Token | made |
Token ID | 925 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
boy | +0.027 |
girl | +0.026 |
Year | +0.023 |
extingu | +0.023 |
asleep | +0.023 |
Neg logit contributions | |
vern | -0.017 |
aches | -0.017 |
earned | -0.016 |
imes | -0.015 |
fters | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +7.60e-03 |
Pos logit contributions | |
boy | +0.040 |
girl | +0.038 |
extingu | +0.037 |
Year | +0.036 |
ksh | +0.034 |
Neg logit contributions | |
vern | -0.028 |
aches | -0.028 |
ons | -0.026 |
gh | -0.026 |
ag | -0.025 |
Token | |
Token ID | 220 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
boy | +0.015 |
girl | +0.014 |
extingu | +0.013 |
Year | +0.013 |
asleep | +0.012 |
Neg logit contributions | |
vern | -0.011 |
aches | -0.011 |
earned | -0.011 |
imes | -0.011 |
ough | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
vern | +0.019 |
aches | +0.019 |
earned | +0.018 |
imes | +0.018 |
ending | +0.017 |
Neg logit contributions | |
boy | -0.019 |
girl | -0.018 |
Year | -0.016 |
extingu | -0.016 |
asleep | -0.015 |
Token | The |
Token ID | 464 |
Feature activation | +9.34e-03 |
Pos logit contributions | |
aches | +0.032 |
vern | +0.032 |
earned | +0.031 |
iable | +0.030 |
imes | +0.030 |
Neg logit contributions | |
boy | -0.035 |
girl | -0.033 |
Year | -0.030 |
asleep | -0.028 |
extingu | -0.028 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
extingu | +0.019 |
ksh | +0.018 |
ucks | +0.018 |
asleep | +0.018 |
Year | +0.018 |
Neg logit contributions | |
aches | -0.012 |
Days | -0.011 |
vern | -0.011 |
exercise | -0.010 |
isky | -0.010 |
Token | maid |
Token ID | 23151 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
boy | +0.155 |
extingu | +0.147 |
Sn | +0.143 |
girl | +0.132 |
Year | +0.124 |
Neg logit contributions | |
aches | -0.353 |
ag | -0.344 |
ending | -0.342 |
gh | -0.329 |
ying | -0.328 |
Token | learnt |
Token ID | 26338 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
boy | +0.083 |
girl | +0.078 |
extingu | +0.077 |
Year | +0.076 |
ksh | +0.073 |
Neg logit contributions | |
aches | -0.075 |
vern | -0.070 |
hardly | -0.068 |
ons | -0.066 |
ending | -0.066 |
Token | that |
Token ID | 326 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
vern | +0.073 |
aches | +0.073 |
earned | +0.067 |
imes | +0.067 |
fters | +0.067 |
Neg logit contributions | |
boy | -0.088 |
girl | -0.084 |
Year | -0.076 |
extingu | -0.076 |
asleep | -0.074 |
Token | taking |
Token ID | 2263 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
boy | +0.118 |
extingu | +0.114 |
Year | +0.112 |
girl | +0.112 |
ksh | +0.112 |
Neg logit contributions | |
vern | -0.073 |
aches | -0.072 |
achieve | -0.066 |
ending | -0.065 |
earned | -0.064 |
Token | risks |
Token ID | 7476 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
boy | +0.046 |
girl | +0.043 |
extingu | +0.042 |
Year | +0.042 |
ksh | +0.041 |
Neg logit contributions | |
aches | -0.020 |
vern | -0.020 |
earned | -0.018 |
ag | -0.018 |
ough | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
boy | +0.029 |
girl | +0.027 |
Year | +0.027 |
extingu | +0.027 |
ksh | +0.026 |
Neg logit contributions | |
aches | -0.021 |
vern | -0.021 |
accomplished | -0.019 |
hardly | -0.019 |
earned | -0.019 |
Token | so |
Token ID | 523 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
boy | +0.026 |
girl | +0.025 |
extingu | +0.024 |
Year | +0.024 |
ksh | +0.022 |
Neg logit contributions | |
vern | -0.019 |
aches | -0.019 |
gh | -0.017 |
earned | -0.017 |
iable | -0.017 |
Token | thankful |
Token ID | 25535 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
vern | +0.034 |
