |
home | -0.009 |
Token | ates |
Token ID | 689 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
yles | +0.261 |
cases | +0.253 |
ls | +0.243 |
ries | +0.243 |
yle | +0.241 |
Neg logit contributions | |
age | -0.135 |
back | -0.105 |
welcome | -0.105 |
> | -0.101 |
est | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-03 |
Pos logit contributions | |
age | +0.063 |
back | +0.053 |
home | +0.050 |
right | +0.049 |
> | +0.049 |
Neg logit contributions | |
yles | -0.099 |
cases | -0.095 |
yle | -0.091 |
salon | -0.091 |
ls | -0.090 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
yles | +0.002 |
cases | +0.002 |
yle | +0.002 |
ls | +0.002 |
salon | +0.002 |
Neg logit contributions | |
age | -0.002 |
est | -0.002 |
amed | -0.002 |
home | -0.002 |
> | -0.002 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.60e-03 |
Pos logit contributions | |
yles | +0.022 |
cases | +0.020 |
yle | +0.020 |
ls | +0.020 |
outing | +0.019 |
Neg logit contributions | |
age | -0.024 |
back | -0.021 |
> | -0.021 |
right | -0.020 |
gy | -0.020 |
Token | ch |
Token ID | 442 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
home | +0.002 |
back | +0.002 |
right | +0.002 |
welcome | +0.002 |
for | +0.002 |
Neg logit contributions | |
cases | -0.003 |
outing | -0.003 |
ls | -0.003 |
yles | -0.003 |
yle | -0.003 |
Token | ocol |
Token ID | 4668 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
cases | +0.015 |
salon | +0.013 |
yles | +0.013 |
rang | +0.011 |
frowned | +0.011 |
Neg logit contributions | |
age | -0.024 |
welcome | -0.022 |
home | -0.021 |
est | -0.021 |
back | -0.021 |
Token | ates |
Token ID | 689 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
yles | +0.269 |
cases | +0.263 |
ls | +0.251 |
yle | +0.250 |
salon | +0.245 |
Neg logit contributions | |
age | -0.125 |
back | -0.093 |
welcome | -0.091 |
> | -0.090 |
home | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | +2.30e-03 |
Pos logit contributions | |
age | +0.063 |
back | +0.053 |
home | +0.050 |
welcome | +0.049 |
right | +0.049 |
Neg logit contributions | |
yles | -0.098 |
cases | -0.095 |
yle | -0.090 |
salon | -0.090 |
ls | -0.089 |
Token | She |
Token ID | 1375 |
Feature activation | -3.77e-03 |
Pos logit contributions | |
yles | +0.004 |
cases | +0.003 |
ls | +0.003 |
yle | +0.003 |
salon | +0.003 |
Neg logit contributions | |
age | -0.005 |
amed | -0.004 |
est | -0.004 |
> | -0.004 |
back | -0.004 |
Token | thanked |
Token ID | 26280 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
age | +0.006 |
back | +0.006 |
> | +0.005 |
right | +0.005 |
sy | +0.005 |
Neg logit contributions | |
yles | -0.007 |
cases | -0.006 |
yle | -0.006 |
outing | -0.006 |
ries | -0.006 |
Token | Ben |
Token ID | 3932 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
cases | +0.059 |
yles | +0.055 |
ls | +0.052 |
outing | +0.051 |
salon | +0.050 |
Neg logit contributions | |
age | -0.050 |
back | -0.049 |
welcome | -0.047 |
home | -0.047 |
right | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | -3.84e-03 |
Pos logit contributions | |
age | +0.010 |
back | +0.008 |
welcome | +0.008 |
home | +0.008 |
> | +0.008 |
Neg logit contributions | |
yles | -0.014 |
cases | -0.013 |
yle | -0.013 |
ls | -0.012 |
salon | -0.012 |
Token | lady |
Token ID | 10846 |
Feature activation | +7.94e-03 |
Pos logit contributions | |
age | +0.006 |
back | +0.005 |
welcome | +0.005 |
right | +0.005 |
home | +0.005 |
Neg logit contributions | |
cases | -0.007 |
yles | -0.007 |
yle | -0.007 |
outing | -0.006 |
salon | -0.006 |
Token | bugs |
Token ID | 32965 |
Feature activation | -5.45e-03 |
Pos logit contributions | |
cases | +0.014 |
yles | +0.014 |
yle | +0.013 |
salon | +0.012 |
ls | +0.012 |
Neg logit contributions | |
age | -0.014 |
back | -0.012 |
welcome | -0.011 |
home | -0.011 |
> | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -4.21e-03 |
Pos logit contributions | |
age | +0.008 |
back | +0.007 |
welcome | +0.006 |
home | +0.006 |
> | +0.006 |
Neg logit contributions | |
yles | -0.011 |
cases | -0.011 |
yle | -0.010 |
ls | -0.010 |
salon | -0.010 |
Token | cater |
Token ID | 20825 |
Feature activation | +5.36e-03 |
Pos logit contributions | |
age | +0.007 |
back | +0.006 |
welcome | +0.006 |
right | +0.006 |
home | +0.006 |
Neg logit contributions | |
cases | -0.008 |
yles | -0.008 |
yle | -0.007 |
outing | -0.007 |
salon | -0.007 |
Token | pill |
Token ID | 27215 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
cases | +0.005 |
yles | +0.005 |
yle | +0.004 |
salon | +0.004 |
outing | +0.004 |
Neg logit contributions | |
age | -0.013 |
back | -0.012 |
> | -0.012 |
welcome | -0.012 |
home | -0.012 |
Token | ars |
Token ID | 945 |
Feature activation | +8.25e-03 |
Pos logit contributions | |
yles | +0.211 |
cases | +0.210 |
ls | +0.207 |
yle | +0.194 |
spill | +0.192 |
Neg logit contributions | |
age | -0.168 |
back | -0.142 |
> | -0.141 |
home | -0.139 |
est | -0.138 |
Token | ." |
Token ID | 526 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
yles | +0.017 |
cases | +0.017 |
yle | +0.016 |
salon | +0.016 |
ls | +0.016 |
Neg logit contributions | |
age | -0.011 |
back | -0.010 |
welcome | -0.009 |
home | -0.009 |
> | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
yles | +0.028 |
cases | +0.027 |
ls | +0.026 |
yle | +0.026 |
salon | +0.025 |
Neg logit contributions | |
age | -0.018 |
back | -0.014 |
> | -0.014 |
welcome | -0.014 |
home | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
age | +0.017 |
est | +0.013 |
back | +0.013 |
welcome | +0.013 |
home | +0.013 |
Neg logit contributions | |
yles | -0.022 |
cases | -0.021 |
ls | -0.021 |
yle | -0.020 |
salon | -0.020 |
Token | Tim |
Token ID | 14967 |
Feature activation | -8.57e-03 |
Pos logit contributions | |
age | +0.019 |
back | +0.016 |
> | +0.016 |
welcome | +0.016 |
home | +0.015 |
Neg logit contributions | |
yles | -0.020 |
cases | -0.019 |
ls | -0.018 |
yle | -0.018 |
salon | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
yles | +0.064 |
cases | +0.064 |
ls | +0.060 |
outing | +0.059 |
yle | +0.058 |
Neg logit contributions | |
age | -0.058 |
home | -0.056 |
back | -0.056 |
right | -0.053 |
welcome | -0.051 |
Token | cars |
Token ID | 5006 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
age | +0.022 |
back | +0.019 |
welcome | +0.018 |
> | +0.018 |
home | +0.018 |
Neg logit contributions | |
yles | -0.023 |
cases | -0.022 |
ls | -0.021 |
yle | -0.021 |
salon | -0.020 |
Token | stopped |
Token ID | 5025 |
Feature activation | -2.68e-04 |
Pos logit contributions | |
age | +0.026 |
back | +0.023 |
home | +0.022 |
right | +0.021 |
across | +0.021 |
Neg logit contributions | |
yles | -0.025 |
yle | -0.022 |
ls | -0.021 |
outing | -0.021 |
ries | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -2.89e-03 |
Pos logit contributions | |
age | +0.000 |
back | +0.000 |
> | +0.000 |
welcome | +0.000 |
home | +0.000 |
Neg logit contributions | |
yles | -0.001 |
cases | -0.001 |
ls | -0.000 |
yle | -0.000 |
salon | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
age | +0.005 |
back | +0.005 |
right | +0.004 |
home | +0.004 |
across | +0.004 |
Neg logit contributions | |
yles | -0.005 |
cases | -0.005 |
yle | -0.005 |
ls | -0.005 |
outing | -0.005 |
Token | pedestrian |
Token ID | 22382 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
age | +0.020 |
> | +0.017 |
back | +0.017 |
welcome | +0.017 |
est | +0.016 |
Neg logit contributions | |
cases | -0.020 |
yles | -0.020 |
salon | -0.019 |
ls | -0.019 |
yle | -0.019 |
Token | light |
Token ID | 1657 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
age | +0.234 |
> | +0.194 |
Follow | +0.186 |
welcome | +0.184 |
home | +0.182 |
Neg logit contributions | |
cases | -0.284 |
yles | -0.274 |
ls | -0.265 |
yle | -0.254 |
outing | -0.253 |
Token | turned |
Token ID | 2900 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
yles | +0.070 |
yle | +0.064 |
cases | +0.063 |
salon | +0.062 |
ls | +0.061 |
Neg logit contributions | |
age | -0.053 |
back | -0.044 |
est | -0.043 |
home | -0.041 |
right | -0.041 |
Token | green |
Token ID | 4077 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
yles | +0.029 |
yle | +0.027 |
salon | +0.026 |
cases | +0.026 |
ls | +0.025 |
Neg logit contributions | |
age | -0.022 |
back | -0.020 |
right | -0.018 |
home | -0.018 |
across | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
age | +0.022 |
est | +0.019 |
back | +0.018 |
home | +0.018 |
across | +0.017 |
Neg logit contributions | |
yles | -0.023 |
yle | -0.022 |
cases | -0.022 |
ls | -0.021 |
salon | -0.021 |
Token | Then |
Token ID | 3244 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
yles | +0.004 |
cases | +0.004 |
yle | +0.003 |
salon | +0.003 |
ls | +0.003 |
Neg logit contributions | |
age | -0.003 |
est | -0.002 |
back | -0.002 |
welcome | -0.002 |
> | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -3.82e-03 |
Pos logit contributions | |
age | +0.013 |
back | +0.011 |
right | +0.010 |
welcome | +0.010 |
home | +0.010 |
Neg logit contributions | |
yles | -0.023 |
yle | -0.022 |
salon | -0.022 |
cases | -0.021 |
ls | -0.021 |
Token | books |
Token ID | 3835 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
age | +0.006 |
back | +0.006 |
welcome | +0.005 |
right | +0.005 |
across | +0.005 |
Neg logit contributions | |
yle | -0.007 |
yles | -0.007 |
outing | -0.007 |
cases | -0.007 |
ls | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +2.27e-03 |
Pos logit contributions | |
age | +0.043 |
back | +0.042 |
right | +0.039 |
across | +0.034 |
home | +0.033 |
Neg logit contributions | |
yles | -0.111 |
yle | -0.107 |
outing | -0.102 |
tant | -0.101 |
hairc | -0.101 |
Token | They |
Token ID | 1119 |
Feature activation | -7.26e-03 |
Pos logit contributions | |
yles | +0.004 |
cases | +0.004 |
yle | +0.004 |
ls | +0.004 |
salon | +0.004 |
Neg logit contributions | |
age | -0.003 |
back | -0.003 |
welcome | -0.003 |
> | -0.003 |
home | -0.003 |
Token | see |
Token ID | 766 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
welcome | +0.009 |
back | +0.008 |
right | +0.008 |
age | +0.008 |
home | +0.007 |
Neg logit contributions | |
yles | -0.016 |
cases | -0.015 |
ls | -0.015 |
yle | -0.015 |
ries | -0.015 |
Token | alt |
Token ID | 5988 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
back | +0.017 |
age | +0.016 |
right | +0.016 |
home | +0.015 |
welcome | +0.015 |
Neg logit contributions | |
yles | -0.023 |
cases | -0.022 |
yle | -0.021 |
outing | -0.021 |
salon | -0.020 |
Token | ars |
Token ID | 945 |
Feature activation | +7.66e-03 |
Pos logit contributions | |
age | +0.202 |
back | +0.157 |
> | +0.153 |
welcome | +0.149 |
home | +0.146 |
Neg logit contributions | |
yles | -0.328 |
cases | -0.317 |
yle | -0.306 |
ls | -0.302 |
salon | -0.297 |
Token | and |
Token ID | 290 |
Feature activation | -4.71e-03 |
Pos logit contributions | |
yles | +0.018 |
yle | +0.017 |
cases | +0.017 |
salon | +0.016 |
ls | +0.016 |
Neg logit contributions | |
age | -0.008 |
back | -0.008 |
right | -0.007 |
home | -0.007 |
across | -0.007 |
Token | offerings |
Token ID | 18369 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
age | +0.007 |
back | +0.007 |
welcome | +0.007 |
right | +0.007 |
across | +0.007 |
Neg logit contributions | |
yle | -0.008 |
yles | -0.008 |
cases | -0.008 |
outing | -0.008 |
ls | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -5.00e-03 |
Pos logit contributions | |
back | +0.019 |
right | +0.016 |
age | +0.016 |
home | +0.016 |
welcome | +0.015 |
Neg logit contributions | |
yles | -0.058 |
yle | -0.055 |
salon | -0.054 |
cases | -0.052 |
tant | -0.052 |
Token | priests |
Token ID | 17345 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
age | +0.008 |
back | +0.008 |
welcome | +0.007 |
right | +0.007 |
home | +0.007 |
Neg logit contributions | |
yles | -0.009 |
yle | -0.009 |
cases | -0.009 |
outing | -0.009 |
ls | -0.009 |
Token | so |
Token ID | 523 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
yles | +0.060 |
cases | +0.059 |
yle | +0.055 |
ls | +0.055 |
salon | +0.054 |
Neg logit contributions | |
age | -0.042 |
back | -0.035 |
welcome | -0.034 |
> | -0.034 |
home | -0.033 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -8.19e-03 |
Pos logit contributions | |
yles | +0.039 |
salon | +0.037 |
yle | +0.036 |
cases | +0.036 |
ries | +0.033 |
Neg logit contributions | |
age | -0.023 |
welcome | -0.022 |
back | -0.021 |
right | -0.021 |
home | -0.021 |
Token | inside |
Token ID | 2641 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
age | +0.011 |
back | +0.009 |
home | +0.008 |
right | +0.008 |
est | +0.008 |
Neg logit contributions | |
yles | -0.017 |
cases | -0.017 |
yle | -0.016 |
salon | -0.016 |
ls | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -3.12e-03 |
Pos logit contributions | |
yles | +0.028 |
cases | +0.027 |
yle | +0.026 |
salon | +0.026 |
ls | +0.025 |
Neg logit contributions | |
age | -0.022 |
back | -0.021 |
right | -0.020 |
welcome | -0.020 |
home | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
age | +0.004 |
back | +0.004 |
right | +0.004 |
welcome | +0.004 |
home | +0.004 |
Neg logit contributions | |
yles | -0.006 |
cases | -0.006 |
yle | -0.006 |
salon | -0.006 |
ls | -0.006 |
Token | fringe |
Token ID | 26821 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
age | +0.029 |
back | +0.027 |
home | +0.026 |
welcome | +0.026 |
right | +0.026 |
Neg logit contributions | |
yles | -0.032 |
cases | -0.031 |
salon | -0.028 |
yle | -0.028 |
ls | -0.028 |
Token | from |
Token ID | 422 |
Feature activation | -9.66e-03 |
Pos logit contributions | |
age | +0.187 |
back | +0.161 |
home | +0.149 |
right | +0.148 |
est | +0.148 |
Neg logit contributions | |
yles | -0.278 |
cases | -0.267 |
yle | -0.255 |
salon | -0.253 |
ls | -0.249 |
Token | the |
Token ID | 262 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
age | +0.013 |
back | +0.013 |
home | +0.013 |
> | +0.012 |
welcome | +0.012 |
Neg logit contributions | |
cases | -0.019 |
yles | -0.018 |
salon | -0.017 |
ls | -0.017 |
yle | -0.017 |
Token | cut |
Token ID | 2005 |
Feature activation | +1.26e-03 |
Pos logit contributions | |
age | +0.031 |
back | +0.027 |
> | +0.026 |
welcome | +0.026 |
home | +0.026 |
Neg logit contributions | |
yles | -0.031 |
cases | -0.031 |
ls | -0.028 |
yle | -0.028 |
salon | -0.028 |
Token | shells |
Token ID | 19679 |
Feature activation | +4.52e-03 |
Pos logit contributions | |
yles | +0.002 |
cases | +0.002 |
salon | +0.002 |
yle | +0.002 |
ls | +0.002 |
Neg logit contributions | |
age | -0.002 |
back | -0.002 |
est | -0.002 |
home | -0.002 |
right | -0.002 |
Token | made |
Token ID | 925 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
yles | +0.010 |
cases | +0.009 |
yle | +0.009 |
salon | +0.009 |
hairc | +0.009 |
Neg logit contributions | |
age | -0.006 |
back | -0.005 |
right | -0.005 |
home | -0.005 |
across | -0.005 |
Token | yellow |
Token ID | 7872 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
age | +0.021 |
back | +0.018 |
welcome | +0.018 |
> | +0.018 |
home | +0.017 |
Neg logit contributions | |
yles | -0.022 |
cases | -0.021 |
yle | -0.020 |
ls | -0.020 |
salon | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
age | +0.038 |
> | +0.031 |
back | +0.030 |
welcome | +0.030 |
Follow | +0.030 |
Neg logit contributions | |
yles | -0.048 |
cases | -0.048 |
ls | -0.045 |
yle | -0.045 |
salon | -0.044 |
Token | green |
Token ID | 4077 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
age | +0.019 |
back | +0.016 |
welcome | +0.016 |
> | +0.015 |
home | +0.015 |
Neg logit contributions | |
yles | -0.019 |
cases | -0.018 |
yle | -0.017 |
ls | -0.017 |
salon | -0.017 |
Token | until |
Token ID | 1566 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
age | +0.027 |
back | +0.022 |
> | +0.022 |
welcome | +0.022 |
home | +0.021 |
Neg logit contributions | |
yles | -0.032 |
cases | -0.032 |
ls | -0.030 |
yle | -0.030 |
salon | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
cases | +0.045 |
yles | +0.041 |
outing | +0.041 |
yle | +0.040 |
ls | +0.038 |
Neg logit contributions | |
back | -0.046 |
home | -0.045 |
age | -0.043 |
right | -0.042 |
across | -0.042 |
Token | formerly |
Token ID | 15734 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
age | +0.023 |
> | +0.019 |
Follow | +0.018 |
back | +0.018 |
welcome | +0.018 |
Neg logit contributions | |
yles | -0.024 |
cases | -0.024 |
ls | -0.022 |
yle | -0.022 |
salon | -0.022 |
Token | color |
Token ID | 3124 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
age | +0.245 |
Follow | +0.214 |
> | +0.212 |
amed | +0.198 |
gy | +0.197 |
Neg logit contributions | |
cases | -0.173 |
spill | -0.167 |
yles | -0.166 |
hairc | -0.164 |
salon | -0.163 |
Token | less |
Token ID | 1203 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
yles | +0.048 |
cases | +0.043 |
yle | +0.042 |
salon | +0.041 |
ls | +0.041 |
Neg logit contributions | |
age | -0.040 |
back | -0.036 |
home | -0.033 |
est | -0.033 |
right | -0.032 |
Token | walls |
Token ID | 7714 |
Feature activation | -6.08e-03 |
Pos logit contributions | |
yles | +0.020 |
cases | +0.020 |
ls | +0.018 |
yle | +0.018 |
salon | +0.018 |
Neg logit contributions | |
age | -0.016 |
back | -0.013 |
> | -0.013 |
welcome | -0.013 |
home | -0.012 |
Token | seemed |
Token ID | 3947 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
age | +0.008 |
back | +0.007 |
home | +0.007 |
right | +0.006 |
est | +0.006 |
Neg logit contributions | |
yles | -0.013 |
cases | -0.012 |
yle | -0.012 |
ls | -0.012 |
salon | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
age | +0.014 |
back | +0.012 |
welcome | +0.012 |
home | +0.011 |
> | +0.011 |
Neg logit contributions | |
yles | -0.021 |
cases | -0.020 |
yle | -0.019 |
ls | -0.019 |
salon | -0.019 |
Token | replied |
Token ID | 8712 |
Feature activation | -9.48e-03 |
Pos logit contributions | |
age | +0.018 |
back | +0.016 |
right | +0.015 |
> | +0.015 |
home | +0.015 |
Neg logit contributions | |
yles | -0.016 |
cases | -0.014 |
yle | -0.014 |
ls | -0.014 |
ries | -0.013 |
Token | with |
Token ID | 351 |
Feature activation | +4.25e-03 |
Pos logit contributions | |
age | +0.016 |
ney | +0.013 |
> | +0.013 |
Follow | +0.012 |
welcome | +0.012 |
Neg logit contributions | |
cases | -0.017 |
ls | -0.016 |
yles | -0.016 |
yle | -0.015 |
outing | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -3.06e-03 |
Pos logit contributions | |
yles | +0.008 |
cases | +0.008 |
ls | +0.008 |
yle | +0.008 |
spill | +0.008 |
Neg logit contributions | |
age | -0.006 |
ney | -0.005 |
gy | -0.005 |
> | -0.005 |
Follow | -0.004 |
Token | gentle |
Token ID | 10296 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
age | +0.006 |
> | +0.005 |
back | +0.005 |
welcome | +0.005 |
home | +0.005 |
Neg logit contributions | |
yles | -0.005 |
cases | -0.005 |
ls | -0.004 |
yle | -0.004 |
salon | -0.004 |
Token | ' |
Token ID | 705 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
cases | +0.018 |
yle | +0.018 |
yles | +0.018 |
spill | +0.017 |
hairc | +0.017 |
Neg logit contributions | |
age | -0.028 |
> | -0.026 |
Follow | -0.025 |
back | -0.024 |
amed | -0.024 |
Token | yip |
Token ID | 39666 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
cases | +0.045 |
yles | +0.042 |
ls | +0.041 |
salon | +0.040 |
outing | +0.039 |
Neg logit contributions | |
age | -0.037 |
back | -0.029 |
welcome | -0.029 |
est | -0.028 |
Follow | -0.028 |
Token | '. |
Token ID | 4458 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
age | +0.159 |
> | +0.125 |
back | +0.123 |
home | +0.119 |
Follow | +0.118 |
Neg logit contributions | |
cases | -0.273 |
yles | -0.272 |
yle | -0.263 |
ls | -0.261 |
salon | -0.255 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
age | +0.045 |
est | +0.038 |
> | +0.037 |
amed | +0.037 |
back | +0.036 |
Neg logit contributions | |
cases | -0.055 |
yles | -0.054 |
ls | -0.051 |
yle | -0.051 |
salon | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
age | +0.022 |
est | +0.021 |
effect | +0.019 |
welcome | +0.019 |
advantage | +0.019 |
Neg logit contributions | |
yles | -0.021 |
cases | -0.021 |
ls | -0.021 |
yle | -0.019 |
l | -0.019 |
Token | The |
Token ID | 464 |
Feature activation | +3.83e-03 |
Pos logit contributions | |
age | +0.023 |
est | +0.021 |
welcome | +0.021 |
home | +0.021 |
back | +0.020 |
Neg logit contributions | |
cases | -0.021 |
yles | -0.020 |
salon | -0.020 |
ls | -0.019 |
yle | -0.019 |
Token | little |
Token ID | 1310 |
Feature activation | +4.90e-03 |
Pos logit contributions | |
yles | +0.007 |
cases | +0.006 |
ls | +0.006 |
yle | +0.006 |
salon | +0.006 |
Neg logit contributions | |
age | -0.007 |
back | -0.006 |
welcome | -0.006 |
> | -0.006 |
home | -0.006 |
Token | show |
Token ID | 905 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
age | +0.048 |
back | +0.041 |
welcome | +0.040 |
> | +0.039 |
home | +0.039 |
Neg logit contributions | |
yles | -0.045 |
cases | -0.044 |
ls | -0.041 |
yle | -0.041 |
salon | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -3.37e-03 |
Pos logit contributions | |
yles | +0.036 |
cases | +0.036 |
yle | +0.034 |
ls | +0.034 |
salon | +0.034 |
Neg logit contributions | |
age | -0.029 |
back | -0.024 |
> | -0.024 |
welcome | -0.023 |
home | -0.023 |
Token | All |
Token ID | 1439 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
age | +0.004 |
welcome | +0.003 |
> | +0.003 |
back | +0.003 |
home | +0.003 |
Neg logit contributions | |
yles | -0.008 |
cases | -0.007 |
ls | -0.007 |
yle | -0.007 |
salon | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
cases | +0.069 |
yles | +0.068 |
outing | +0.061 |
salon | +0.061 |
ls | +0.061 |
Neg logit contributions | |
age | -0.048 |
welcome | -0.043 |
back | -0.043 |
est | -0.042 |
home | -0.041 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -9.65e-03 |
Pos logit contributions | |
welcome | +0.016 |
best | +0.015 |
home | +0.015 |
right | +0.014 |
back | +0.014 |
Neg logit contributions | |
cases | -0.026 |
yles | -0.024 |
outing | -0.023 |
ls | -0.023 |
ries | -0.022 |
Token | clot |
Token ID | 5148 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
est | +0.015 |
age | +0.015 |
home | +0.015 |
back | +0.014 |
welcome | +0.014 |
Neg logit contributions | |
cases | -0.018 |
yles | -0.017 |
outing | -0.017 |
ls | -0.015 |
eling | -0.015 |
Token | he |
Token ID | 258 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
age | +0.268 |
back | +0.230 |
> | +0.228 |
welcome | +0.228 |
home | +0.225 |
Neg logit contributions | |
yles | -0.172 |
cases | -0.168 |
ls | -0.155 |
yle | -0.152 |
salon | -0.148 |
Token | es |
Token ID | 274 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
outing | +0.116 |
cases | +0.111 |
yles | +0.111 |
iqu | +0.108 |
ucker | +0.101 |
Neg logit contributions | |
age | -0.088 |
day | -0.078 |
home | -0.078 |
man | -0.077 |
est | -0.076 |
Token | were |
Token ID | 547 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
yles | +0.034 |
cases | +0.033 |
salon | +0.031 |
outing | +0.031 |
yle | +0.030 |
Neg logit contributions | |
age | -0.030 |
back | -0.027 |
est | -0.026 |
home | -0.026 |
welcome | -0.025 |
Token | marching |
Token ID | 26409 |
Feature activation | -7.82e-03 |
Pos logit contributions | |
cases | +0.060 |
yles | +0.060 |
ls | +0.057 |
yle | +0.055 |
salon | +0.055 |
Neg logit contributions | |
age | -0.036 |
back | -0.031 |
home | -0.030 |
welcome | -0.029 |
right | -0.029 |
Token | down |
Token ID | 866 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
age | +0.012 |
> | +0.009 |
welcome | +0.009 |
Follow | +0.009 |
ney | +0.009 |
Neg logit contributions | |
cases | -0.015 |
yles | -0.015 |
yle | -0.014 |
ls | -0.014 |
salon | -0.013 |
Token | You |
Token ID | 1639 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
cases | +0.034 |
yles | +0.034 |
ls | +0.032 |
ries | +0.030 |
salon | +0.030 |
Neg logit contributions | |
age | -0.033 |
right | -0.027 |
back | -0.027 |
> | -0.026 |
Follow | -0.026 |
Token | are |
Token ID | 389 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
age | +0.027 |
welcome | +0.023 |
back | +0.023 |
right | +0.022 |
home | +0.021 |
Neg logit contributions | |
yles | -0.030 |
cases | -0.028 |
salon | -0.027 |
yle | -0.026 |
ls | -0.026 |
Token | under |
Token ID | 739 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
yles | +0.042 |
cases | +0.041 |
ls | +0.040 |
wra | +0.040 |
yle | +0.040 |
Neg logit contributions | |
age | -0.043 |
est | -0.035 |
ney | -0.033 |
gy | -0.032 |
> | -0.032 |
Token | arrest |
Token ID | 3251 |
Feature activation | +8.39e-02 |
Pos logit contributions | |
age | +0.033 |
back | +0.030 |
home | +0.030 |
> | +0.030 |
welcome | +0.029 |
Neg logit contributions | |
yles | -0.022 |
cases | -0.022 |
outing | -0.020 |
yle | -0.020 |
ls | -0.019 |
Token | for |
Token ID | 329 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
cases | +0.143 |
ls | +0.143 |
spill | +0.133 |
yles | +0.132 |
hairc | +0.131 |
Neg logit contributions | |
age | -0.132 |
ney | -0.111 |
amed | -0.110 |
Follow | -0.109 |
sy | -0.108 |
Token | harassing |
Token ID | 34110 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
age | +0.024 |
back | +0.019 |
> | +0.018 |
welcome | +0.018 |
est | +0.018 |
Neg logit contributions | |
yles | -0.038 |
cases | -0.038 |
ls | -0.036 |
yle | -0.036 |
salon | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -3.45e-04 |
Pos logit contributions | |
age | +0.194 |
> | +0.157 |
back | +0.154 |
Follow | +0.152 |
welcome | +0.151 |
Neg logit contributions | |
cases | -0.218 |
yles | -0.214 |
ls | -0.204 |
yle | -0.202 |
hairc | -0.199 |
Token | stealing |
Token ID | 16568 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
age | +0.001 |
back | +0.001 |
welcome | +0.001 |
> | +0.001 |
home | +0.000 |
Neg logit contributions | |
yles | -0.001 |
cases | -0.001 |
ls | -0.001 |
yle | -0.001 |
salon | -0.001 |
Token | from |
Token ID | 422 |
Feature activation | -1.14e-03 |
Pos logit contributions | |
age | +0.016 |
back | +0.014 |
welcome | +0.013 |
> | +0.013 |
home | +0.013 |
Neg logit contributions | |
yles | -0.024 |
cases | -0.024 |
yle | -0.023 |
ls | -0.022 |
salon | -0.022 |
Token | these |
Token ID | 777 |
Feature activation | +4.27e-03 |
Pos logit contributions | |
age | +0.002 |
back | +0.001 |
home | +0.001 |
welcome | +0.001 |
> | +0.001 |
Neg logit contributions | |
cases | -0.002 |
yles | -0.002 |
ls | -0.002 |
yle | -0.002 |
salon | -0.002 |
Token | children |
Token ID | 1751 |
Feature activation | +4.25e-03 |
Pos logit contributions | |
yles | +0.008 |
cases | +0.007 |
yle | +0.007 |
outing | +0.007 |
ls | +0.006 |
Neg logit contributions | |
age | -0.007 |
back | -0.007 |
home | -0.006 |
welcome | -0.006 |
right | -0.006 |
Token | stop |
Token ID | 2245 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
yles | +0.025 |
cases | +0.023 |
yle | +0.023 |
ls | +0.022 |
ries | +0.022 |
Neg logit contributions | |
home | -0.013 |
back | -0.012 |
age | -0.012 |
right | -0.011 |
> | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e-04 |
Pos logit contributions | |
yles | +0.031 |
cases | +0.030 |
yle | +0.028 |
ls | +0.028 |
salon | +0.028 |
Neg logit contributions | |
age | -0.016 |
back | -0.015 |
right | -0.014 |
home | -0.014 |
across | -0.013 |
Token | Anna |
Token ID | 11735 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
age | +0.000 |
back | +0.000 |
> | +0.000 |
welcome | +0.000 |
home | +0.000 |
Neg logit contributions | |
yles | -0.000 |
cases | -0.000 |
ls | -0.000 |
yle | -0.000 |
salon | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -5.59e-03 |
Pos logit contributions | |
age | +0.020 |
back | +0.017 |
right | +0.015 |
across | +0.014 |
home | +0.014 |
Neg logit contributions | |
yles | -0.049 |
ries | -0.046 |
cases | -0.046 |
outing | -0.045 |
yle | -0.045 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
back | +0.009 |
right | +0.008 |
age | +0.008 |
home | +0.008 |
welcome | +0.008 |
Neg logit contributions | |
cases | -0.010 |
yles | -0.010 |
outing | -0.009 |
yle | -0.009 |
ls | -0.009 |
Token | unb |
Token ID | 22619 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
yles | +0.040 |
ries | +0.038 |
ocol | +0.037 |
ls | +0.036 |
salon | +0.035 |
Neg logit contributions | |
back | -0.038 |
age | -0.035 |
right | -0.035 |
across | -0.032 |
home | -0.031 |
Token | uck |
Token ID | 1347 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
age | +0.196 |
welcome | +0.162 |
back | +0.161 |
> | +0.161 |
home | +0.157 |
Neg logit contributions | |
yles | -0.219 |
cases | -0.217 |
ls | -0.202 |
yle | -0.202 |
salon | -0.197 |
Token | led |
Token ID | 992 |
Feature activation | -9.61e-03 |
Pos logit contributions | |
age | +0.092 |
back | +0.090 |
right | +0.081 |
amed | +0.081 |
est | +0.080 |
Neg logit contributions | |
yles | -0.105 |
salon | -0.097 |
cases | -0.096 |
yle | -0.095 |
outing | -0.093 |
Token | and |
Token ID | 290 |
Feature activation | -6.19e-03 |
Pos logit contributions | |
age | +0.015 |
> | +0.012 |
welcome | +0.012 |
Follow | +0.011 |
amed | +0.011 |
Neg logit contributions | |
yles | -0.018 |
cases | -0.018 |
ls | -0.017 |
yle | -0.017 |
hairc | -0.016 |
Token | got |
Token ID | 1392 |
Feature activation | -6.06e-03 |
Pos logit contributions | |
back | +0.011 |
right | +0.010 |
age | +0.009 |
welcome | +0.009 |
home | +0.009 |
Neg logit contributions | |
yles | -0.011 |
cases | -0.011 |
outing | -0.010 |
ls | -0.010 |
ge | -0.010 |
Token | off |
Token ID | 572 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
age | +0.006 |
back | +0.005 |
> | +0.004 |
welcome | +0.004 |
home | +0.004 |
Neg logit contributions | |
yles | -0.015 |
cases | -0.014 |
ls | -0.014 |
yle | -0.014 |
salon | -0.014 |
Token | - |
Token ID | 532 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
age | +0.016 |
back | +0.013 |
> | +0.012 |
welcome | +0.012 |
home | +0.012 |
Neg logit contributions | |
yles | -0.022 |
cases | -0.022 |
ls | -0.021 |
yle | -0.021 |
salon | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -1.80e-03 |
Pos logit contributions | |
age | +0.021 |
back | +0.017 |
welcome | +0.017 |
home | +0.016 |
right | +0.016 |
Neg logit contributions | |
yles | -0.026 |
cases | -0.026 |
ls | -0.024 |
yle | -0.024 |
salon | -0.024 |
Token | shirt |
Token ID | 10147 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
age | +0.003 |
> | +0.003 |
back | +0.003 |
welcome | +0.003 |
est | +0.003 |
Neg logit contributions | |
yles | -0.003 |
cases | -0.003 |
salon | -0.003 |
ls | -0.003 |
yle | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -3.99e-03 |
Pos logit contributions | |
age | +0.040 |
> | +0.032 |
back | +0.032 |
welcome | +0.032 |
home | +0.031 |
Neg logit contributions | |
cases | -0.050 |
yles | -0.050 |
ls | -0.047 |
yle | -0.047 |
salon | -0.046 |
Token | pants |
Token ID | 12581 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
age | +0.006 |
back | +0.005 |
welcome | +0.004 |
home | +0.004 |
right | +0.004 |
Neg logit contributions | |
yles | -0.008 |
cases | -0.008 |
ls | -0.008 |
outing | -0.008 |
yle | -0.008 |
Token | combo |
Token ID | 14831 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