aches | +0.033 |
ending | +0.030 |
earned | +0.030 |
accomplished | +0.029 |
Neg logit contributions | |
boy | -0.041 |
girl | -0.039 |
Year | -0.038 |
extingu | -0.038 |
ksh | -0.035 |
Token | that |
Token ID | 326 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
boy | +0.084 |
girl | +0.080 |
Year | +0.077 |
extingu | +0.075 |
ksh | +0.072 |
Neg logit contributions | |
vern | -0.055 |
aches | -0.055 |
earned | -0.049 |
gh | -0.048 |
ending | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +1.52e-03 |
Pos logit contributions | |
boy | +0.126 |
girl | +0.122 |
Year | +0.121 |
extingu | +0.120 |
ksh | +0.116 |
Neg logit contributions | |
aches | -0.056 |
vern | -0.053 |
gh | -0.046 |
earned | -0.046 |
imes | -0.045 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ksh | +0.003 |
extingu | +0.003 |
ucks | +0.002 |
Year | +0.002 |
ASH | +0.002 |
Neg logit contributions | |
vern | -0.002 |
aches | -0.002 |
gh | -0.002 |
important | -0.002 |
extraordinary | -0.002 |
Token | maid |
Token ID | 23151 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
extingu | +0.166 |
boy | +0.164 |
Sn | +0.163 |
ASH | +0.153 |
girl | +0.152 |
Neg logit contributions | |
aches | -0.320 |
ag | -0.315 |
gh | -0.303 |
vern | -0.299 |
hardly | -0.295 |
Token | had |
Token ID | 550 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
boy | +0.072 |
girl | +0.069 |
Year | +0.066 |
extingu | +0.066 |
ksh | +0.062 |
Neg logit contributions | |
aches | -0.057 |
vern | -0.056 |
earned | -0.052 |
ending | -0.051 |
ons | -0.050 |
Token | forgiven |
Token ID | 32350 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
aches | +0.022 |
vern | +0.022 |
imes | +0.021 |
fters | +0.021 |
affles | +0.021 |
Neg logit contributions | |
boy | -0.026 |
girl | -0.025 |
asleep | -0.022 |
Year | -0.021 |
extingu | -0.021 |
Token | him |
Token ID | 683 |
Feature activation | +4.73e-03 |
Pos logit contributions | |
boy | +0.039 |
girl | +0.037 |
Year | +0.036 |
extingu | +0.035 |
asleep | +0.033 |
Neg logit contributions | |
aches | -0.021 |
vern | -0.021 |
gh | -0.019 |
earned | -0.019 |
imes | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
boy | +0.009 |
girl | +0.009 |
Year | +0.008 |
extingu | +0.008 |
ksh | +0.007 |
Neg logit contributions | |
vern | -0.007 |
aches | -0.007 |
earned | -0.007 |
gh | -0.007 |
achieve | -0.007 |
Token | again |
Token ID | 757 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
boy | +0.124 |
girl | +0.119 |
Year | +0.113 |
extingu | +0.112 |
asleep | +0.107 |
Neg logit contributions | |
vern | -0.067 |
aches | -0.067 |
earned | -0.060 |
gh | -0.058 |
ending | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +9.53e-03 |
Pos logit contributions | |
boy | +0.079 |
girl | +0.075 |
Year | +0.073 |
extingu | +0.071 |
ksh | +0.068 |
Neg logit contributions | |
vern | -0.058 |
aches | -0.058 |
earned | -0.053 |
achieve | -0.053 |
gh | -0.052 |
Token | He |
Token ID | 679 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
boy | +0.017 |
girl | +0.015 |
Year | +0.014 |
extingu | +0.014 |
asleep | +0.013 |
Neg logit contributions | |
aches | -0.017 |
vern | -0.017 |
fters | -0.016 |
earned | -0.016 |
iable | -0.015 |
Token | said |
Token ID | 531 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
extingu | +0.032 |
boy | +0.031 |
Year | +0.031 |
girl | +0.031 |
ksh | +0.030 |
Neg logit contributions | |
aches | -0.021 |
accomplished | -0.020 |
hardly | -0.020 |
vern | -0.019 |
achieved | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +5.62e-03 |
Pos logit contributions | |
boy | +0.022 |
girl | +0.021 |
extingu | +0.020 |