age | +0.025 |
back | +0.021 |
right | +0.019 |
home | +0.019 |
est | +0.019 |
Neg logit contributions | |
yles | -0.039 |
cases | -0.036 |
yle | -0.035 |
ls | -0.035 |
outing | -0.035 |
Token | - |
Token ID | 532 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
age | +0.179 |
> | +0.145 |
welcome | +0.143 |
back | +0.142 |
Follow | +0.138 |
Neg logit contributions | |
cases | -0.226 |
yles | -0.225 |
yle | -0.212 |
ls | -0.209 |
salon | -0.206 |
Token | and |
Token ID | 290 |
Feature activation | -2.62e-03 |
Pos logit contributions | |
age | +0.020 |
back | +0.018 |
right | +0.018 |
welcome | +0.017 |
home | +0.017 |
Neg logit contributions | |
yles | -0.019 |
cases | -0.017 |
ls | -0.017 |
yle | -0.017 |
ries | -0.016 |
Token | brushed |
Token ID | 31782 |
Feature activation | +2.04e-03 |
Pos logit contributions | |
age | +0.005 |
back | +0.004 |
welcome | +0.004 |
home | +0.004 |
> | +0.004 |
Neg logit contributions | |
yles | -0.004 |
cases | -0.004 |
yle | -0.004 |
ls | -0.004 |
salon | -0.004 |
Token | his |
Token ID | 465 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
yles | +0.004 |
cases | +0.004 |
yle | +0.004 |
ls | +0.004 |
salon | +0.004 |
Neg logit contributions | |
age | -0.003 |
back | -0.002 |
est | -0.002 |
home | -0.002 |
right | -0.002 |
Token | hair |
Token ID | 4190 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
yles | +0.042 |
cases | +0.040 |
ls | +0.038 |
yle | +0.037 |
salon | +0.037 |
Neg logit contributions | |
age | -0.046 |
back | -0.041 |
home | -0.039 |
> | -0.038 |
welcome | -0.038 |
Token | her |
Token ID | 607 |
Feature activation | -6.11e-03 |
Pos logit contributions | |
yles | +0.010 |
cases | +0.010 |
yle | +0.009 |
salon | +0.009 |
outing | +0.009 |
Neg logit contributions | |
age | -0.014 |
back | -0.014 |
home | -0.013 |
right | -0.013 |
welcome | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
age | +0.009 |
back | +0.008 |
home | +0.008 |
right | +0.008 |
> | +0.008 |
Neg logit contributions | |
yles | -0.012 |
cases | -0.012 |
yle | -0.011 |
ls | -0.011 |
salon | -0.010 |
Token | pan |
Token ID | 3425 |
Feature activation | -1.83e-03 |
Pos logit contributions | |
age | +0.028 |
back | +0.025 |
welcome | +0.024 |
right | +0.024 |
home | +0.024 |
Neg logit contributions | |
yles | -0.024 |
cases | -0.023 |
yle | -0.022 |
ls | -0.021 |
salon | -0.020 |
Token | with |
Token ID | 351 |
Feature activation | +4.63e-03 |
Pos logit contributions | |
age | +0.002 |
back | +0.002 |
right | +0.002 |
home | +0.002 |
est | +0.002 |
Neg logit contributions | |
yles | -0.004 |
cases | -0.004 |
yle | -0.004 |
salon | -0.004 |
ls | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
cases | +0.010 |
yles | +0.010 |
yle | +0.009 |
ls | +0.009 |
salon | +0.009 |
Neg logit contributions | |
back | -0.006 |
age | -0.006 |
home | -0.006 |
right | -0.005 |
welcome | -0.005 |
Token | unb |
Token ID | 22619 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
age | +0.029 |
back | +0.025 |
welcome | +0.025 |
> | +0.025 |
home | +0.024 |
Neg logit contributions | |
yles | -0.024 |
cases | -0.023 |
ls | -0.021 |
yle | -0.021 |
salon | -0.021 |
Token | aked |
Token ID | 4335 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
age | +0.206 |
back | +0.172 |
> | +0.168 |
welcome | +0.167 |
home | +0.166 |
Neg logit contributions | |
yles | -0.202 |
cases | -0.198 |
ls | -0.184 |
yle | -0.183 |
salon | -0.180 |
Token | cake |
Token ID | 12187 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
age | +0.073 |
back | +0.064 |
right | +0.060 |
home | +0.059 |
est | +0.058 |
Neg logit contributions | |
yles | -0.114 |
cases | -0.106 |
yle | -0.103 |
ls | -0.101 |
salon | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e-03 |
Pos logit contributions | |
back | +0.064 |
age | +0.064 |
right | +0.056 |
home | +0.054 |
across | +0.048 |
Neg logit contributions | |
yles | -0.152 |
yle | -0.139 |
eling | -0.133 |
cases | -0.132 |
Get | -0.129 |
Token | Mom |
Token ID | 11254 |
Feature activation | +2.21e-03 |
Pos logit contributions | |
yles | +0.004 |
cases | +0.004 |
yle | +0.003 |
eling | +0.003 |
ls | +0.003 |
Neg logit contributions | |
age | -0.002 |
back | -0.002 |
welcome | -0.002 |
right | -0.002 |
home | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +6.58e-03 |
Pos logit contributions | |
yles | +0.004 |
yle | +0.004 |
cases | +0.004 |
hairc | +0.004 |
ls | +0.004 |
Neg logit contributions | |
age | -0.003 |
back | -0.003 |
right | -0.003 |
man | -0.003 |
amed | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
yles | +0.005 |
cases | +0.005 |
ls | +0.004 |
yle | +0.004 |
salon | +0.004 |
Neg logit contributions | |
age | -0.003 |
back | -0.003 |
> | -0.003 |
welcome | -0.003 |
home | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
age | +0.017 |
est | +0.013 |
back | +0.013 |
welcome | +0.013 |
> | +0.013 |
Neg logit contributions | |
yles | -0.027 |
cases | -0.026 |
ls | -0.025 |
yle | -0.025 |
salon | -0.025 |
Token | So |
Token ID | 2396 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
age | +0.022 |
> | +0.018 |
back | +0.018 |
welcome | +0.018 |
right | +0.018 |
Neg logit contributions | |
yles | -0.023 |
cases | -0.023 |
ls | -0.021 |
yle | -0.021 |
ries | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -4.59e-03 |
Pos logit contributions | |
age | +0.051 |
back | +0.046 |
home | +0.045 |
welcome | +0.045 |
right | +0.044 |
Neg logit contributions | |
yles | -0.089 |
cases | -0.086 |
yle | -0.080 |
outing | -0.079 |
salon | -0.079 |
Token | with |
Token ID | 351 |
Feature activation | +2.74e-03 |
Pos logit contributions | |
right | +0.007 |
back | +0.007 |
home | +0.007 |
welcome | +0.007 |
age | +0.007 |
Neg logit contributions | |
yles | -0.008 |
cases | -0.008 |
outing | -0.007 |
ls | -0.007 |
yle | -0.007 |
Token | artificial |
Token ID | 11666 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
yles | +0.006 |
cases | +0.006 |
yle | +0.005 |
ls | +0.005 |
salon | +0.005 |
Neg logit contributions | |
age | -0.003 |
back | -0.003 |
home | -0.003 |
welcome | -0.003 |
> | -0.003 |
Token | so |
Token ID | 523 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
age | +0.188 |
back | +0.156 |
welcome | +0.154 |
> | +0.153 |
home | +0.151 |
Neg logit contributions | |
yles | -0.215 |
cases | -0.211 |
ls | -0.196 |
yle | -0.196 |
salon | -0.194 |
Token | aps |
Token ID | 1686 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
yles | +0.035 |
cases | +0.034 |
yle | +0.032 |
salon | +0.031 |
ries | +0.031 |
Neg logit contributions | |
age | -0.022 |
welcome | -0.019 |
back | -0.018 |
right | -0.018 |
home | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -5.38e-03 |
Pos logit contributions | |
age | +0.053 |
back | +0.046 |
welcome | +0.044 |
est | +0.044 |
home | +0.043 |
Neg logit contributions | |
yles | -0.076 |
cases | -0.073 |
yle | -0.068 |
salon | -0.068 |
ls | -0.066 |
Token | they |
Token ID | 484 |
Feature activation | -8.29e-03 |
Pos logit contributions | |
right | +0.009 |
back | +0.009 |
home | +0.009 |
welcome | +0.009 |
best | +0.008 |
Neg logit contributions | |
yles | -0.009 |
cases | -0.009 |
outing | -0.008 |
ls | -0.008 |
yle | -0.008 |
Token | made |
Token ID | 925 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
age | +0.013 |
back | +0.012 |
home | +0.011 |
amed | +0.011 |
> | +0.011 |
Neg logit contributions | |
yles | -0.015 |
cases | -0.015 |
salon | -0.014 |
ls | -0.014 |
ries | -0.014 |
Token | then |
Token ID | 788 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
age | +0.002 |
est | +0.002 |
welcome | +0.002 |
> | +0.002 |
Follow | +0.002 |
Neg logit contributions | |
yles | -0.002 |
cases | -0.002 |
ls | -0.002 |
yle | -0.002 |
salon | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | -3.24e-03 |
Pos logit contributions | |
yles | +0.058 |
cases | +0.057 |
ls | +0.056 |
yle | +0.054 |
spill | +0.052 |
Neg logit contributions | |
age | -0.051 |
> | -0.042 |
gy | -0.042 |
est | -0.041 |
back | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | -1.84e-03 |
Pos logit contributions | |
age | +0.005 |
> | +0.004 |
Follow | +0.004 |
amed | +0.004 |
welcome | +0.004 |
Neg logit contributions | |
cases | -0.006 |
yles | -0.006 |
ls | -0.006 |
yle | -0.006 |
salon | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
age | +0.003 |
back | +0.003 |
> | +0.003 |
welcome | +0.003 |
home | +0.003 |
Neg logit contributions | |
yles | -0.003 |
cases | -0.003 |
ls | -0.003 |
yle | -0.003 |
salon | -0.003 |
Token | SPL |
Token ID | 46341 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
age | +0.035 |
> | +0.028 |
Follow | +0.028 |
back | +0.028 |
welcome | +0.027 |
Neg logit contributions | |
yles | -0.029 |
cases | -0.029 |
ls | -0.027 |
yle | -0.027 |
salon | -0.027 |
Token | ASH |
Token ID | 11211 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ries | +0.052 |
yles | +0.050 |
outing | +0.048 |
yle | +0.046 |
hairc | +0.046 |
Neg logit contributions | |
age | -0.031 |
welcome | -0.028 |
back | -0.027 |
Follow | -0.026 |
home | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
age | +0.183 |
> | +0.154 |
welcome | +0.151 |
back | +0.150 |
Follow | +0.148 |
Neg logit contributions | |
cases | -0.212 |
yles | -0.210 |
yle | -0.194 |
ls | -0.194 |
salon | -0.192 |
Token | always |
Token ID | 1464 |
Feature activation | -7.70e-03 |
Pos logit contributions | |
yles | +0.011 |
cases | +0.010 |
spill | +0.010 |
ls | +0.010 |
salon | +0.010 |
Neg logit contributions | |
age | -0.009 |
Follow | -0.008 |
est | -0.007 |
> | -0.007 |
welcome | -0.007 |
Token | under |
Token ID | 739 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
age | +0.013 |
Follow | +0.011 |
> | +0.010 |
gy | +0.009 |
gen | +0.009 |
Neg logit contributions | |
yles | -0.014 |
cases | -0.013 |
spill | -0.013 |
salon | -0.012 |
ries | -0.012 |
Token | control |
Token ID | 1630 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
age | +0.029 |
back | +0.026 |
home | +0.025 |
welcome | +0.024 |
> | +0.024 |
Neg logit contributions | |
yles | -0.035 |
cases | -0.035 |
yle | -0.033 |
ls | -0.032 |
salon | -0.032 |
Token | ! |
Token ID | 0 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
age | +0.014 |
back | +0.012 |
home | +0.012 |
est | +0.012 |
welcome | +0.011 |
Neg logit contributions | |
yles | -0.022 |
cases | -0.021 |
yle | -0.020 |
ls | -0.020 |
salon | -0.019 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.95e-03 |
Pos logit contributions | |
age | +0.001 |
back | +0.000 |
home | +0.000 |
> | +0.000 |
right | +0.000 |
Neg logit contributions | |
yles | -0.001 |
cases | -0.001 |
ls | -0.001 |
ries | -0.001 |
yle | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -6.93e-04 |
Pos logit contributions | |
cases | +0.005 |
yles | +0.005 |
ls | +0.005 |
yle | +0.005 |
salon | +0.005 |
Neg logit contributions | |
age | -0.005 |
> | -0.004 |
welcome | -0.004 |
Follow | -0.004 |
amed | -0.004 |
Token | said |
Token ID | 531 |
Feature activation | +2.50e-03 |
Pos logit contributions | |
age | +0.001 |
back | +0.001 |
home | +0.001 |
welcome | +0.001 |
right | +0.001 |
Neg logit contributions | |
yles | -0.001 |
cases | -0.001 |
outing | -0.001 |
ries | -0.001 |
ls | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.42e-03 |
Pos logit contributions | |
yles | +0.005 |
cases | +0.005 |
ls | +0.005 |
yle | +0.005 |
salon | +0.004 |
Neg logit contributions | |
age | -0.004 |
> | -0.003 |
back | -0.003 |
welcome | -0.003 |
home | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
yles | +0.003 |
cases | +0.003 |
ls | +0.003 |
yle | +0.003 |
salon | +0.003 |
Neg logit contributions | |
age | -0.002 |
back | -0.002 |
> | -0.002 |
welcome | -0.002 |
home | -0.002 |
Token | Church |
Token ID | 46686 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
yles | +0.028 |
cases | +0.028 |
ls | +0.026 |
yle | +0.026 |
salon | +0.025 |
Neg logit contributions | |
age | -0.029 |
back | -0.024 |
welcome | -0.024 |
> | -0.024 |
est | -0.024 |
Token | is |
Token ID | 318 |
Feature activation | +1.73e-03 |
Pos logit contributions | |
age | +0.176 |
> | +0.140 |
back | +0.138 |
welcome | +0.136 |
Follow | +0.135 |
Neg logit contributions | |
cases | -0.220 |
yles | -0.219 |
ls | -0.205 |
yle | -0.202 |
salon | -0.202 |
Token | so |
Token ID | 523 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
yles | +0.003 |
cases | +0.003 |
ls | +0.003 |
salon | +0.003 |
yle | +0.003 |
Neg logit contributions | |
age | -0.003 |
> | -0.002 |
Follow | -0.002 |
est | -0.002 |
back | -0.002 |
Token | nice |
Token ID | 3621 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
yles | +0.047 |
yle | +0.044 |
cases | +0.044 |
ries | +0.043 |
salon | +0.043 |
Neg logit contributions | |
age | -0.024 |
welcome | -0.022 |
back | -0.021 |
right | -0.020 |
home | -0.020 |
Token | mom |
Token ID | 1995 |
Feature activation | -8.06e-03 |
Pos logit contributions | |
age | +0.034 |
> | +0.027 |
amed | +0.026 |
back | +0.026 |
Follow | +0.026 |
Neg logit contributions | |
cases | -0.045 |
yles | -0.045 |
ls | -0.042 |
salon | -0.041 |
yle | -0.041 |
Token | my |
Token ID | 1820 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
age | +0.008 |
> | +0.006 |
Follow | +0.006 |
amed | +0.005 |
back | +0.005 |
Neg logit contributions | |
yles | -0.019 |
cases | -0.019 |
salon | -0.018 |
yle | -0.018 |
ls | -0.018 |
Token | make |
Token ID | 787 |
Feature activation | -5.96e-03 |
Pos logit contributions | |
cases | +0.024 |
yles | +0.023 |
ls | +0.022 |
yle | +0.021 |
outing | +0.021 |
Neg logit contributions | |
age | -0.018 |
back | -0.015 |
welcome | -0.015 |
home | -0.015 |
right | -0.014 |
Token | one |
Token ID | 530 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
age | +0.010 |
back | +0.008 |
welcome | +0.008 |
home | +0.008 |
> | +0.008 |
Neg logit contributions | |
yles | -0.011 |
cases | -0.011 |
ls | -0.010 |
yle | -0.010 |
salon | -0.010 |
Token | too |
Token ID | 1165 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
age | +0.028 |
> | +0.022 |
gy | +0.022 |
amed | +0.021 |
Follow | +0.021 |
Neg logit contributions | |
yles | -0.028 |
ls | -0.027 |
cases | -0.026 |
yle | -0.026 |
spill | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +1.70e-03 |
Pos logit contributions | |
yles | +0.078 |
cases | +0.074 |
salon | +0.072 |
yle | +0.071 |
ls | +0.070 |
Neg logit contributions | |
age | -0.035 |
back | -0.034 |
right | -0.033 |
home | -0.032 |
welcome | -0.031 |
Token | He |
Token ID | 679 |
Feature activation | -3.32e-03 |
Pos logit contributions | |
yles | +0.004 |
cases | +0.004 |
yle | +0.004 |
ls | +0.004 |
salon | +0.004 |
Neg logit contributions | |
age | -0.002 |
back | -0.002 |
welcome | -0.002 |
> | -0.002 |
home | -0.002 |
Token | dips |
Token ID | 48904 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
age | +0.006 |
back | +0.005 |
right | +0.005 |
> | +0.005 |
welcome | +0.005 |
Neg logit contributions | |
yles | -0.005 |
cases | -0.005 |
yle | -0.005 |
outing | -0.005 |
ries | -0.004 |
Token | his |
Token ID | 465 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
age | +0.189 |
back | +0.169 |
home | +0.162 |
welcome | +0.162 |
right | +0.160 |
Neg logit contributions | |
cases | -0.207 |
yles | -0.203 |
ls | -0.185 |
salon | -0.184 |
yle | -0.182 |
Token | brush |
Token ID | 14093 |
Feature activation | +7.72e-03 |
Pos logit contributions | |
yles | +0.028 |
cases | +0.027 |
ls | +0.026 |
yle | +0.025 |
salon | +0.025 |
Neg logit contributions | |
age | -0.036 |
> | -0.030 |
welcome | -0.030 |
Follow | -0.029 |
back | -0.029 |