Year | +0.020 |
ksh | +0.019 |
Neg logit contributions | |
vern | -0.016 |
aches | -0.016 |
gh | -0.015 |
earned | -0.015 |
ending | -0.015 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
extingu | +0.012 |
ksh | +0.011 |
ucks | +0.011 |
cy | +0.011 |
boy | +0.011 |
Neg logit contributions | |
vern | -0.007 |
aches | -0.007 |
gh | -0.006 |
achieve | -0.006 |
accomplished | -0.006 |
Token | maid |
Token ID | 23151 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
boy | +0.160 |
Sn | +0.142 |
extingu | +0.141 |
girl | +0.137 |
Year | +0.124 |
Neg logit contributions | |
aches | -0.339 |
gh | -0.334 |
ag | -0.334 |
vern | -0.320 |
ending | -0.316 |
Token | and |
Token ID | 290 |
Feature activation | +4.43e-03 |
Pos logit contributions | |
boy | +0.075 |
girl | +0.071 |
Year | +0.066 |
extingu | +0.065 |
asleep | +0.062 |
Neg logit contributions | |
vern | -0.070 |
aches | -0.070 |
earned | -0.065 |
imes | -0.064 |
ending | -0.064 |
Token | a |
Token ID | 257 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
ksh | +0.009 |
Year | +0.009 |
extingu | +0.009 |
boy | +0.008 |
cy | +0.008 |
Neg logit contributions | |
aches | -0.006 |
ons | -0.005 |
accomplished | -0.005 |
hardly | -0.005 |
achieved | -0.005 |
Token | dolphin |
Token ID | 44136 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
Year | +0.052 |
ksh | +0.051 |
ucks | +0.050 |
extingu | +0.049 |
ASH | +0.049 |
Neg logit contributions | |
vern | -0.042 |
aches | -0.037 |
achieve | -0.037 |
accomplished | -0.035 |
capable | -0.035 |
Token | were |
Token ID | 547 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
boy | +0.081 |
Year | +0.076 |
girl | +0.076 |
extingu | +0.073 |
ksh | +0.072 |
Neg logit contributions | |
vern | -0.066 |
aches | -0.065 |
ending | -0.060 |
ag | -0.060 |
gh | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-03 |
Pos logit contributions | |
boy | +0.005 |
girl | +0.004 |
extingu | +0.004 |
Year | +0.004 |
asleep | +0.004 |
Neg logit contributions | |
vern | -0.003 |
aches | -0.003 |
gh | -0.003 |
iable | -0.003 |
earned | -0.003 |
Token | The |
Token ID | 383 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
ough | +0.002 |
vern | +0.002 |
earned | +0.002 |
imes | +0.002 |
ending | +0.002 |
Neg logit contributions | |
boy | -0.002 |
girl | -0.002 |
extingu | -0.002 |
asleep | -0.002 |
Year | -0.002 |
Token | more |
Token ID | 517 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
aches | +0.025 |
vern | +0.024 |
exercise | +0.022 |
fters | +0.022 |
imes | +0.022 |
Neg logit contributions | |
ksh | -0.022 |
ucks | -0.022 |
extingu | -0.021 |
asleep | -0.020 |
cy | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -7.19e-03 |
Pos logit contributions | |
aches | +0.045 |
vern | +0.040 |
ons | +0.040 |
ade | +0.038 |
imes | +0.038 |
Neg logit contributions | |
extingu | -0.048 |
ksh | -0.048 |
boy | -0.046 |
Year | -0.044 |
asleep | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | -5.90e-03 |
Pos logit contributions | |
aches | +0.010 |
fters | +0.009 |
ough | +0.009 |
imes | +0.009 |
achieve | +0.009 |
Neg logit contributions | |
extingu | -0.013 |
Year | -0.013 |
ksh | -0.013 |
boy | -0.013 |
ucks | -0.012 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
aches | +0.010 |
vern | +0.009 |
capable | +0.008 |
exercise | +0.008 |
fters | +0.008 |
Neg logit contributions | |
ucks | -0.010 |
ksh | -0.010 |
extingu | -0.010 |
Year | -0.009 |
eddy | -0.008 |
Token | rier |
Token ID | 5277 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
Sn | +0.170 |
extingu | +0.168 |
boy | +0.166 |
girl | +0.144 |
Smith | +0.142 |
Neg logit contributions | |