Token | in |
Token ID | 287 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
cases | +0.015 |
yles | +0.015 |
ls | +0.014 |
yle | +0.014 |
salon | +0.014 |
Neg logit contributions | |
age | -0.011 |
welcome | -0.009 |
> | -0.009 |
Follow | -0.009 |
est | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
age | +0.023 |
back | +0.022 |
right | +0.021 |
home | +0.021 |
welcome | +0.020 |
Neg logit contributions | |
cases | -0.037 |
yles | -0.035 |
ls | -0.033 |
salon | -0.032 |
yle | -0.032 |
Token | red |
Token ID | 2266 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
age | +0.032 |
gy | +0.028 |
Follow | +0.027 |
> | +0.026 |
wood | +0.026 |
Neg logit contributions | |
salon | -0.025 |
spill | -0.025 |
brushes | -0.024 |
ls | -0.022 |
wra | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
age | +0.002 |
> | +0.002 |
welcome | +0.002 |
back | +0.002 |
Follow | +0.002 |
Neg logit contributions | |
yles | -0.003 |
cases | -0.003 |
ls | -0.003 |
yle | -0.003 |
salon | -0.003 |
Token | It |
Token ID | 632 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
age | +0.017 |
back | +0.014 |
> | +0.014 |
est | +0.014 |
home | +0.014 |
Neg logit contributions | |
yles | -0.022 |
cases | -0.022 |
yle | -0.020 |
ls | -0.020 |
salon | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | +6.77e-03 |
Pos logit contributions | |
yles | +0.029 |
cases | +0.027 |
yle | +0.026 |
outing | +0.025 |
ls | +0.025 |
Neg logit contributions | |
age | -0.028 |
back | -0.024 |
right | -0.023 |
> | -0.022 |
est | -0.022 |
Token | poison |
Token ID | 8764 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
yles | +0.013 |
cases | +0.013 |
ls | +0.012 |
yle | +0.012 |
salon | +0.012 |
Neg logit contributions | |
age | -0.010 |
back | -0.008 |
> | -0.008 |
welcome | -0.008 |
est | -0.008 |
Token | he |
Token ID | 339 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
cases | +0.025 |
yles | +0.025 |
ls | +0.024 |
spill | +0.023 |
yle | +0.023 |
Neg logit contributions | |
age | -0.021 |
> | -0.017 |
welcome | -0.017 |
Follow | -0.017 |
home | -0.016 |
Token | ml |
Token ID | 4029 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
yles | +0.050 |
cases | +0.048 |
yle | +0.045 |
salon | +0.045 |
ries | +0.043 |
Neg logit contributions | |
age | -0.050 |
back | -0.042 |
> | -0.041 |
welcome | -0.041 |
right | -0.040 |
Token | ock |
Token ID | 735 |
Feature activation | +4.45e-03 |
Pos logit contributions | |
age | +0.197 |
back | +0.167 |
welcome | +0.164 |
> | +0.164 |
Follow | +0.163 |
Neg logit contributions | |
cases | -0.189 |
yles | -0.189 |
yle | -0.176 |
ls | -0.175 |
salon | -0.174 |
Token | . |
Token ID | 13 |
Feature activation | -3.22e-03 |
Pos logit contributions | |
yles | +0.009 |
cases | +0.008 |
yle | +0.008 |
salon | +0.008 |
ls | +0.008 |
Neg logit contributions | |
age | -0.007 |
back | -0.006 |
> | -0.005 |
home | -0.005 |
est | -0.005 |
Token | It |
Token ID | 632 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
age | +0.005 |
back | +0.004 |
> | +0.004 |
est | +0.004 |
home | +0.004 |
Neg logit contributions | |
yles | -0.006 |
cases | -0.006 |
yle | -0.006 |
ls | -0.006 |
salon | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +6.92e-03 |
Pos logit contributions | |
yles | +0.032 |
cases | +0.031 |
yle | +0.029 |
salon | +0.029 |
outing | +0.028 |
Neg logit contributions | |
age | -0.029 |
back | -0.024 |
right | -0.023 |
> | -0.023 |
gy | -0.023 |
Token | very |
Token ID | 845 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
yles | +0.014 |
cases | +0.013 |
yle | +0.013 |
ls | +0.012 |
salon | +0.012 |
Neg logit contributions | |
age | -0.010 |
back | -0.009 |
welcome | -0.008 |
> | -0.008 |
home | -0.008 |
Token | up |
Token ID | 510 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
yles | +0.009 |
cases | +0.009 |
ls | +0.008 |
yle | +0.008 |
salon | +0.008 |
Neg logit contributions | |
age | -0.005 |
> | -0.003 |
welcome | -0.003 |
Follow | -0.003 |
back | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +2.18e-04 |
Pos logit contributions | |
yles | +0.041 |
cases | +0.041 |
yle | +0.038 |
salon | +0.037 |
outing | +0.037 |
Neg logit contributions | |
back | -0.016 |
right | -0.016 |
age | -0.015 |
home | -0.014 |
welcome | -0.013 |
Token | carrot |
Token ID | 40562 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
yles | +0.000 |
cases | +0.000 |
yle | +0.000 |
ls | +0.000 |
salon | +0.000 |
Neg logit contributions | |
age | -0.000 |
back | -0.000 |
welcome | -0.000 |
home | -0.000 |
> | -0.000 |
Token | stick |
Token ID | 4859 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
age | +0.019 |
welcome | +0.017 |
> | +0.017 |
Follow | +0.017 |
amed | +0.017 |
Neg logit contributions | |
cases | -0.019 |
ls | -0.019 |
yles | -0.019 |
spill | -0.018 |
salon | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -2.59e-03 |
Pos logit contributions | |
yles | +0.026 |
cases | +0.026 |
ls | +0.024 |
yle | +0.024 |
salon | +0.024 |
Neg logit contributions | |
age | -0.020 |
> | -0.016 |
welcome | -0.016 |
back | -0.016 |
home | -0.016 |
Token | dips |
Token ID | 48904 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
back | +0.004 |
right | +0.004 |
age | +0.004 |
welcome | +0.004 |
Follow | +0.004 |
Neg logit contributions | |
cases | -0.004 |
yles | -0.004 |
yle | -0.004 |
outing | -0.004 |
salon | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | +3.72e-03 |
Pos logit contributions | |
age | +0.228 |
back | +0.198 |
welcome | +0.195 |
> | +0.194 |
home | +0.193 |
Neg logit contributions | |
yles | -0.166 |
cases | -0.165 |
ls | -0.149 |
yle | -0.148 |
salon | -0.147 |
Token | in |
Token ID | 287 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
ls | +0.007 |
yles | +0.007 |
cases | +0.007 |
outing | +0.007 |
spill | +0.007 |
Neg logit contributions | |
age | -0.006 |
welcome | -0.004 |
> | -0.004 |
est | -0.004 |
Follow | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -6.31e-04 |
Pos logit contributions | |
age | +0.022 |
back | +0.020 |
right | +0.020 |
home | +0.020 |
welcome | +0.020 |
Neg logit contributions | |
cases | -0.035 |
yles | -0.033 |
ls | -0.031 |
salon | -0.030 |
yle | -0.030 |
Token | white |
Token ID | 2330 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
age | +0.001 |
> | +0.001 |
back | +0.001 |
welcome | +0.001 |
est | +0.001 |
Neg logit contributions | |
yles | -0.001 |
cases | -0.001 |
ls | -0.001 |
yle | -0.001 |
salon | -0.001 |
Token | sauce |
Token ID | 10746 |
Feature activation | -2.56e-03 |
Pos logit contributions | |
age | +0.043 |
Follow | +0.039 |
amed | +0.038 |
ok | +0.038 |
welcome | +0.038 |
Neg logit contributions | |
spill | -0.029 |
wra | -0.029 |
ls | -0.028 |
yles | -0.027 |
hairc | -0.027 |
Token | " |
Token ID | 366 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
yles | +0.004 |
cases | +0.004 |
yle | +0.004 |
ls | +0.004 |
salon | +0.004 |
Neg logit contributions | |
age | -0.003 |
back | -0.002 |
> | -0.002 |
welcome | -0.002 |
right | -0.002 |
Token | We |
Token ID | 1135 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
yles | +0.030 |
cases | +0.029 |
yle | +0.028 |
ls | +0.027 |
salon | +0.027 |
Neg logit contributions | |
age | -0.028 |
back | -0.023 |
home | -0.023 |
welcome | -0.023 |
> | -0.023 |
Token | are |
Token ID | 389 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
age | +0.084 |
> | +0.071 |
back | +0.071 |
home | +0.069 |
est | +0.069 |
Neg logit contributions | |
yles | -0.063 |
cases | -0.061 |
yle | -0.057 |
ls | -0.056 |
spill | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
yles | +0.040 |
ls | +0.035 |
yle | +0.034 |
typing | +0.034 |
cases | +0.034 |
Neg logit contributions | |
age | -0.056 |
est | -0.046 |
ney | -0.044 |
Follow | -0.042 |
nob | -0.041 |
Token | weapon |
Token ID | 4282 |
Feature activation | +4.15e-03 |
Pos logit contributions | |
age | +0.012 |
> | +0.009 |
Follow | +0.009 |
amed | +0.008 |
est | +0.008 |
Neg logit contributions | |
yles | -0.024 |
salon | -0.023 |
yle | -0.023 |
cases | -0.023 |
spill | -0.022 |
Token | creators |
Token ID | 16294 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
cases | +0.008 |
ls | +0.007 |
yles | +0.007 |
salon | +0.007 |
spill | +0.007 |
Neg logit contributions | |
age | -0.006 |
> | -0.005 |
amed | -0.005 |
welcome | -0.005 |
Follow | -0.005 |
Token | ! |
Token ID | 0 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
age | +0.156 |
> | +0.121 |
back | +0.120 |
welcome | +0.120 |
Follow | +0.118 |
Neg logit contributions | |
yles | -0.229 |
cases | -0.225 |
yle | -0.214 |
salon | -0.212 |
ls | -0.211 |
Token | We |
Token ID | 775 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
age | +0.022 |
home | +0.019 |
back | +0.019 |
amed | +0.019 |
> | +0.018 |
Neg logit contributions | |
yles | -0.022 |
cases | -0.021 |
yle | -0.020 |
ls | -0.019 |
Get | -0.019 |
Token | can |
Token ID | 460 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
age | +0.030 |
> | +0.025 |
back | +0.025 |
est | +0.025 |
home | +0.025 |
Neg logit contributions | |
yles | -0.024 |
cases | -0.023 |
ls | -0.022 |
yle | -0.022 |
spill | -0.021 |
Token | stop |
Token ID | 2245 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
yles | +0.019 |
cases | +0.019 |
yle | +0.018 |
ls | +0.018 |
salon | +0.018 |
Neg logit contributions | |
age | -0.018 |
> | -0.015 |
back | -0.015 |
welcome | -0.015 |
est | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
yles | +0.031 |
cases | +0.028 |
ls | +0.028 |
yle | +0.027 |
spill | +0.027 |
Neg logit contributions | |
age | -0.039 |
est | -0.032 |
welcome | -0.032 |
amed | -0.031 |
> | -0.031 |
Token | It |
Token ID | 632 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
yles | +0.018 |
cases | +0.017 |
yle | +0.017 |
ls | +0.017 |
salon | +0.016 |
Neg logit contributions | |
age | -0.008 |
welcome | -0.006 |
back | -0.006 |
right | -0.006 |
Follow | -0.006 |
Token | is |
Token ID | 318 |
Feature activation | +3.85e-03 |
Pos logit contributions | |
yles | +0.041 |
cases | +0.040 |
yle | +0.039 |
outing | +0.036 |
ls | +0.036 |
Neg logit contributions | |
age | -0.032 |
back | -0.028 |
right | -0.026 |
welcome | -0.025 |
est | -0.025 |
Token | blue |
Token ID | 4171 |
Feature activation | -7.80e-03 |
Pos logit contributions | |
yles | +0.007 |
cases | +0.007 |
ls | +0.007 |
yle | +0.007 |
salon | +0.007 |
Neg logit contributions | |
age | -0.006 |
back | -0.005 |
> | -0.005 |
welcome | -0.005 |
home | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +7.35e-03 |
Pos logit contributions | |
age | +0.013 |
> | +0.011 |
Follow | +0.010 |
welcome | +0.010 |
back | +0.010 |
Neg logit contributions | |
cases | -0.014 |
yles | -0.014 |
ls | -0.013 |
salon | -0.013 |
ries | -0.013 |
Token | He |
Token ID | 679 |
Feature activation | +4.35e-03 |
Pos logit contributions | |
yles | +0.017 |
cases | +0.017 |
ls | +0.016 |
salon | +0.016 |
yle | +0.016 |
Neg logit contributions | |
age | -0.008 |
welcome | -0.007 |
back | -0.006 |
right | -0.006 |
Follow | -0.006 |
Token | dips |
Token ID | 48904 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
cases | +0.008 |
yles | +0.008 |
yle | +0.007 |
ge | +0.007 |
outing | +0.007 |
Neg logit contributions | |
back | -0.006 |
right | -0.006 |
age | -0.006 |
welcome | -0.006 |
best | -0.006 |
Token | his |
Token ID | 465 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
age | +0.174 |
back | +0.154 |
welcome | +0.147 |
home | +0.147 |
right | +0.144 |
Neg logit contributions | |
cases | -0.215 |
yles | -0.213 |
salon | -0.196 |
ls | -0.194 |
yle | -0.193 |
Token | brush |
Token ID | 14093 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
yles | +0.040 |
cases | +0.039 |
ls | +0.036 |
yle | +0.036 |
salon | +0.035 |
Neg logit contributions | |
age | -0.046 |
back | -0.039 |
> | -0.039 |
welcome | -0.039 |
home | -0.038 |
Token | in |
Token ID | 287 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
cases | +0.024 |
yles | +0.023 |
ls | +0.022 |
salon | +0.022 |
yle | +0.022 |
Neg logit contributions | |
age | -0.016 |
welcome | -0.013 |
> | -0.013 |
Follow | -0.013 |
est | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
age | +0.019 |
back | +0.017 |
home | +0.016 |
right | +0.016 |
welcome | +0.016 |
Neg logit contributions | |
cases | -0.025 |
yles | -0.025 |
ls | -0.023 |
yle | -0.023 |
salon | -0.022 |
Token | paint |
Token ID | 7521 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
age | +0.021 |
Follow | +0.018 |
> | +0.018 |
gy | +0.018 |
est | +0.018 |
Neg logit contributions | |
cases | -0.015 |
salon | -0.015 |
spill | -0.015 |
yles | -0.014 |
wra | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
yles | +0.016 |
cases | +0.015 |
ls | +0.015 |
yle | +0.014 |
salon | +0.014 |
Neg logit contributions | |
age | -0.012 |
back | -0.010 |
> | -0.010 |
welcome | -0.010 |
home | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +2.21e-03 |
Pos logit contributions | |
yles | +0.004 |
cases | +0.004 |
yle | +0.003 |
salon | +0.003 |
outing | +0.003 |
Neg logit contributions | |
age | -0.002 |
back | -0.002 |
welcome | -0.002 |
right | -0.002 |
est | -0.002 |
Token | wand |
Token ID | 11569 |
Feature activation | -6.40e-03 |
Pos logit contributions | |
yles | +0.004 |
cases | +0.004 |
ls | +0.003 |
yle | +0.003 |
salon | +0.003 |
Neg logit contributions | |
age | -0.004 |
back | -0.003 |
> | -0.003 |
welcome | -0.003 |
home | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +5.00e-03 |
Pos logit contributions | |
age | +0.009 |
back | +0.007 |
home | +0.007 |
right | +0.007 |
est | +0.007 |
Neg logit contributions | |
yles | -0.014 |
cases | -0.013 |
yle | -0.013 |
ls | -0.012 |
salon | -0.012 |
Token | She |
Token ID | 1375 |
Feature activation | -7.68e-03 |
Pos logit contributions | |
yles | +0.009 |
cases | +0.009 |
ls | +0.008 |
yle | +0.008 |
salon | +0.008 |
Neg logit contributions | |
age | -0.009 |
back | -0.007 |
welcome | -0.007 |
> | -0.007 |
home | -0.007 |
Token | dips |
Token ID | 48904 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
age | +0.012 |
back | +0.011 |
right | +0.011 |
> | +0.011 |
welcome | +0.011 |
Neg logit contributions | |
cases | -0.013 |
yles | -0.013 |
yle | -0.012 |
ries | -0.012 |
outing | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
age | +0.218 |
back | +0.188 |
welcome | +0.185 |
> | +0.185 |
home | +0.183 |
Neg logit contributions | |
yles | -0.169 |
cases | -0.167 |
ls | -0.153 |
yle | -0.152 |
salon | -0.150 |
Token | wand |
Token ID | 11569 |
Feature activation | -6.76e-03 |
Pos logit contributions | |
age | +0.022 |
> | +0.019 |
welcome | +0.019 |
Follow | +0.019 |
back | +0.019 |
Neg logit contributions | |
yles | -0.014 |
cases | -0.014 |
ls | -0.014 |
spill | -0.014 |
yle | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
age | +0.010 |
welcome | +0.008 |
> | +0.008 |
Follow | +0.008 |
gy | +0.008 |
Neg logit contributions | |
cases | -0.012 |
yles | -0.012 |
ls | -0.012 |
spill | -0.012 |
yle | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
age | +0.019 |
back | +0.017 |
home | +0.016 |
right | +0.016 |
welcome | +0.016 |
Neg logit contributions | |
cases | -0.025 |
yles | -0.025 |
ls | -0.023 |
yle | -0.023 |
salon | -0.023 |
Token | soap |
Token ID | 19533 |
Feature activation | +7.52e-03 |
Pos logit contributions | |
age | +0.021 |
gy | +0.019 |
> | +0.019 |
ok | +0.018 |
Follow | +0.018 |
Neg logit contributions | |
spill | -0.015 |
salon | -0.014 |
ls | -0.014 |
wra | -0.014 |
cases | -0.014 |
Token | chicken |
Token ID | 9015 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