aches | -0.331 |
ag | -0.316 |
gh | -0.293 |
inations | -0.293 |
ying | -0.292 |
Token | . |
Token ID | 13 |
Feature activation | +6.32e-03 |
Pos logit contributions | |
ksh | +0.139 |
Year | +0.137 |
boy | +0.135 |
extingu | +0.130 |
girl | +0.128 |
Neg logit contributions | |
aches | -0.124 |
vern | -0.110 |
earned | -0.106 |
gh | -0.103 |
ons | -0.102 |
Token | Come |
Token ID | 7911 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
boy | +0.012 |
girl | +0.012 |
extingu | +0.010 |
Year | +0.010 |
asleep | +0.010 |
Neg logit contributions | |
vern | -0.009 |
ough | -0.009 |
imes | -0.009 |
achieve | -0.008 |
earned | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -9.52e-03 |
Pos logit contributions | |
boy | +0.084 |
girl | +0.080 |
extingu | +0.076 |
Year | +0.075 |
ksh | +0.075 |
Neg logit contributions | |
aches | -0.066 |
vern | -0.065 |
achieve | -0.064 |
ough | -0.064 |
gh | -0.062 |
Token | my |
Token ID | 616 |
Feature activation | -2.26e-03 |
Pos logit contributions | |
aches | +0.014 |
vern | +0.014 |
ag | +0.013 |
achieve | +0.013 |
iable | +0.012 |
Neg logit contributions | |
boy | -0.019 |
girl | -0.018 |
Year | -0.016 |
extingu | -0.016 |
ksh | -0.016 |
Token | telling |
Token ID | 5149 |
Feature activation | -1.30e-03 |
Pos logit contributions | |
boy | +0.005 |
girl | +0.004 |
extingu | +0.004 |
Year | +0.004 |
ksh | +0.004 |
Neg logit contributions | |
aches | -0.004 |
vern | -0.004 |
supposed | -0.003 |
accomplished | -0.003 |
gh | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
vern | +0.002 |
aches | +0.002 |
earned | +0.002 |
imes | +0.002 |
ending | +0.002 |
Neg logit contributions | |
boy | -0.002 |
girl | -0.002 |
Year | -0.002 |
extingu | -0.002 |
asleep | -0.002 |
Token | story |
Token ID | 1621 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
boy | +0.034 |
girl | +0.032 |
extingu | +0.030 |
Year | +0.030 |
asleep | +0.029 |
Neg logit contributions | |
vern | -0.026 |
aches | -0.026 |
earned | -0.023 |
gh | -0.023 |
ending | -0.023 |
Token | about |
Token ID | 546 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
boy | +0.122 |
girl | +0.117 |
extingu | +0.108 |
Year | +0.106 |
asleep | +0.105 |
Neg logit contributions | |
aches | -0.063 |
vern | -0.062 |
earned | -0.056 |
fters | -0.055 |
imes | -0.055 |
Token | a |
Token ID | 257 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
boy | +0.057 |
girl | +0.054 |
extingu | +0.050 |
Year | +0.050 |
ksh | +0.048 |
Neg logit contributions | |
aches | -0.052 |
vern | -0.051 |
earned | -0.047 |
imes | -0.047 |
ons | -0.046 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
extingu | +0.037 |
ucks | +0.036 |
ksh | +0.036 |
boy | +0.035 |
Year | +0.034 |
Neg logit contributions | |
vern | -0.026 |
gh | -0.024 |
aches | -0.023 |
achieve | -0.023 |
capable | -0.022 |
Token | maid |
Token ID | 23151 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
boy | +0.157 |
Sn | +0.152 |
extingu | +0.151 |
girl | +0.139 |
Year | +0.126 |
Neg logit contributions | |
ag | -0.329 |
aches | -0.327 |
gh | -0.319 |
hardly | -0.308 |
vern | -0.302 |
Token | who |
Token ID | 508 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
boy | +0.062 |
girl | +0.058 |
Year | +0.055 |
extingu | +0.054 |
ASH | +0.051 |
Neg logit contributions | |
aches | -0.055 |
vern | -0.054 |
imes | -0.051 |
ending | -0.051 |
earned | -0.051 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
boy | +0.036 |
girl | +0.034 |
extingu | +0.033 |
Year | +0.033 |
ksh | +0.032 |
Neg logit contributions | |
aches | -0.028 |
vern | -0.027 |
ons | -0.025 |
accomplished | -0.025 |