yles | +0.007 |
cases | +0.007 |
yle | +0.007 |
ls | +0.006 |
salon | +0.006 |
Neg logit contributions | |
age | -0.007 |
back | -0.006 |
welcome | -0.006 |
home | -0.005 |
> | -0.005 |
Token | n |
Token ID | 299 |
Feature activation | +8.84e-03 |
Pos logit contributions | |
age | +0.043 |
welcome | +0.037 |
amed | +0.037 |
> | +0.037 |
est | +0.036 |
Neg logit contributions | |
ls | -0.039 |
cases | -0.039 |
yles | -0.038 |
salon | -0.037 |
yle | -0.037 |
Token | ug |
Token ID | 1018 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
yles | +0.014 |
cases | +0.014 |
yle | +0.013 |
ls | +0.013 |
outing | +0.013 |
Neg logit contributions | |
age | -0.016 |
back | -0.014 |
welcome | -0.013 |
> | -0.013 |
est | -0.013 |
Token | get |
Token ID | 1136 |
Feature activation | -9.52e-03 |
Pos logit contributions | |
age | +0.103 |
welcome | +0.088 |
> | +0.087 |
Follow | +0.086 |
back | +0.085 |
Neg logit contributions | |
yles | -0.087 |
cases | -0.087 |
yle | -0.082 |
ls | -0.081 |
salon | -0.079 |
Token | and |
Token ID | 290 |
Feature activation | +9.49e-04 |
Pos logit contributions | |
age | +0.015 |
welcome | +0.013 |
est | +0.012 |
Follow | +0.012 |
> | +0.012 |
Neg logit contributions | |
cases | -0.017 |
yles | -0.016 |
ls | -0.016 |
salon | -0.016 |
yle | -0.016 |
Token | dips |
Token ID | 48904 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
cases | +0.002 |
yles | +0.002 |
yle | +0.002 |
outing | +0.001 |
salon | +0.001 |
Neg logit contributions | |
age | -0.002 |
back | -0.002 |
right | -0.001 |
welcome | -0.001 |
Follow | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | +8.01e-03 |
Pos logit contributions | |
age | +0.210 |
back | +0.184 |
welcome | +0.180 |
home | +0.179 |
> | +0.178 |
Neg logit contributions | |
cases | -0.173 |
yles | -0.173 |
salon | -0.155 |
ls | -0.155 |
yle | -0.154 |
Token | in |
Token ID | 287 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
ls | +0.015 |
cases | +0.015 |
yles | +0.015 |
outing | +0.014 |
spill | +0.014 |
Neg logit contributions | |
age | -0.013 |
welcome | -0.010 |
est | -0.010 |
> | -0.009 |
Follow | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +2.84e-03 |
Pos logit contributions | |
age | +0.018 |
back | +0.017 |
home | +0.016 |
right | +0.016 |
welcome | +0.016 |
Neg logit contributions | |
cases | -0.027 |
yles | -0.026 |
ls | -0.024 |
salon | -0.024 |
yle | -0.024 |
Token | red |
Token ID | 2266 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
yles | +0.005 |
cases | +0.005 |
ls | +0.005 |
yle | +0.004 |
salon | +0.004 |
Neg logit contributions | |
age | -0.005 |
> | -0.004 |
back | -0.004 |
welcome | -0.004 |
est | -0.004 |
Token | sauce |
Token ID | 10746 |
Feature activation | +1.25e-03 |
Pos logit contributions | |
age | +0.055 |
Follow | +0.049 |
welcome | +0.048 |
amed | +0.048 |
> | +0.048 |
Neg logit contributions | |
spill | -0.043 |
cases | -0.043 |
salon | -0.042 |
yles | -0.042 |
ls | -0.042 |
Token | their |
Token ID | 511 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
cases | +0.013 |
yles | +0.012 |
outing | +0.012 |
yle | +0.011 |
salon | +0.011 |
Neg logit contributions | |
back | -0.011 |
age | -0.011 |
welcome | -0.011 |
home | -0.011 |
right | -0.010 |
Token | mom |
Token ID | 1995 |
Feature activation | -8.95e-03 |
Pos logit contributions | |
yles | +0.033 |
cases | +0.033 |
eling | +0.030 |
outing | +0.030 |
yle | +0.029 |
Neg logit contributions | |
back | -0.023 |
home | -0.022 |
best | -0.021 |
welcome | -0.021 |
age | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +2.01e-03 |
Pos logit contributions | |
age | +0.016 |
Follow | +0.013 |
> | +0.013 |
amed | +0.012 |
welcome | +0.012 |
Neg logit contributions | |
yles | -0.015 |
cases | -0.015 |
ls | -0.014 |
salon | -0.014 |
yle | -0.014 |
Token | They |
Token ID | 1119 |
Feature activation | -6.71e-03 |
Pos logit contributions | |
yles | +0.004 |
yle | +0.004 |
cases | +0.004 |
ls | +0.004 |
salon | +0.004 |
Neg logit contributions | |
age | -0.003 |
back | -0.002 |
welcome | -0.002 |
> | -0.002 |
home | -0.002 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
age | +0.009 |
back | +0.009 |
welcome | +0.009 |
home | +0.009 |
> | +0.009 |
Neg logit contributions | |
yles | -0.013 |
cases | -0.013 |
ries | -0.012 |
ls | -0.012 |
outing | -0.012 |
Token | many |
Token ID | 867 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
age | +0.021 |
back | +0.017 |
welcome | +0.016 |
home | +0.016 |
right | +0.015 |
Neg logit contributions | |
yles | -0.052 |
cases | -0.051 |
yle | -0.049 |
ls | -0.048 |
salon | -0.048 |
Token | flowers |
Token ID | 12734 |
Feature activation | +9.41e-03 |
Pos logit contributions | |
yles | +0.129 |
cases | +0.125 |
yle | +0.119 |
salon | +0.119 |
oled | +0.116 |
Neg logit contributions | |
best | -0.071 |
welcome | -0.067 |
est | -0.067 |
right | -0.063 |
back | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e-03 |
Pos logit contributions | |
yles | +0.022 |
cases | +0.021 |
yle | +0.021 |
salon | +0.020 |
hairc | +0.020 |
Neg logit contributions | |
age | -0.011 |
back | -0.009 |
welcome | -0.009 |
right | -0.008 |
home | -0.008 |
Token | birds |
Token ID | 10087 |
Feature activation | -8.43e-03 |
Pos logit contributions | |
yles | +0.003 |
yle | +0.003 |
cases | +0.003 |
salon | +0.002 |
outing | +0.002 |
Neg logit contributions | |
age | -0.001 |
right | -0.001 |
back | -0.001 |
welcome | -0.001 |
across | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +1.72e-03 |
Pos logit contributions | |
age | +0.007 |
back | +0.005 |
right | +0.005 |
home | +0.005 |
welcome | +0.005 |
Neg logit contributions | |
cases | -0.023 |
yles | -0.022 |
yle | -0.022 |
tant | -0.021 |
hairc | -0.021 |
Token | bugs |
Token ID | 11316 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
yles | +0.003 |
cases | +0.003 |
yle | +0.003 |
outing | +0.003 |
salon | +0.003 |
Neg logit contributions | |
age | -0.002 |
back | -0.002 |
right | -0.002 |
welcome | -0.002 |
across | -0.002 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
age | +0.006 |
back | +0.006 |
home | +0.005 |
right | +0.005 |
Follow | +0.005 |
Neg logit contributions | |
yles | -0.006 |
yle | -0.005 |
outing | -0.005 |
ls | -0.005 |
cases | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -3.44e-03 |
Pos logit contributions | |
age | +0.041 |
back | +0.034 |
welcome | +0.033 |
home | +0.033 |
> | +0.032 |
Neg logit contributions | |
yles | -0.053 |
cases | -0.053 |
ls | -0.049 |
yle | -0.049 |
salon | -0.049 |
Token | cute |
Token ID | 13779 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
age | +0.006 |
back | +0.005 |
welcome | +0.005 |
home | +0.005 |
right | +0.005 |
Neg logit contributions | |
yles | -0.006 |
cases | -0.006 |
ls | -0.006 |
yle | -0.006 |
ries | -0.006 |
Token | little |
Token ID | 1310 |
Feature activation | +3.65e-03 |
Pos logit contributions | |
age | +0.046 |
back | +0.038 |
> | +0.038 |
welcome | +0.038 |
home | +0.037 |
Neg logit contributions | |
yles | -0.048 |
cases | -0.047 |
ls | -0.044 |
yle | -0.044 |
salon | -0.043 |
Token | puppy |
Token ID | 26188 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
yles | +0.006 |
cases | +0.006 |
ls | +0.006 |
salon | +0.006 |
yle | +0.006 |
Neg logit contributions | |
age | -0.006 |
> | -0.005 |
amed | -0.005 |
welcome | -0.005 |
Follow | -0.005 |
Token | w |
Token ID | 266 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
age | +0.036 |
> | +0.030 |
welcome | +0.029 |
amed | +0.029 |
est | +0.029 |
Neg logit contributions | |
yles | -0.039 |
cases | -0.038 |
ls | -0.037 |
yle | -0.036 |
salon | -0.035 |
Token | agging |
Token ID | 16406 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
yles | +0.119 |
cases | +0.116 |
salon | +0.108 |
yle | +0.107 |
ls | +0.107 |
Neg logit contributions | |
age | -0.098 |
back | -0.080 |
welcome | -0.078 |
> | -0.078 |
home | -0.077 |
Token | its |
Token ID | 663 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
age | +0.092 |
Follow | +0.078 |
welcome | +0.077 |
> | +0.073 |
est | +0.072 |
Neg logit contributions | |
yles | -0.103 |
cases | -0.102 |
ls | -0.097 |
yle | -0.097 |
spill | -0.093 |
Token | tail |
Token ID | 7894 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
cases | +0.037 |
spill | +0.036 |
wra | +0.036 |
ls | +0.035 |
tant | +0.035 |
Neg logit contributions | |
Follow | -0.030 |
age | -0.030 |
iddle | -0.026 |
welcome | -0.026 |
wood | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -2.38e-03 |
Pos logit contributions | |
age | +0.026 |
welcome | +0.022 |
Follow | +0.022 |
> | +0.022 |
est | +0.021 |
Neg logit contributions | |
cases | -0.025 |
yles | -0.024 |
ls | -0.023 |
yle | -0.022 |
salon | -0.022 |
Token | |
Token ID | 220 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
age | +0.003 |
back | +0.002 |
> | +0.002 |
welcome | +0.002 |
home | +0.002 |
Neg logit contributions | |
yles | -0.005 |
cases | -0.005 |
ls | -0.005 |
yle | -0.005 |
salon | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
yles | +0.004 |
cases | +0.004 |
outing | +0.003 |
yle | +0.003 |
ls | +0.003 |
Neg logit contributions | |
age | -0.006 |
back | -0.006 |
home | -0.006 |
welcome | -0.006 |
right | -0.006 |
Token | little |
Token ID | 1310 |
Feature activation | +9.96e-03 |
Pos logit contributions | |
age | +0.020 |
Follow | +0.016 |
> | +0.016 |
gy | +0.016 |
amed | +0.016 |
Neg logit contributions | |
cases | -0.018 |
yles | -0.018 |
wra | -0.017 |
salon | -0.017 |
ls | -0.017 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
yles | +0.017 |
cases | +0.016 |
ls | +0.016 |
salon | +0.016 |
ries | +0.016 |
Neg logit contributions | |
age | -0.017 |
> | -0.014 |
Follow | -0.014 |
amed | -0.014 |
welcome | -0.013 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.75e-03 |
Pos logit contributions | |
age | +0.051 |
back | +0.043 |
> | +0.043 |
welcome | +0.042 |
home | +0.042 |
Neg logit contributions | |
yles | -0.044 |
cases | -0.044 |
ls | -0.040 |
yle | -0.040 |
salon | -0.040 |
Token | really |
Token ID | 1107 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
yles | +0.003 |
cases | +0.003 |
yle | +0.003 |
ls | +0.003 |
else | +0.003 |
Neg logit contributions | |
age | -0.003 |
gy | -0.002 |
> | -0.002 |
ney | -0.002 |
man | -0.002 |
Token | proud |
Token ID | 6613 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
age | +0.020 |
back | +0.016 |
welcome | +0.016 |
> | +0.015 |
home | +0.015 |
Neg logit contributions | |
yles | -0.028 |
cases | -0.028 |
ls | -0.026 |
yle | -0.026 |
salon | -0.026 |
Token | of |
Token ID | 286 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
yles | +0.105 |
cases | +0.104 |
ls | +0.096 |
yle | +0.096 |
salon | +0.094 |
Neg logit contributions | |
age | -0.104 |
back | -0.088 |
welcome | -0.086 |
> | -0.086 |
home | -0.085 |
Token | herself |
Token ID | 5223 |
Feature activation | +4.63e-03 |
Pos logit contributions | |
yles | +0.055 |
cases | +0.054 |
ls | +0.050 |
yle | +0.050 |
salon | +0.049 |
Neg logit contributions | |
age | -0.049 |
back | -0.041 |
welcome | -0.041 |
> | -0.040 |
home | -0.040 |
Token | for |
Token ID | 329 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
cases | +0.008 |
ls | +0.008 |
yles | +0.008 |
yle | +0.007 |
salon | +0.007 |
Neg logit contributions | |
age | -0.007 |
amed | -0.006 |
> | -0.006 |
Follow | -0.006 |
welcome | -0.006 |
Token | becoming |
Token ID | 5033 |
Feature activation | +4.01e-03 |
Pos logit contributions | |
age | +0.025 |
back | +0.023 |
welcome | +0.023 |
right | +0.022 |
home | +0.022 |
Neg logit contributions | |
cases | -0.039 |
yles | -0.037 |
ls | -0.036 |
yle | -0.034 |
salon | -0.034 |
Token | brave |
Token ID | 14802 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
yles | +0.008 |
cases | +0.007 |
yle | +0.007 |
ls | +0.007 |
ries | +0.007 |
Neg logit contributions | |
age | -0.006 |
> | -0.005 |
Follow | -0.005 |
est | -0.005 |
ney | -0.005 |
Token | week |
Token ID | 1285 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
yles | +0.065 |
cases | +0.065 |
ls | +0.063 |
yle | +0.062 |
salon | +0.062 |
Neg logit contributions | |
age | -0.021 |
> | -0.014 |
back | -0.013 |
amed | -0.013 |
welcome | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
yles | +0.048 |
cases | +0.046 |
ls | +0.045 |
yle | +0.044 |
outing | +0.044 |
Neg logit contributions | |
age | -0.027 |
back | -0.023 |
home | -0.022 |
right | -0.021 |
welcome | -0.021 |
Token | The |
Token ID | 383 |
Feature activation | -3.14e-03 |
Pos logit contributions | |
yles | +0.005 |
cases | +0.005 |
salon | +0.005 |
yle | +0.005 |
spill | +0.005 |
Neg logit contributions | |
age | -0.004 |
amed | -0.003 |
> | -0.003 |
back | -0.003 |
home | -0.003 |
Token | farmer |
Token ID | 18739 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
age | +0.006 |
> | +0.005 |
amed | +0.005 |
Follow | +0.005 |
back | +0.005 |
Neg logit contributions | |
cases | -0.005 |
yles | -0.005 |
ls | -0.005 |
salon | -0.004 |
yle | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | -7.61e-03 |
Pos logit contributions | |
yles | +0.050 |
cases | +0.048 |
yle | +0.045 |
ls | +0.045 |
salon | +0.044 |
Neg logit contributions | |
age | -0.051 |
back | -0.043 |
welcome | -0.042 |
> | -0.042 |
home | -0.041 |
Token | many |
Token ID | 867 |
Feature activation | +5.66e-02 |
Pos logit contributions | |
age | +0.008 |
back | +0.007 |
home | +0.006 |
welcome | +0.006 |
right | +0.006 |
Neg logit contributions | |
yles | -0.019 |
cases | -0.018 |
yle | -0.017 |
ls | -0.017 |
outing | -0.017 |
Token | animals |
Token ID | 4695 |
Feature activation | +1.27e-03 |
Pos logit contributions | |
yles | +0.123 |
salon | +0.115 |
yle | +0.115 |
cases | +0.115 |
outing | +0.109 |
Neg logit contributions | |
age | -0.076 |
est | -0.066 |
welcome | -0.066 |
home | -0.065 |
back | -0.065 |
Token | that |
Token ID | 326 |
Feature activation | +3.35e-03 |
Pos logit contributions | |
yles | +0.003 |
cases | +0.003 |
yle | +0.003 |
ls | +0.003 |
salon | +0.003 |
Neg logit contributions | |
age | -0.002 |
back | -0.001 |
welcome | -0.001 |
home | -0.001 |
right | -0.001 |
Token | Sam |
Token ID | 3409 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
yles | +0.006 |
cases | +0.005 |
salon | +0.005 |
yle | +0.005 |
outing | +0.005 |
Neg logit contributions | |
age | -0.006 |
welcome | -0.005 |
back | -0.005 |
home | -0.005 |
right | -0.005 |
Token | loved |
Token ID | 6151 |
Feature activation | +4.19e-03 |
Pos logit contributions | |
yles | +0.085 |
cases | +0.080 |
ls | +0.078 |
yle | +0.078 |
outing | +0.077 |
Neg logit contributions | |
age | -0.074 |
back | -0.064 |
home | -0.060 |
right | -0.060 |
> | -0.059 |
Token | to |
Token ID | 284 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
cases | +0.008 |
yles | +0.008 |
salon | +0.008 |
yle | +0.008 |
ls | +0.008 |
Neg logit contributions | |
age | -0.006 |
back | -0.005 |
home | -0.005 |
welcome | -0.005 |
right | -0.005 |
Token | I |
Token ID | 314 |
Feature activation | -2.20e-03 |
Pos logit contributions | |
yles | +0.006 |
cases | +0.006 |
yle | +0.006 |
hairc | +0.006 |
salon | +0.006 |
Neg logit contributions | |
age | -0.006 |
> | -0.005 |
back | -0.005 |
home | -0.005 |
gy | -0.005 |
Token | will |
Token ID | 481 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
age | +0.004 |
> | +0.003 |
back | +0.003 |
welcome | +0.003 |
home | +0.003 |
Neg logit contributions | |
yles | -0.004 |
cases | -0.004 |
ls | -0.004 |
yle | -0.004 |
salon | -0.004 |
Token | give |
Token ID | 1577 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
age | +0.072 |
back | +0.059 |
> | +0.059 |
est | +0.057 |
welcome | +0.057 |
Neg logit contributions | |
yles | -0.085 |
cases | -0.084 |
yle | -0.079 |
ls | -0.078 |
salon | -0.078 |
Token | you |
Token ID | 345 |
Feature activation | -1.51e-03 |
Pos logit contributions | |
yles | +0.046 |
cases | +0.044 |
ls | +0.042 |
yle | +0.042 |
salon | +0.040 |
Neg logit contributions | |
age | -0.056 |
> | -0.046 |
est | -0.045 |
welcome | -0.045 |
back | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
age | +0.002 |
> | +0.002 |
gy | +0.002 |
Follow | +0.002 |
ney | +0.002 |
Neg logit contributions | |
cases | -0.003 |
yles | -0.003 |
hairc | -0.003 |
ls | -0.003 |
yle | -0.003 |
Token | courage |
Token ID | 11917 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
age | +0.023 |
back | +0.020 |
welcome | +0.020 |
home | +0.020 |
right | +0.020 |
Neg logit contributions | |
yles | -0.018 |
cases | -0.018 |
ls | -0.017 |
yle | -0.016 |
outing | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +2.00e-03 |
Pos logit contributions | |
cases | +0.111 |
yles | +0.110 |
ls | +0.104 |
yle | +0.103 |
salon | +0.102 |
Neg logit contributions | |
age | -0.093 |
> | -0.075 |
welcome | -0.073 |
back | -0.072 |
est | -0.072 |
Token | strength |
Token ID | 4202 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
yles | +0.004 |
cases | +0.004 |
ls | +0.003 |
yle | +0.003 |
salon | +0.003 |
Neg logit contributions | |
age | -0.003 |
back | -0.003 |
welcome | -0.003 |
> | -0.003 |
home | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
yles | +0.115 |
cases | +0.114 |
ls | +0.107 |
yle | +0.107 |
salon | +0.105 |
Neg logit contributions | |
age | -0.088 |
> | -0.070 |
back | -0.070 |
welcome | -0.069 |
est | -0.068 |
Token | save |
Token ID | 3613 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
yles | +0.031 |
cases | +0.030 |
ls | +0.029 |
yle | +0.028 |
outing | +0.028 |
Neg logit contributions | |
age | -0.021 |
welcome | -0.017 |
back | -0.017 |
home | -0.017 |
right | -0.016 |
Token | yourself |
Token ID | 3511 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
yles | +0.060 |
cases | +0.059 |
ls | +0.056 |
yle | +0.055 |
salon | +0.054 |
Neg logit contributions | |
age | -0.063 |
> | -0.051 |
back | -0.051 |
welcome | -0.051 |
est | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | -4.38e-03 |
Pos logit contributions | |
age | +0.063 |
> | +0.052 |
Follow | +0.051 |
welcome | +0.051 |
ney | +0.048 |
Neg logit contributions | |
cases | -0.071 |
yles | -0.069 |
salon | -0.066 |
ls | -0.065 |
yle | -0.064 |
Token | Eric |
Token ID | 7651 |
Feature activation | +9.93e-03 |
Pos logit contributions | |
age | +0.008 |
back | +0.007 |
home | +0.007 |
across | +0.007 |
right | +0.007 |
Neg logit contributions | |
cases | -0.007 |
yles | -0.007 |
outing | -0.006 |
yle | -0.006 |
ries | -0.006 |
Token | played |
Token ID | 2826 |
Feature activation | -5.34e-03 |
Pos logit contributions | |
yles | +0.017 |
cases | +0.017 |
ries | +0.016 |
ls | +0.016 |
outing | +0.015 |
Neg logit contributions | |
age | -0.017 |
back | -0.015 |
est | -0.014 |
across | -0.014 |
home | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
age | +0.009 |
> | +0.007 |
welcome | +0.007 |
Follow | +0.007 |
ney | +0.007 |
Neg logit contributions | |
yles | -0.010 |
cases | -0.009 |
ls | -0.009 |
yle | -0.009 |
salon | -0.009 |
Token | trumpet |
Token ID | 40334 |
Feature activation | -4.85e-03 |
Pos logit contributions | |
age | +0.026 |
welcome | +0.022 |
Follow | +0.022 |
> | +0.022 |
home | +0.021 |
Neg logit contributions | |
cases | -0.018 |
yles | -0.018 |
ls | -0.016 |
yle | -0.016 |
salon | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.89e-03 |
Pos logit contributions | |
age | +0.007 |
welcome | +0.006 |
> | +0.006 |
Follow | +0.006 |
amed | +0.006 |
Neg logit contributions | |
cases | -0.009 |
yles | -0.009 |
ls | -0.009 |
salon | -0.009 |
yle | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
age | +0.003 |
back | +0.002 |
> | +0.002 |
welcome | +0.002 |
home | +0.002 |
Neg logit contributions | |
yles | -0.004 |
cases | -0.004 |
ls | -0.004 |
yle | -0.004 |
salon | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -9.37e-03 |
Pos logit contributions | |
age | +0.014 |
back | +0.011 |
welcome | +0.011 |
> | +0.011 |
est | +0.011 |
Neg logit contributions | |
yles | -0.021 |
cases | -0.021 |
ls | -0.020 |
yle | -0.020 |
salon | -0.019 |
Token | The |
Token ID | 464 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
age | +0.016 |
> | +0.013 |
back | +0.013 |
welcome | +0.013 |
home | +0.013 |
Neg logit contributions | |
yles | -0.017 |
cases | -0.016 |
ls | -0.015 |
yle | -0.015 |
salon | -0.015 |
Token | next |
Token ID | 1306 |
Feature activation | -8.68e-04 |
Pos logit contributions | |
yles | +0.010 |
cases | +0.010 |
ls | +0.009 |
yle | +0.009 |
salon | +0.009 |
Neg logit contributions | |
age | -0.010 |
> | -0.008 |
back | -0.008 |
welcome | -0.008 |
Follow | -0.008 |
Token | day |
Token ID | 1110 |
Feature activation | +2.58e-03 |
Pos logit contributions | |
age | +0.001 |
Follow | +0.001 |
> | +0.001 |
gy | +0.001 |
amed | +0.001 |
Neg logit contributions | |
yles | -0.002 |
cases | -0.002 |
salon | -0.002 |
hairc | -0.002 |
yle | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -9.55e-03 |
Pos logit contributions | |
yles | +0.004 |
ls | +0.004 |
cases | +0.004 |
yle | +0.003 |
s | +0.003 |
Neg logit contributions | |
age | -0.004 |
ney | -0.003 |
est | -0.003 |
> | -0.003 |
gy | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -9.53e-03 |
Pos logit contributions | |
age | +0.016 |
est | +0.014 |
back | +0.013 |
gy | +0.013 |
welcome | +0.012 |
Neg logit contributions | |
yles | -0.016 |
ls | -0.016 |
cases | -0.016 |
yle | -0.015 |
l | -0.015 |
Token | P |
Token ID | 47 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
age | +0.015 |
back | +0.013 |
home | +0.012 |
est | +0.012 |
welcome | +0.012 |
Neg logit contributions | |
yles | -0.017 |
ls | -0.017 |
cases | -0.016 |
yle | -0.016 |
spill | -0.015 |
Token | oppy |
Token ID | 26696 |
Feature activation | -7.71e-03 |
Pos logit contributions | |
age | +0.033 |
back | +0.029 |
est | +0.028 |
right | +0.028 |
> | +0.028 |
Neg logit contributions | |
ls | -0.023 |
yles | -0.022 |
cases | -0.021 |
yle | -0.021 |
outing | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -2.25e-03 |
Pos logit contributions | |
age | +0.014 |
back | +0.012 |
> | +0.012 |
welcome | +0.011 |
home | +0.011 |
Neg logit contributions | |
yles | -0.013 |
cases | -0.012 |
yle | -0.012 |
ls | -0.011 |
salon | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | -3.91e-03 |
Pos logit contributions | |
age | +0.003 |
back | +0.003 |
home | +0.003 |
right | +0.003 |
welcome | +0.003 |
Neg logit contributions | |
cases | -0.004 |
yles | -0.004 |
outing | -0.004 |
ries | -0.004 |
salon | -0.004 |
Token | dad |
Token ID | 9955 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
back | +0.006 |
home | +0.005 |
best | +0.005 |
right | +0.005 |
welcome | +0.004 |
Neg logit contributions | |
yles | -0.009 |
cases | -0.008 |
outing | -0.008 |
ge | -0.008 |
ries | -0.008 |
Token | threw |
Token ID | 9617 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
yles | +0.013 |
cases | +0.012 |
ls | +0.012 |
outing | +0.012 |
salon | +0.012 |
Neg logit contributions | |
age | -0.014 |
back | -0.013 |
home | -0.013 |
right | -0.012 |
amed | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
age | +0.030 |
> | +0.024 |
ney | +0.024 |
Follow | +0.024 |
welcome | +0.024 |
Neg logit contributions | |
yles | -0.021 |
ls | -0.020 |
cases | -0.020 |
yle | -0.019 |
spill | -0.019 |
Token | ball |
Token ID | 2613 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
age | +0.027 |
> | +0.021 |
welcome | +0.021 |
Follow | +0.021 |
back | +0.021 |
Neg logit contributions | |
cases | -0.028 |
yles | -0.028 |
ls | -0.027 |
yle | -0.026 |
salon | -0.026 |
Token | back |
Token ID | 736 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
age | +0.049 |
> | +0.039 |
welcome | +0.039 |
Follow | +0.037 |
ney | +0.037 |
Neg logit contributions | |
ls | -0.067 |
cases | -0.064 |
s | -0.061 |
spill | -0.061 |
yles | -0.060 |
Token | their |
Token ID | 511 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
age | +0.014 |
> | +0.011 |
amed | +0.011 |
est | +0.011 |
Follow | +0.011 |
Neg logit contributions | |
yles | -0.014 |
cases | -0.014 |
ls | -0.013 |
yle | -0.013 |
salon | -0.012 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
yles | +0.022 |
cases | +0.022 |
yle | +0.021 |
ls | +0.020 |
outing | +0.019 |
Neg logit contributions | |
age | -0.020 |
back | -0.018 |
home | -0.017 |
welcome | -0.017 |
> | -0.017 |
Token | if |
Token ID | 611 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
age | +0.014 |
back | +0.011 |
welcome | +0.010 |
> | +0.010 |
home | +0.010 |
Neg logit contributions | |
yles | -0.026 |
cases | -0.026 |
ls | -0.025 |
yle | -0.025 |
salon | -0.024 |
Token | they |
Token ID | 484 |
Feature activation | -3.49e-03 |
Pos logit contributions | |
back | +0.035 |
right | +0.034 |
home | +0.034 |
age | +0.033 |
welcome | +0.033 |
Neg logit contributions | |
cases | -0.023 |
yles | -0.022 |
outing | -0.022 |
tant | -0.021 |
yle | -0.020 |
Token | could |
Token ID | 714 |
Feature activation | +2.26e-03 |
Pos logit contributions | |
back | +0.005 |
age | +0.005 |
right | +0.004 |
welcome | +0.004 |
home | +0.004 |
Neg logit contributions | |
yles | -0.007 |
ries | -0.007 |
cases | -0.007 |
salon | -0.006 |
outing | -0.006 |
Token | play |
Token ID | 711 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
yles | +0.004 |
cases | +0.004 |
ls | +0.004 |
yle | +0.004 |
salon | +0.004 |
Neg logit contributions | |
age | -0.004 |
back | -0.003 |
> | -0.003 |
welcome | -0.003 |
est | -0.003 |
Token | some |
Token ID | 617 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
yles | +0.030 |
cases | +0.028 |
ls | +0.028 |
salon | +0.028 |
spill | +0.027 |
Neg logit contributions | |
age | -0.025 |
> | -0.020 |
Follow | -0.019 |
amed | -0.019 |
est | -0.019 |
Token | more |
Token ID | 517 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
yles | +0.079 |
cases | +0.078 |
yle | +0.074 |
ls | +0.073 |
salon | +0.072 |
Neg logit contributions | |
age | -0.035 |
back | -0.028 |
welcome | -0.027 |
home | -0.027 |
> | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +1.62e-03 |
Pos logit contributions | |
age | +0.030 |
back | +0.025 |
home | +0.025 |
welcome | +0.025 |
right | +0.024 |
Neg logit contributions | |
yles | -0.046 |
cases | -0.046 |
yle | -0.044 |
outing | -0.042 |
salon | -0.042 |
Token | Their |
Token ID | 5334 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
yles | +0.003 |
cases | +0.003 |
yle | +0.003 |
eling | +0.003 |
ls | +0.003 |
Neg logit contributions | |
age | -0.003 |
back | -0.002 |
home | -0.002 |
welcome | -0.002 |
> | -0.002 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
yles | +0.033 |
cases | +0.033 |
yle | +0.031 |
ls | +0.030 |
outing | +0.029 |
Neg logit contributions | |
age | -0.026 |
back | -0.024 |
home | -0.023 |
> | -0.022 |
welcome | -0.022 |
Token | not |
Token ID | 407 |
Feature activation | -1.71e-03 |
Pos logit contributions | |
yles | +0.005 |
cases | +0.005 |
ls | +0.004 |
yle | +0.004 |
salon | +0.004 |
Neg logit contributions | |
age | -0.004 |
> | -0.004 |
back | -0.004 |
welcome | -0.004 |
est | -0.004 |
Token | help |
Token ID | 1037 |
Feature activation | +6.10e-03 |
Pos logit contributions | |
age | +0.003 |
back | +0.002 |
> | +0.002 |
welcome | +0.002 |
home | +0.002 |
Neg logit contributions | |
yles | -0.003 |
cases | -0.003 |
ls | -0.003 |
yle | -0.003 |
salon | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
yles | +0.011 |
cases | +0.011 |
ls | +0.010 |
yle | +0.010 |
salon | +0.010 |
Neg logit contributions | |
age | -0.010 |
back | -0.009 |
home | -0.008 |
welcome | -0.008 |
right | -0.008 |
Token | baby |
Token ID | 5156 |
Feature activation | +2.45e-03 |
Pos logit contributions | |
age | +0.032 |
back | +0.029 |
home | +0.028 |
welcome | +0.028 |
> | +0.028 |
Neg logit contributions | |
yles | -0.022 |
cases | -0.022 |
ls | -0.019 |
yle | -0.019 |
salon | -0.019 |
Token | bird |
Token ID | 6512 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
yles | +0.005 |
cases | +0.005 |
ls | +0.004 |
yle | +0.004 |
salon | +0.004 |
Neg logit contributions | |
age | -0.004 |
back | -0.003 |
> | -0.003 |
welcome | -0.003 |
home | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +4.48e-04 |
Pos logit contributions | |
age | +0.018 |
> | +0.014 |
welcome | +0.014 |
back | +0.014 |
home | +0.014 |
Neg logit contributions | |
yles | -0.021 |
cases | -0.021 |
ls | -0.019 |
yle | -0.019 |
salon | -0.019 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
yles | +0.001 |
cases | +0.001 |
ls | +0.001 |
yle | +0.001 |
salon | +0.001 |
Neg logit contributions | |
age | -0.001 |
est | -0.001 |
back | -0.001 |
amed | -0.001 |
welcome | -0.001 |
Token | Once |
Token ID | 7454 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
yles | +0.047 |
ls | +0.045 |
cases | +0.045 |
yle | +0.043 |
l | +0.041 |
Neg logit contributions | |
age | -0.055 |
est | -0.045 |
Follow | -0.044 |
advantage | -0.044 |
amed | -0.043 |
Token | upon |
Token ID | 2402 |
Feature activation | +4.62e-05 |
Pos logit contributions | |
yles | +0.075 |
cases | +0.074 |
yle | +0.068 |
salon | +0.067 |
hairc | +0.065 |
Neg logit contributions | |
age | -0.080 |
back | -0.074 |
home | -0.073 |
welcome | -0.072 |
> | -0.072 |
Token | a |
Token ID | 257 |
Feature activation | -8.85e-05 |
Pos logit contributions | |
yles | +0.000 |
cases | +0.000 |
ls | +0.000 |
yle | +0.000 |
salon | +0.000 |
Neg logit contributions | |
age | -0.000 |
back | -0.000 |
> | -0.000 |
welcome | -0.000 |
home | -0.000 |
Token | time |
Token ID | 640 |
Feature activation | -3.92e-03 |
Pos logit contributions | |
age | +0.000 |
back | +0.000 |
Follow | +0.000 |
est | +0.000 |
amed | +0.000 |
Neg logit contributions | |
yles | -0.000 |
cases | -0.000 |
ls | -0.000 |
spill | -0.000 |
salon | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +6.69e-03 |
Pos logit contributions | |
age | +0.012 |
back | +0.010 |
> | +0.010 |
welcome | +0.010 |
home | +0.010 |
Neg logit contributions | |
yles | -0.016 |
cases | -0.016 |
ls | -0.015 |
yle | -0.015 |
salon | -0.015 |
Token | They |
Token ID | 1119 |
Feature activation | +2.07e-03 |
Pos logit contributions | |
yles | +0.013 |
cases | +0.013 |
ls | +0.012 |
yle | +0.012 |
salon | +0.012 |
Neg logit contributions | |
age | -0.010 |
back | -0.008 |
> | -0.008 |
welcome | -0.008 |
est | -0.008 |
Token | forget |
Token ID | 6044 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
yles | +0.004 |
cases | +0.004 |
ls | +0.003 |
ries | +0.003 |
yle | +0.003 |
Neg logit contributions | |
age | -0.003 |
back | -0.003 |
welcome | -0.003 |
right | -0.003 |
home | -0.003 |
Token | about |
Token ID | 546 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
yles | +0.078 |
cases | +0.076 |
yle | +0.072 |
ls | +0.072 |
salon | +0.071 |
Neg logit contributions | |
age | -0.055 |
back | -0.046 |
> | -0.045 |
welcome | -0.044 |
home | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -8.44e-03 |
Pos logit contributions | |
cases | +0.048 |
yles | +0.043 |
ls | +0.042 |
yle | +0.041 |
outing | +0.041 |
Neg logit contributions | |
back | -0.026 |
home | -0.025 |
right | -0.025 |
welcome | -0.023 |
best | -0.021 |
Token | cat |
Token ID | 3797 |
Feature activation | +6.50e-03 |
Pos logit contributions | |
age | +0.015 |
> | +0.012 |