ending | -0.025 |
Token | in |
Token ID | 287 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
boy | +0.018 |
extingu | +0.018 |
girl | +0.017 |
Year | +0.017 |
ksh | +0.016 |
Neg logit contributions | |
vern | -0.018 |
aches | -0.018 |
gh | -0.017 |
accomplished | -0.017 |
ag | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e-03 |
Pos logit contributions | |
boy | +0.032 |
girl | +0.031 |
ksh | +0.031 |
Year | +0.029 |
extingu | +0.029 |
Neg logit contributions | |
vern | -0.021 |
aches | -0.019 |
achieve | -0.019 |
ons | -0.019 |
accomplished | -0.019 |
Token | in |
Token ID | 287 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
ksh | +0.002 |
boy | +0.002 |
ucks | +0.002 |
girl | +0.002 |
cash | +0.002 |
Neg logit contributions | |
accomplished | -0.001 |
achieved | -0.001 |
aches | -0.001 |
achieve | -0.001 |
ag | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +9.30e-04 |
Pos logit contributions | |
boy | +0.042 |
ksh | +0.041 |
girl | +0.040 |
Claus | +0.037 |
extingu | +0.037 |
Neg logit contributions | |
aches | -0.021 |
vern | -0.019 |
accomplished | -0.019 |
ons | -0.018 |
achieved | -0.018 |
Token | sea |
Token ID | 5417 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
extingu | +0.002 |
boy | +0.002 |
ksh | +0.002 |
ucks | +0.001 |
girl | +0.001 |
Neg logit contributions | |
aches | -0.001 |
accomplished | -0.001 |
achieve | -0.001 |
vern | -0.001 |
earned | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
boy | +0.065 |
girl | +0.062 |
extingu | +0.061 |
Year | +0.061 |
ksh | +0.059 |
Neg logit contributions | |
aches | -0.045 |
vern | -0.044 |
achieve | -0.041 |
accomplished | -0.040 |
ough | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +1.80e-03 |
Pos logit contributions | |
boy | +0.095 |
girl | +0.092 |
extingu | +0.091 |
Year | +0.091 |
ksh | +0.086 |
Neg logit contributions | |
aches | -0.082 |
vern | -0.076 |
accomplished | -0.075 |
gh | -0.073 |
ons | -0.072 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
extingu | +0.004 |
ksh | +0.003 |
ucks | +0.003 |
Sn | +0.003 |
asleep | +0.003 |
Neg logit contributions | |
aches | -0.003 |
accomplished | -0.002 |
extraordinary | -0.002 |
achieve | -0.002 |
ough | -0.002 |
Token | maid |
Token ID | 23151 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
extingu | +0.167 |
boy | +0.166 |
Sn | +0.163 |
girl | +0.149 |
cash | +0.128 |
Neg logit contributions | |
aches | -0.342 |
ag | -0.324 |
hardly | -0.315 |
ade | -0.314 |
gh | -0.305 |
Token | carefully |
Token ID | 7773 |
Feature activation | -1.32e-03 |
Pos logit contributions | |
boy | +0.079 |
girl | +0.075 |
extingu | +0.072 |
Year | +0.071 |
ksh | +0.067 |
Neg logit contributions | |
aches | -0.057 |
vern | -0.055 |
ending | -0.051 |
earned | -0.050 |
ons | -0.050 |
Token | chose |
Token ID | 7690 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
aches | +0.002 |
vern | +0.002 |
earned | +0.002 |
gh | +0.002 |
ag | +0.002 |
Neg logit contributions | |
boy | -0.002 |
girl | -0.002 |
Year | -0.002 |
extingu | -0.002 |
ksh | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +8.52e-03 |
Pos logit contributions | |
aches | +0.027 |
vern | +0.026 |
earned | +0.024 |
imes | +0.023 |
gh | +0.023 |
Neg logit contributions | |
boy | -0.036 |
girl | -0.034 |
Year | -0.032 |
extingu | -0.031 |
ksh | -0.030 |
Token | It |
Token ID | 632 |
Feature activation | -7.82e-04 |
Pos logit contributions | |
boy | +0.017 |
girl | +0.017 |
extingu | +0.016 |
Year | +0.016 |
maid | +0.015 |
Neg logit contributions | |
imes | -0.011 |
vern | -0.011 |
ough | -0.010 |
earned | -0.010 |
aches | -0.010 |
Token | " |
Token ID | 366 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
boy | +0.013 |
extingu | +0.013 |
Year | +0.013 |
girl | +0.013 |
ksh | +0.013 |
Neg logit contributions | |
vern | -0.009 |
achieve | -0.009 |
hardly | -0.008 |
accomplished | -0.008 |
iable | -0.008 |
Token | I |
Token ID | 40 |
Feature activation | +1.37e-03 |
Pos logit contributions | |
boy | +0.053 |
girl | +0.049 |
extingu | +0.048 |
tent | +0.048 |
Year | +0.047 |
Neg logit contributions | |
ending | -0.043 |
earned | -0.043 |
vern | -0.041 |
aches | -0.041 |
achieve | -0.041 |
Token | 'm |
Token ID | 1101 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
boy | +0.003 |
girl | +0.003 |
Year | +0.003 |
ksh | +0.003 |
extingu | +0.003 |
Neg logit contributions | |
vern | -0.001 |
aches | -0.001 |
expect | -0.001 |
hardly | -0.001 |
earned | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
boy | +0.065 |
girl | +0.061 |
ksh | +0.058 |
Year | +0.056 |
cy | +0.056 |
Neg logit contributions | |
supposed | -0.048 |
vern | -0.048 |
aches | -0.046 |
hardly | -0.045 |
imes | -0.044 |
Token | secret |
Token ID | 3200 |
Feature activation | -7.01e-03 |
Pos logit contributions | |
ucks | +0.038 |
ipt | +0.033 |
ksh | +0.033 |
ASH | +0.032 |
ays | +0.032 |
Neg logit contributions | |
vern | -0.023 |
daring | -0.023 |
else | -0.021 |
capable | -0.021 |
gh | -0.021 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
vern | +0.011 |
aches | +0.010 |
supposed | +0.010 |
ade | +0.010 |
else | +0.010 |
Neg logit contributions | |
ksh | -0.012 |
ASH | -0.011 |
ucks | -0.011 |
Year | -0.010 |
boy | -0.010 |
Token | maid |
Token ID | 23151 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
boy | +0.169 |
Sn | +0.164 |
girl | +0.158 |
Year | +0.149 |
asleep | +0.139 |
Neg logit contributions | |
gh | -0.305 |
ag | -0.303 |
aches | -0.294 |
vern | -0.294 |
ovable | -0.284 |
Token | . |
Token ID | 13 |
Feature activation | +7.30e-03 |
Pos logit contributions | |
boy | +0.072 |
Year | +0.068 |
extingu | +0.067 |
girl | +0.066 |
ASH | +0.065 |
Neg logit contributions | |
aches | -0.055 |
vern | -0.055 |
ending | -0.053 |
imes | -0.051 |
earned | -0.051 |
Token | Would |
Token ID | 10928 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
boy | +0.014 |
girl | +0.013 |
extingu | +0.013 |
Year | +0.013 |
asleep | +0.012 |
Neg logit contributions | |
earned | -0.010 |
ending | -0.009 |
vern | -0.009 |
ough | -0.009 |
imes | -0.009 |
Token | you |
Token ID | 345 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
boy | +0.031 |
girl | +0.029 |
Year | +0.027 |
extingu | +0.026 |
asleep | +0.026 |
Neg logit contributions | |
vern | -0.021 |
aches | -0.021 |
earned | -0.019 |
imes | -0.019 |
ending | -0.018 |
Token | like |
Token ID | 588 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
vern | +0.017 |
aches | +0.017 |
earned | +0.016 |
imes | +0.015 |
ending | +0.015 |
Neg logit contributions | |
boy | -0.026 |
girl | -0.025 |
Year | -0.023 |
extingu | -0.023 |
asleep | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
boy | +0.074 |
girl | +0.073 |
extingu | +0.072 |
Year | +0.069 |
ksh | +0.069 |
Neg logit contributions | |
aches | -0.066 |
vern | -0.063 |
accomplished | -0.059 |
achieve | -0.058 |
earned | -0.058 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
boy | +0.037 |
girl | +0.036 |
Year | +0.033 |
extingu | +0.033 |
ksh | +0.031 |
Neg logit contributions | |
vern | -0.027 |
aches | -0.027 |
ag | -0.023 |
gh | -0.023 |
earned | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
vern | +0.016 |
aches | +0.015 |
ending | +0.014 |
hardly | +0.014 |