back | +0.012 |
Follow | +0.012 |
est | +0.012 |
Neg logit contributions | |
yles | -0.014 |
cases | -0.014 |
ls | -0.013 |
salon | -0.013 |
spill | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +7.00e-03 |
Pos logit contributions | |
yles | +0.013 |
cases | +0.013 |
yle | +0.012 |
ls | +0.012 |
salon | +0.012 |
Neg logit contributions | |
age | -0.009 |
back | -0.008 |
> | -0.007 |
home | -0.007 |
welcome | -0.007 |
Token | The |
Token ID | 383 |
Feature activation | +6.04e-03 |
Pos logit contributions | |
yles | +0.014 |
cases | +0.014 |
ls | +0.013 |
yle | +0.013 |
salon | +0.013 |
Neg logit contributions | |
age | -0.010 |
back | -0.008 |
welcome | -0.008 |
> | -0.008 |
home | -0.008 |
Token | cat |
Token ID | 3797 |
Feature activation | +6.80e-03 |
Pos logit contributions | |
cases | +0.009 |
salon | +0.009 |
yles | +0.009 |
ls | +0.009 |
spill | +0.009 |
Neg logit contributions | |
age | -0.011 |
amed | -0.009 |
est | -0.009 |
Follow | -0.009 |
> | -0.009 |
Token | forg |
Token ID | 5784 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
yles | +0.013 |
cases | +0.013 |
yle | +0.012 |
outing | +0.012 |
salon | +0.011 |
Neg logit contributions | |
age | -0.011 |
back | -0.010 |
right | -0.009 |
welcome | -0.009 |
> | -0.009 |
Token | ets |
Token ID | 1039 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
yles | +0.017 |
cases | +0.017 |
ls | +0.016 |
yle | +0.015 |
salon | +0.015 |
Neg logit contributions | |
age | -0.020 |
> | -0.017 |
back | -0.017 |
welcome | -0.016 |
home | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -6.45e-03 |
Pos logit contributions | |
yles | +0.121 |
cases | +0.115 |
yle | +0.112 |
ls | +0.110 |
salon | +0.107 |
Neg logit contributions | |
age | -0.061 |
back | -0.054 |
right | -0.051 |
home | -0.049 |
welcome | -0.049 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
age | +0.012 |
> | +0.010 |
back | +0.010 |
welcome | +0.010 |
home | +0.009 |
Neg logit contributions | |
yles | -0.011 |
cases | -0.010 |
ls | -0.010 |
yle | -0.010 |
salon | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e-03 |
Pos logit contributions | |
age | +0.024 |
> | +0.019 |
Follow | +0.019 |
back | +0.019 |
amed | +0.019 |
Neg logit contributions | |
yles | -0.026 |
cases | -0.026 |
salon | -0.024 |
ls | -0.024 |
yle | -0.024 |
Token | Tom |
Token ID | 4186 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
age | +0.003 |
amed | +0.002 |
home | +0.002 |
sy | +0.002 |
ench | +0.002 |
Neg logit contributions | |
cases | -0.002 |
yles | -0.002 |
hairc | -0.002 |
salon | -0.002 |
yle | -0.002 |
Token | put |
Token ID | 1234 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
yles | +0.044 |
cases | +0.044 |
ls | +0.041 |
yle | +0.040 |
salon | +0.040 |
Neg logit contributions | |
age | -0.046 |
> | -0.038 |
back | -0.038 |
welcome | -0.037 |
home | -0.037 |
Token | me |
Token ID | 502 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
age | +0.021 |
> | +0.017 |
est | +0.016 |
Follow | +0.016 |
ney | +0.016 |
Neg logit contributions | |
yles | -0.025 |
cases | -0.024 |
ls | -0.024 |
ries | -0.023 |
yle | -0.023 |
Token | in |
Token ID | 287 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
age | +0.056 |
> | +0.046 |
est | +0.045 |
effect | +0.044 |
Follow | +0.043 |
Neg logit contributions | |
cases | -0.085 |
yles | -0.082 |
ls | -0.081 |
ries | -0.080 |
hairc | -0.078 |
Token | jail |
Token ID | 7356 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
age | +0.029 |
back | +0.023 |
> | +0.023 |
welcome | +0.023 |
home | +0.023 |
Neg logit contributions | |
yles | -0.037 |
cases | -0.036 |
ls | -0.034 |
yle | -0.034 |
salon | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -2.09e-03 |
Pos logit contributions | |
yles | +0.121 |
yle | +0.114 |
cases | +0.110 |
ls | +0.108 |
spill | +0.106 |
Neg logit contributions | |
age | -0.058 |
back | -0.055 |
right | -0.051 |
home | -0.050 |
welcome | -0.046 |
Token | But |
Token ID | 887 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
age | +0.003 |
amed | +0.003 |
home | +0.003 |
back | +0.003 |
> | +0.003 |
Neg logit contributions | |
cases | -0.004 |
yles | -0.004 |
hairc | -0.003 |
yle | -0.003 |
salon | -0.003 |
Token | I |
Token ID | 314 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
age | +0.024 |
back | +0.020 |
welcome | +0.020 |
home | +0.020 |
> | +0.019 |
Neg logit contributions | |
yles | -0.025 |
cases | -0.024 |
ls | -0.023 |
yle | -0.022 |
salon | -0.022 |
Token | store |
Token ID | 3650 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
age | +0.027 |
back | +0.023 |
home | +0.022 |
welcome | +0.022 |
> | +0.022 |
Neg logit contributions | |
yles | -0.028 |
cases | -0.027 |
ls | -0.026 |
yle | -0.025 |
ries | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -4.11e-04 |
Pos logit contributions | |
cases | +0.098 |
yles | +0.095 |
yle | +0.089 |
salon | +0.088 |
ls | +0.088 |
Neg logit contributions | |
age | -0.084 |
> | -0.068 |
welcome | -0.067 |
est | -0.067 |
Follow | -0.066 |
Token | He |
Token ID | 679 |
Feature activation | -6.63e-03 |
Pos logit contributions | |
age | +0.000 |
back | +0.000 |
welcome | +0.000 |
> | +0.000 |
home | +0.000 |
Neg logit contributions | |
yles | -0.001 |
cases | -0.001 |
ls | -0.001 |
yle | -0.001 |
salon | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +5.78e-03 |
Pos logit contributions | |
age | +0.011 |
back | +0.010 |
> | +0.009 |
home | +0.009 |
gy | +0.009 |
Neg logit contributions | |
yles | -0.012 |
cases | -0.012 |
ls | -0.011 |
ries | -0.011 |
yle | -0.011 |
Token | looking |
Token ID | 2045 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
yles | +0.013 |
cases | +0.013 |
yle | +0.012 |
salon | +0.012 |
ls | +0.012 |
Neg logit contributions | |
age | -0.007 |
> | -0.005 |
est | -0.005 |
back | -0.005 |
welcome | -0.005 |
Token | for |
Token ID | 329 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
age | +0.016 |
> | +0.010 |
gy | +0.010 |
amed | +0.010 |
ney | +0.010 |
Neg logit contributions | |
cases | -0.034 |
yles | -0.033 |
ls | -0.033 |
yle | -0.032 |
hairc | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -2.26e-03 |
Pos logit contributions | |
age | +0.026 |
back | +0.026 |
home | +0.026 |
welcome | +0.024 |
right | +0.024 |
Neg logit contributions | |
yles | -0.059 |
cases | -0.058 |
outing | -0.056 |
ls | -0.055 |
salon | -0.055 |
Token | new |
Token ID | 649 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
age | +0.004 |
back | +0.003 |
welcome | +0.003 |
home | +0.003 |
> | +0.003 |
Neg logit contributions | |
yles | -0.004 |
cases | -0.004 |
ls | -0.004 |
yle | -0.004 |
salon | -0.004 |
Token | hat |
Token ID | 6877 |
Feature activation | -5.30e-03 |
Pos logit contributions | |
salon | +0.023 |
yles | +0.023 |
cases | +0.023 |
yle | +0.022 |
hairc | +0.021 |
Neg logit contributions | |
age | -0.024 |
> | -0.021 |
amed | -0.021 |
Follow | -0.020 |
welcome | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | +9.83e-03 |
Pos logit contributions | |
age | +0.008 |
> | +0.007 |
welcome | +0.007 |
Follow | +0.006 |
back | +0.006 |
Neg logit contributions | |
cases | -0.010 |
yles | -0.010 |
yle | -0.009 |
ls | -0.009 |
salon | -0.009 |
Token | wear |
Token ID | 5806 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
yles | +0.019 |
cases | +0.019 |
outing | +0.017 |
ls | +0.017 |
yle | +0.016 |
Neg logit contributions | |
age | -0.017 |
welcome | -0.014 |
back | -0.014 |
home | -0.014 |
right | -0.013 |
Token | plate |
Token ID | 7480 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
age | +0.013 |
back | +0.012 |
welcome | +0.011 |
right | +0.011 |
home | +0.011 |
Neg logit contributions | |
yles | -0.015 |
cases | -0.015 |
ls | -0.013 |
yle | -0.013 |
outing | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +8.22e-03 |
Pos logit contributions | |
age | +0.034 |
back | +0.029 |
welcome | +0.027 |
home | +0.027 |
right | +0.027 |
Neg logit contributions | |
yles | -0.052 |
cases | -0.049 |
yle | -0.047 |
ls | -0.047 |
salon | -0.046 |
Token | She |
Token ID | 1375 |
Feature activation | -5.47e-04 |
Pos logit contributions | |
yles | +0.016 |
cases | +0.016 |
ls | +0.015 |
yle | +0.015 |
salon | +0.014 |
Neg logit contributions | |
age | -0.012 |
back | -0.010 |
welcome | -0.010 |
> | -0.010 |
home | -0.010 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
back | +0.001 |
amed | +0.001 |
age | +0.001 |
right | +0.001 |
> | +0.001 |
Neg logit contributions | |
yles | -0.001 |
cases | -0.001 |
outing | -0.001 |
salon | -0.001 |
hairc | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -8.45e-03 |
Pos logit contributions | |
back | +0.019 |
right | +0.018 |
home | +0.017 |
welcome | +0.016 |
out | +0.015 |
Neg logit contributions | |
cases | -0.042 |
yles | -0.040 |
outing | -0.040 |
eling | -0.038 |
yle | -0.038 |
Token | pastry |
Token ID | 41738 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
age | +0.014 |
back | +0.013 |
right | +0.013 |
home | +0.012 |
welcome | +0.012 |
Neg logit contributions | |
yles | -0.015 |
cases | -0.014 |
ls | -0.013 |
yle | -0.013 |
outing | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +3.55e-03 |
Pos logit contributions | |
age | +0.022 |
back | +0.021 |
right | +0.020 |
home | +0.018 |
across | +0.018 |
Neg logit contributions | |
yles | -0.047 |
cases | -0.044 |
yle | -0.043 |
outing | -0.041 |
ls | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | -8.31e-03 |
Pos logit contributions | |
yles | +0.008 |
cases | +0.008 |
outing | +0.007 |
yle | +0.007 |
ls | +0.007 |
Neg logit contributions | |
back | -0.005 |
right | -0.004 |
across | -0.004 |
over | -0.004 |
welcome | -0.004 |
Token | note |
Token ID | 3465 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
age | +0.015 |
back | +0.013 |
welcome | +0.013 |
> | +0.013 |
home | +0.013 |
Neg logit contributions | |
yles | -0.013 |
cases | -0.013 |
ls | -0.012 |
yle | -0.012 |
salon | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +8.22e-03 |
Pos logit contributions | |
back | +0.017 |
right | +0.016 |
age | +0.014 |
across | +0.012 |
home | +0.012 |
Neg logit contributions | |
yles | -0.049 |
yle | -0.045 |
tant | -0.044 |
eling | -0.044 |
hairc | -0.043 |
Token | She |
Token ID | 1375 |
Feature activation | -7.75e-04 |
Pos logit contributions | |
yles | +0.017 |
cases | +0.016 |
ls | +0.015 |
yle | +0.015 |
salon | +0.015 |
Neg logit contributions | |
age | -0.012 |
back | -0.010 |
welcome | -0.010 |
> | -0.009 |
home | -0.009 |
Token | day |
Token ID | 1110 |
Feature activation | -2.67e-04 |
Pos logit contributions | |
age | +0.044 |
back | +0.029 |
> | +0.028 |
amed | +0.028 |
Follow | +0.027 |
Neg logit contributions | |
yles | -0.111 |
cases | -0.110 |
ls | -0.108 |
salon | -0.106 |
spill | -0.106 |
Token | , |
Token ID | 11 |
Feature activation | -5.96e-03 |
Pos logit contributions | |
age | +0.000 |
back | +0.000 |
welcome | +0.000 |
> | +0.000 |
home | +0.000 |
Neg logit contributions | |
yles | -0.001 |
cases | -0.001 |
yle | -0.001 |
ls | -0.001 |
salon | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
age | +0.007 |
back | +0.007 |
home | +0.007 |
right | +0.007 |
welcome | +0.007 |
Neg logit contributions | |
yles | -0.012 |
cases | -0.012 |
salon | -0.011 |
outing | -0.011 |
ls | -0.011 |
Token | little |
Token ID | 1310 |
Feature activation | +2.85e-03 |
Pos logit contributions | |
age | +0.044 |
> | +0.037 |
back | +0.037 |
welcome | +0.036 |
home | +0.036 |
Neg logit contributions | |
cases | -0.032 |
yles | -0.032 |
ls | -0.029 |
yle | -0.028 |
salon | -0.028 |
Token | boy |
Token ID | 2933 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
yles | +0.003 |
cases | +0.003 |
ls | +0.003 |
spill | +0.003 |
salon | +0.003 |
Neg logit contributions | |
age | -0.006 |
> | -0.005 |
amed | -0.005 |
Follow | -0.005 |
sy | -0.005 |
Token | decided |
Token ID | 3066 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
age | +0.045 |
back | +0.037 |
welcome | +0.037 |
> | +0.037 |
home | +0.036 |
Neg logit contributions | |
yles | -0.041 |
cases | -0.041 |
ls | -0.038 |
yle | -0.037 |
salon | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | +6.02e-03 |
Pos logit contributions | |
age | +0.038 |
back | +0.031 |
> | +0.030 |
welcome | +0.030 |
home | +0.030 |
Neg logit contributions | |
yles | -0.051 |
cases | -0.050 |
ls | -0.047 |
yle | -0.047 |
salon | -0.046 |
Token | try |
Token ID | 1949 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
yles | +0.011 |
cases | +0.011 |
yle | +0.010 |
salon | +0.010 |
ls | +0.010 |
Neg logit contributions | |
age | -0.009 |
back | -0.008 |
> | -0.008 |
welcome | -0.008 |
est | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -5.83e-03 |
Pos logit contributions | |
yles | +0.093 |
cases | +0.092 |
ls | +0.087 |
yle | +0.087 |
salon | +0.085 |
Neg logit contributions | |
age | -0.065 |
back | -0.053 |
> | -0.051 |
home | -0.051 |
welcome | -0.051 |
Token | count |
Token ID | 954 |
Feature activation | -3.17e-03 |
Pos logit contributions | |
age | +0.008 |
back | +0.007 |
welcome | +0.007 |
home | +0.007 |
> | +0.006 |
Neg logit contributions | |
yles | -0.012 |
cases | -0.012 |
ls | -0.011 |
yle | -0.011 |
outing | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
back | +0.004 |
age | +0.004 |
home | +0.004 |
right | +0.004 |
across | +0.004 |
Neg logit contributions | |
yles | -0.007 |
cases | -0.007 |
yle | -0.006 |
salon | -0.006 |
ls | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
yles | +0.001 |
cases | +0.001 |
outing | +0.001 |
yle | +0.001 |
ls | +0.001 |
Neg logit contributions | |
age | -0.001 |
back | -0.001 |
home | -0.001 |
right | -0.001 |
welcome | -0.001 |
Token | teacher |
Token ID | 4701 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
age | +0.025 |
back | +0.023 |
welcome | +0.022 |
right | +0.022 |
home | +0.022 |
Neg logit contributions | |
yles | -0.019 |
cases | -0.017 |
ries | -0.016 |
ls | -0.016 |
yle | -0.016 |
Token | wrote |
Token ID | 2630 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
yles | +0.033 |
outing | +0.031 |
yle | +0.030 |
ls | +0.030 |
ries | +0.029 |
Neg logit contributions | |
age | -0.030 |
back | -0.027 |
right | -0.026 |
home | -0.026 |
across | -0.024 |
Token | on |
Token ID | 319 |
Feature activation | +8.11e-04 |
Pos logit contributions | |
age | +0.020 |
back | +0.017 |
> | +0.015 |
home | +0.015 |
right | +0.015 |
Neg logit contributions | |
yles | -0.035 |
cases | -0.034 |
yle | -0.033 |
salon | -0.033 |
ls | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
yles | +0.002 |
cases | +0.002 |
yle | +0.002 |
ls | +0.002 |
outing | +0.002 |
Neg logit contributions | |
age | -0.001 |
back | -0.001 |
right | -0.001 |
home | -0.001 |
est | -0.001 |
Token | black |
Token ID | 2042 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
age | +0.022 |
back | +0.019 |
right | +0.018 |
welcome | +0.018 |
home | +0.018 |
Neg logit contributions | |
yles | -0.023 |
cases | -0.022 |
ls | -0.021 |
yle | -0.020 |
ries | -0.020 |
Token | board |
Token ID | 3526 |
Feature activation | +6.21e-03 |
Pos logit contributions | |
age | +0.031 |
back | +0.026 |
est | +0.026 |
welcome | +0.025 |
home | +0.025 |
Neg logit contributions | |
yles | -0.036 |
cases | -0.034 |
ls | -0.033 |
yle | -0.032 |
outing | -0.031 |
Token | with |
Token ID | 351 |
Feature activation | +7.62e-03 |
Pos logit contributions | |
yles | +0.013 |
cases | +0.012 |
yle | +0.012 |
ls | +0.012 |
salon | +0.011 |
Neg logit contributions | |
age | -0.009 |
back | -0.007 |
> | -0.007 |
welcome | -0.007 |
home | -0.007 |
Token | chalk |
Token ID | 30860 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
yles | +0.019 |
outing | +0.018 |
salon | +0.018 |
cases | +0.018 |
ls | +0.018 |
Neg logit contributions | |
age | -0.007 |
back | -0.007 |
home | -0.006 |
welcome | -0.006 |
right | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
yles | +0.092 |
yle | +0.084 |
cases | +0.084 |
eling | +0.083 |
outing | +0.082 |
Neg logit contributions | |
age | -0.051 |
back | -0.043 |
right | -0.040 |
home | -0.039 |
across | -0.037 |
Token | Lily |
Token ID | 20037 |
Feature activation | +5.32e-03 |
Pos logit contributions | |
yles | +0.005 |
cases | +0.005 |
ls | +0.004 |
yle | +0.004 |
salon | +0.004 |
Neg logit contributions | |
age | -0.004 |
back | -0.003 |
> | -0.003 |
welcome | -0.003 |
home | -0.003 |
Token | I |
Token ID | 314 |
Feature activation | -8.11e-03 |
Pos logit contributions | |
age | +0.017 |
back | +0.015 |
welcome | +0.015 |
home | +0.015 |
> | +0.015 |
Neg logit contributions | |
yles | -0.015 |
cases | -0.015 |
ls | -0.014 |
yle | -0.014 |
salon | -0.013 |
Token | want |
Token ID | 765 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
age | +0.014 |
welcome | +0.011 |
back | +0.011 |
> | +0.011 |
home | +0.011 |
Neg logit contributions | |
yles | -0.015 |
cases | -0.015 |
ls | -0.014 |
yle | -0.014 |
ries | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
age | +0.075 |
back | +0.066 |
home | +0.064 |
welcome | +0.061 |
right | +0.060 |
Neg logit contributions | |
yles | -0.123 |
cases | -0.121 |
yle | -0.114 |
ls | -0.113 |
outing | -0.112 |
Token | see |
Token ID | 766 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
yles | +0.020 |
cases | +0.019 |
ls | +0.018 |
yle | +0.018 |
outing | +0.017 |
Neg logit contributions | |
age | -0.016 |
back | -0.013 |
welcome | -0.013 |
home | -0.013 |
> | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -4.19e-04 |
Pos logit contributions | |
age | +0.017 |
back | +0.016 |
home | +0.015 |
right | +0.015 |
welcome | +0.015 |
Neg logit contributions | |
cases | -0.021 |
yles | -0.021 |
salon | -0.020 |
ls | -0.020 |
outing | -0.020 |
Token | Maybe |
Token ID | 6674 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
age | +0.001 |
est | +0.001 |
amed | +0.001 |
home | +0.001 |
> | +0.001 |
Neg logit contributions | |
cases | -0.001 |
yles | -0.001 |
salon | -0.001 |
yle | -0.001 |
hairc | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | +2.78e-03 |
Pos logit contributions | |
back | +0.136 |
age | +0.134 |
home | +0.132 |
right | +0.131 |
welcome | +0.127 |
Neg logit contributions | |
yles | -0.142 |
cases | -0.138 |
outing | -0.135 |
yle | -0.130 |
tant | -0.129 |
Token | is |
Token ID | 318 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
yles | +0.006 |
cases | +0.006 |
yle | +0.006 |
salon | +0.005 |
ls | +0.005 |
Neg logit contributions | |
age | -0.004 |
back | -0.003 |
right | -0.003 |
welcome | -0.003 |
est | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -1.41e-03 |
Pos logit contributions | |
age | +0.005 |
Follow | +0.004 |
est | +0.004 |
> | +0.004 |
amed | +0.004 |
Neg logit contributions | |
yles | -0.005 |
cases | -0.005 |
ls | -0.005 |
spill | -0.005 |
salon | -0.005 |
Token | doll |
Token ID | 3654 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
age | +0.002 |
amed | +0.002 |
> | +0.002 |
Follow | +0.002 |
est | +0.002 |
Neg logit contributions | |
yles | -0.002 |
salon | -0.002 |
cases | -0.002 |
spill | -0.002 |
ls | -0.002 |
Token | or |
Token ID | 393 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
age | +0.025 |
back | +0.020 |
> | +0.020 |
welcome | +0.020 |
home | +0.019 |
Neg logit contributions | |
yles | -0.036 |
cases | -0.036 |
ls | -0.033 |
yle | -0.033 |
salon | -0.033 |
Token | house |
Token ID | 4803 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
cases | +0.058 |
yles | +0.056 |
salon | +0.054 |
ls | +0.053 |
yle | +0.053 |
Neg logit contributions | |
age | -0.045 |
> | -0.037 |
welcome | -0.036 |
Follow | -0.036 |
amed | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e-03 |
Pos logit contributions | |
age | +0.072 |
> | +0.059 |
Follow | +0.057 |
welcome | +0.056 |
amed | +0.055 |
Neg logit contributions | |
cases | -0.089 |
yles | -0.086 |
ls | -0.082 |
salon | -0.081 |
yle | -0.080 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
age | +0.002 |
est | +0.001 |
sy | +0.001 |
back | +0.001 |
amed | +0.001 |
Neg logit contributions | |
cases | -0.002 |
yles | -0.002 |
ls | -0.002 |
yle | -0.002 |
ries | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
age | +0.021 |
est | +0.020 |
back | +0.018 |
welcome | +0.017 |
effect | +0.017 |
Neg logit contributions | |
yles | -0.022 |
cases | -0.022 |
ls | -0.020 |
yle | -0.020 |
l | -0.019 |
Token | Billy |
Token ID | 49640 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
age | +0.021 |
est | +0.019 |
back | +0.019 |
welcome | +0.019 |
home | +0.019 |
Neg logit contributions | |
cases | -0.022 |
yles | -0.021 |
ls | -0.019 |
yle | -0.019 |
outing | -0.019 |
Token | stamped |
Token ID | 28305 |
Feature activation | -9.80e-02 |
Pos logit contributions | |
age | +0.022 |
welcome | +0.019 |
back | +0.019 |
> | +0.018 |
home | +0.018 |
Neg logit contributions | |
cases | -0.016 |
yles | -0.016 |
ls | -0.015 |
yle | -0.014 |
salon | -0.014 |
Token | his |
Token ID | 465 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
age | +0.166 |
back | +0.137 |
> | +0.136 |
welcome | +0.135 |
home | +0.133 |
Neg logit contributions | |
yles | -0.174 |
cases | -0.171 |
ls | -0.160 |
yle | -0.159 |
salon | -0.156 |
Token | feet |
Token ID | 3625 |
Feature activation | +4.03e-03 |
Pos logit contributions | |
cases | +0.028 |
salon | +0.027 |
ls | +0.027 |
yles | +0.027 |
spill | +0.026 |
Neg logit contributions | |
age | -0.034 |
Follow | -0.029 |
welcome | -0.029 |
amed | -0.029 |
> | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | -3.98e-03 |
Pos logit contributions | |
cases | +0.008 |
yles | +0.007 |
salon | +0.007 |
ls | +0.007 |
yle | +0.007 |
Neg logit contributions | |
age | -0.006 |
welcome | -0.005 |
> | -0.005 |
Follow | -0.005 |
est | -0.005 |
Token | said |
Token ID | 531 |
Feature activation | -2.13e-03 |
Pos logit contributions | |
age | +0.008 |
back | +0.007 |
home | +0.007 |
right | +0.007 |
> | +0.007 |
Neg logit contributions | |
yles | -0.006 |
cases | -0.005 |
yle | -0.005 |
ls | -0.005 |
salon | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -4.46e-03 |
Pos logit contributions | |
age | +0.003 |
> | +0.002 |
welcome | +0.002 |
est | +0.002 |
Follow | +0.002 |
Neg logit contributions | |
cases | -0.004 |
yles | -0.004 |
ls | -0.004 |
yle | -0.004 |
salon | -0.004 |
Token | noise |
Token ID | 7838 |
Feature activation | +3.38e-03 |
Pos logit contributions | |
cases | +0.022 |
yles | +0.022 |
ls | +0.022 |
spill | +0.022 |
salon | +0.020 |
Neg logit contributions | |
age | -0.029 |
Follow | -0.026 |
> | -0.026 |
amed | -0.026 |
welcome | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -3.49e-03 |
Pos logit contributions | |
yles | +0.007 |
cases | +0.007 |
ls | +0.006 |
yle | +0.006 |
salon | +0.006 |
Neg logit contributions | |
age | -0.005 |
back | -0.004 |
> | -0.004 |
welcome | -0.004 |
home | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -8.95e-03 |
Pos logit contributions | |
age | +0.005 |
back | +0.004 |
welcome | +0.004 |
> | +0.004 |
home | +0.004 |
Neg logit contributions | |
yles | -0.007 |
cases | -0.007 |
ls | -0.007 |
yle | -0.007 |
salon | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -8.23e-03 |
Pos logit contributions | |
age | +0.012 |
back | +0.010 |
> | +0.009 |
welcome | +0.009 |
est | +0.009 |
Neg logit contributions | |
yles | -0.019 |
cases | -0.018 |
ls | -0.018 |
yle | -0.017 |
salon | -0.017 |
Token | " |
Token ID | 1 |
Feature activation | -6.97e-04 |
Pos logit contributions | |
age | +0.013 |
back | +0.010 |
> | +0.010 |
welcome | +0.010 |
home | +0.010 |
Neg logit contributions | |
yles | -0.016 |
cases | -0.016 |
ls | -0.015 |
yle | -0.015 |
salon | -0.014 |
Token | Crunch |
Token ID | 49384 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
age | +0.001 |
right | +0.001 |
back | +0.001 |
> | +0.001 |
amed | +0.001 |
Neg logit contributions | |
cases | -0.001 |
yles | -0.001 |
ls | -0.001 |
yle | -0.001 |
salon | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -5.28e-03 |
Pos logit contributions | |
age | +0.135 |
Follow | +0.111 |
back | +0.106 |
home | +0.104 |
> | +0.103 |
Neg logit contributions | |
ls | -0.158 |
ries | -0.154 |
cases | -0.152 |
yles | -0.147 |
spill | -0.143 |
Token | crunch |
Token ID | 23527 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
age | +0.009 |
welcome | +0.008 |
back | +0.008 |
right | +0.008 |
> | +0.007 |
Neg logit contributions | |
yles | -0.010 |
cases | -0.009 |
yle | -0.009 |
ls | -0.008 |
salon | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -4.14e-03 |
Pos logit contributions | |
age | +0.021 |
back | +0.017 |
> | +0.017 |
welcome | +0.017 |
home | +0.017 |
Neg logit contributions | |
yles | -0.026 |
cases | -0.026 |
ls | -0.025 |
yle | -0.024 |
ries | -0.024 |
Token | crunch |
Token ID | 23527 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
age | +0.007 |
back | +0.006 |
welcome | +0.006 |
right | +0.006 |
> | +0.006 |
Neg logit contributions | |
yles | -0.007 |
cases | -0.007 |
yle | -0.007 |
salon | -0.007 |
ls | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +3.86e-03 |
Pos logit contributions | |
age | +0.020 |
back | +0.016 |
> | +0.016 |
welcome | +0.016 |
home | +0.016 |
Neg logit contributions | |
yles | -0.025 |
cases | -0.025 |
ls | -0.024 |
yle | -0.023 |
salon | -0.023 |
Token | dream |
Token ID | 4320 |
Feature activation | -7.85e-03 |
Pos logit contributions | |
age | +0.045 |
amed | +0.040 |
> | +0.037 |
Follow | +0.037 |
back | +0.036 |
Neg logit contributions | |
cases | -0.062 |
yles | -0.061 |
salon | -0.060 |
ls | -0.058 |
hairc | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -1.30e-03 |
Pos logit contributions | |
age | +0.010 |
back | +0.008 |
> | +0.008 |
welcome | +0.008 |
home | +0.008 |
Neg logit contributions | |
yles | -0.017 |
cases | -0.017 |
ls | -0.016 |
yle | -0.015 |
salon | -0.015 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
age | +0.002 |
back | +0.002 |
> | +0.002 |
welcome | +0.002 |
home | +0.002 |
Neg logit contributions | |
yles | -0.002 |
cases | -0.002 |
ls | -0.002 |
yle | -0.002 |
salon | -0.002 |
Token | my |
Token ID | 1820 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
yles | +0.032 |
ries | +0.031 |
salon | +0.031 |
spill | +0.030 |
cases | +0.030 |
Neg logit contributions | |
age | -0.025 |
Follow | -0.023 |
amed | -0.021 |
> | -0.020 |
across | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e-03 |
Pos logit contributions | |
age | +0.037 |
amed | +0.032 |
> | +0.031 |
Follow | +0.031 |
welcome | +0.029 |
Neg logit contributions | |
yles | -0.040 |
cases | -0.039 |
ls | -0.037 |
yle | -0.037 |
hairc | -0.036 |
Token | Maybe |
Token ID | 6674 |
Feature activation | -8.53e-02 |
Pos logit contributions | |
yles | +0.002 |
cases | +0.002 |
yle | +0.002 |
hairc | +0.002 |
salon | +0.002 |
Neg logit contributions | |
age | -0.002 |
amed | -0.002 |
home | -0.002 |
> | -0.002 |
back | -0.002 |
Token | we |
Token ID | 356 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
age | +0.129 |
back | +0.115 |
home | +0.112 |
welcome | +0.112 |
right | +0.110 |
Neg logit contributions | |
cases | -0.159 |
yles | -0.158 |
outing | -0.148 |
ls | -0.148 |
salon | -0.146 |
Token | can |
Token ID | 460 |
Feature activation | +6.61e-03 |
Pos logit contributions | |
age | +0.040 |
back | +0.033 |
welcome | +0.033 |
> | +0.033 |
home | +0.032 |
Neg logit contributions | |
yles | -0.042 |
cases | -0.042 |
ls | -0.039 |
yle | -0.039 |
salon | -0.038 |
Token | find |
Token ID | 1064 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
yles | +0.012 |
cases | +0.012 |
yle | +0.011 |
salon | +0.011 |
ls | +0.011 |
Neg logit contributions | |
age | -0.010 |
> | -0.008 |
back | -0.008 |
welcome | -0.008 |
est | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -5.09e-04 |
Pos logit contributions | |
age | +0.049 |
> | +0.038 |
back | +0.037 |
welcome | +0.037 |
est | +0.036 |
Neg logit contributions | |
yles | -0.065 |
cases | -0.064 |
ls | -0.060 |
yle | -0.060 |
salon | -0.058 |
Token | book |
Token ID | 1492 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
age | +0.001 |
> | +0.001 |
amed | +0.001 |
est | +0.001 |
Follow | +0.001 |
Neg logit contributions | |
yles | -0.001 |
cases | -0.001 |
salon | -0.001 |
yle | -0.001 |
hairc | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
age | +0.030 |
back | +0.024 |
> | +0.023 |
welcome | +0.023 |
home | +0.023 |
Neg logit contributions | |
yles | -0.042 |
cases | -0.041 |
ls | -0.039 |
yle | -0.039 |
salon | -0.038 |
Token | them |
Token ID | 606 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
cases | +0.035 |
yles | +0.034 |
outing | +0.032 |
ls | +0.031 |
ries | +0.031 |
Neg logit contributions | |
back | -0.031 |
age | -0.030 |
welcome | -0.029 |
home | -0.029 |
right | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +8.71e-03 |
Pos logit contributions | |
cases | +0.026 |
yles | +0.025 |
ls | +0.024 |
yle | +0.023 |
salon | +0.023 |
Neg logit contributions | |
age | -0.028 |
amed | -0.023 |
welcome | -0.022 |
est | -0.022 |
> | -0.022 |
Token | He |
Token ID | 679 |
Feature activation | +8.22e-03 |
Pos logit contributions | |
yles | +0.022 |
cases | +0.021 |
yle | +0.020 |
salon | +0.020 |
ries | +0.020 |
Neg logit contributions | |
age | -0.009 |
back | -0.007 |
welcome | -0.007 |
Follow | -0.006 |
right | -0.006 |
Token | w |
Token ID | 266 |
Feature activation | +6.92e-02 |
Pos logit contributions | |
yles | +0.014 |
cases | +0.014 |
yle | +0.014 |
outing | +0.013 |
salon | +0.012 |
Neg logit contributions | |
back | -0.013 |
age | -0.013 |
right | -0.012 |
Follow | -0.012 |
welcome | -0.012 |
Token | ags |
Token ID | 3775 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
yles | +0.179 |
cases | +0.177 |
yle | +0.168 |
ls | +0.168 |
salon | +0.166 |
Neg logit contributions | |
age | -0.062 |
back | -0.042 |
welcome | -0.040 |
> | -0.040 |
home | -0.039 |
Token | his |
Token ID | 465 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
age | +0.126 |
back | +0.115 |
home | +0.108 |
welcome | +0.103 |
right | +0.101 |
Neg logit contributions | |
cases | -0.201 |
yles | -0.198 |
salon | -0.183 |
yle | -0.182 |
ls | -0.182 |
Token | tail |
Token ID | 7894 |
Feature activation | -6.11e-03 |
Pos logit contributions | |
ls | +0.046 |
cases | +0.046 |
salon | +0.046 |
yles | +0.045 |
wra | +0.045 |
Neg logit contributions | |
age | -0.036 |
Follow | -0.031 |
wood | -0.031 |
day | -0.028 |
sy | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +8.64e-03 |
Pos logit contributions | |
age | +0.011 |
> | +0.009 |
Follow | +0.009 |
amed | +0.009 |
welcome | +0.009 |
Neg logit contributions | |
cases | -0.009 |
ls | -0.008 |
yles | -0.008 |
salon | -0.008 |
outing | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.96e-03 |
Pos logit contributions | |
yles | +0.020 |
cases | +0.020 |
yle | +0.019 |
salon | +0.019 |
ls | +0.018 |
Neg logit contributions | |
age | -0.010 |
back | -0.008 |
welcome | -0.008 |
> | -0.008 |
home | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
age | +0.003 |
est | +0.002 |
back | +0.002 |
> | +0.002 |
welcome | +0.002 |
Neg logit contributions | |
yles | -0.004 |
cases | -0.004 |
ls | -0.004 |
yle | -0.004 |
salon | -0.004 |