accomplished | +0.014 |
Neg logit contributions | |
boy | -0.021 |
Year | -0.021 |
girl | -0.021 |
extingu | -0.020 |
ksh | -0.020 |
Token | sailed |
Token ID | 33835 |
Feature activation | +6.01e-02 |
Pos logit contributions | |
boy | +0.019 |
girl | +0.019 |
Year | +0.018 |
extingu | +0.018 |
asleep | +0.016 |
Neg logit contributions | |
vern | -0.016 |
aches | -0.015 |
earned | -0.014 |
accomplished | -0.014 |
ending | -0.014 |
Token | away |
Token ID | 1497 |
Feature activation | +6.86e-03 |
Pos logit contributions | |
boy | +0.105 |
Year | +0.102 |
girl | +0.101 |
extingu | +0.099 |
ksh | +0.094 |
Neg logit contributions | |
vern | -0.097 |
aches | -0.095 |
ag | -0.094 |
gh | -0.092 |
accomplished | -0.088 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
boy | +0.013 |
Year | +0.013 |
girl | +0.013 |
ksh | +0.012 |
extingu | +0.012 |
Neg logit contributions | |
vern | -0.010 |
aches | -0.009 |
accomplished | -0.009 |
achieve | -0.009 |
gh | -0.008 |
Token | rily |
Token ID | 28904 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
boy | +0.192 |
girl | +0.187 |
extingu | +0.166 |
Year | +0.155 |
Sn | +0.151 |
Neg logit contributions | |
aches | -0.322 |
ag | -0.307 |
gh | -0.298 |
vern | -0.297 |
hardly | -0.294 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
boy | +0.061 |
girl | +0.058 |
Year | +0.056 |
extingu | +0.055 |
ksh | +0.053 |
Neg logit contributions | |
aches | -0.051 |
vern | -0.050 |
gh | -0.048 |
earned | -0.046 |
ag | -0.045 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
boy | +0.033 |
girl | +0.032 |
Year | +0.030 |
extingu | +0.030 |
asleep | +0.028 |
Neg logit contributions | |
vern | -0.028 |
aches | -0.027 |
earned | -0.026 |
imes | -0.025 |
ending | -0.025 |
Token | Once |
Token ID | 7454 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
boy | +0.122 |
girl | +0.122 |
extingu | +0.121 |
Year | +0.116 |
ksh | +0.113 |
Neg logit contributions | |
vern | -0.079 |
ons | -0.077 |
gh | -0.076 |
aches | -0.074 |
accomplished | -0.074 |
Token | there |
Token ID | 612 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
boy | +0.045 |
girl | +0.039 |
asleep | +0.029 |
cy | +0.027 |
tent | +0.026 |
Neg logit contributions | |
aches | -0.098 |
vern | -0.097 |
earned | -0.096 |
fters | -0.095 |
ough | -0.095 |
Token | sun |
Token ID | 4252 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
accomplished | +0.008 |
aches | +0.008 |
ade | +0.008 |
ag | +0.008 |
earned | +0.007 |
Neg logit contributions | |
extingu | -0.013 |
Year | -0.011 |
ksh | -0.011 |
Sn | -0.011 |
boy | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -7.09e-03 |
Pos logit contributions | |
boy | +0.063 |
girl | +0.061 |
Year | +0.059 |
extingu | +0.058 |
cottage | +0.054 |
Neg logit contributions | |
aches | -0.033 |
ough | -0.030 |
gh | -0.029 |
ons | -0.029 |
ag | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
vern | +0.009 |
aches | +0.009 |
earned | +0.009 |
ough | +0.009 |
imes | +0.009 |
Neg logit contributions | |
boy | -0.014 |
girl | -0.014 |
extingu | -0.013 |
Year | -0.013 |
maid | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
aches | +0.076 |
vern | +0.073 |
imes | +0.072 |
iable | +0.072 |
earned | +0.071 |
Neg logit contributions | |
boy | -0.044 |
girl | -0.039 |
Year | -0.033 |
duck | -0.029 |
asleep | -0.028 |
Token | A |
Token ID | 32 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
aches | +0.047 |
vern | +0.046 |
imes | +0.045 |
earned | +0.042 |
iable | +0.041 |
Neg logit contributions | |
boy | -0.069 |
girl | -0.065 |
Year | -0.058 |
duck | -0.055 |
pengu | -0.053 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
extingu | +0.018 |
Year | +0.017 |
asleep | +0.017 |
ksh | +0.017 |
ASH | +0.016 |
Neg logit contributions | |
vern | -0.024 |
aches | -0.024 |
ade | -0.023 |
gh | -0.022 |
ending | -0.022 |
Token | maid |
Token ID | 23151 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
extingu | +0.142 |
Sn | +0.140 |
Year | +0.134 |
boy | +0.132 |
girl | +0.128 |
Neg logit contributions | |
ag | -0.322 |
aches | -0.321 |
gh | -0.319 |
hardly | -0.303 |
ending | -0.299 |
Token | that |
Token ID | 326 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
boy | +0.071 |
extingu | +0.067 |
girl | +0.067 |
ksh | +0.067 |
Year | +0.065 |
Neg logit contributions | |
aches | -0.057 |
ons | -0.055 |
ending | -0.052 |
vern | -0.051 |
imes | -0.050 |
Token | lived |
Token ID | 5615 |
Feature activation | +6.22e-03 |
Pos logit contributions | |
boy | +0.087 |
girl | +0.083 |
extingu | +0.080 |
Year | +0.079 |
ksh | +0.074 |
Neg logit contributions | |
aches | -0.101 |
vern | -0.099 |
gh | -0.092 |
ons | -0.092 |
earned | -0.092 |
Token | in |
Token ID | 287 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
extingu | +0.013 |
ksh | +0.012 |
Year | +0.012 |
boy | +0.012 |
girl | +0.011 |
Neg logit contributions | |
aches | -0.009 |
accomplished | -0.008 |
vern | -0.008 |
ag | -0.007 |
imes | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -4.10e-03 |
Pos logit contributions | |
ksh | +0.036 |
boy | +0.036 |
girl | +0.035 |
extingu | +0.034 |
Year | +0.033 |
Neg logit contributions | |
vern | -0.019 |
aches | -0.018 |
ons | -0.018 |
accomplished | -0.017 |
achieve | -0.017 |
Token | bed |
Token ID | 3996 |
Feature activation | -5.82e-03 |
Pos logit contributions | |
vern | +0.005 |
aches | +0.005 |
achieve | +0.004 |
ag | +0.004 |
fters | +0.004 |
Neg logit contributions | |
boy | -0.005 |
girl | -0.005 |
Year | -0.004 |
extingu | -0.004 |
ksh | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
aches | +0.009 |
vern | +0.009 |
gh | +0.009 |
ag | +0.008 |
achieve | +0.008 |
Neg logit contributions | |
boy | -0.011 |
girl | -0.010 |
extingu | -0.010 |
cy | -0.010 |
Year | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +8.40e-03 |
Pos logit contributions | |
boy | +0.030 |
girl | +0.028 |
asleep | +0.025 |
Year | +0.024 |
extingu | +0.024 |
Neg logit contributions | |
aches | -0.035 |
vern | -0.033 |
fters | -0.031 |
earned | -0.030 |
iable | -0.030 |
Token | dreamed |
Token ID | 27947 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
boy | +0.015 |
girl | +0.015 |
extingu | +0.015 |
Year | +0.015 |
ksh | +0.014 |
Neg logit contributions | |
aches | -0.013 |
vern | -0.012 |
hardly | -0.011 |
accomplished | -0.011 |
earned | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
boy | +0.034 |
girl | +0.033 |
asleep | +0.031 |
Year | +0.028 |
tent | +0.028 |
Neg logit contributions | |
aches | -0.020 |
vern | -0.019 |
earned | -0.018 |
ough | -0.018 |
iable | -0.018 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
boy | +0.094 |
girl | +0.092 |
ksh | +0.089 |
extingu | +0.087 |
cy | +0.086 |
Neg logit contributions | |
aches | -0.065 |
vern | -0.064 |
ons | -0.056 |
imes | -0.055 |
fters | -0.055 |
Token | maid |
Token ID | 23151 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
boy | +0.157 |
girl | +0.146 |
extingu | +0.131 |
Year | +0.116 |
Sn | +0.104 |
Neg logit contributions | |
aches | -0.352 |
ag | -0.340 |
vern | -0.334 |
gh | -0.333 |
ending | -0.327 |
Token | s |
Token ID | 82 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
boy | +0.074 |
girl | +0.069 |
extingu | +0.066 |
Year | +0.066 |
ksh | +0.060 |
Neg logit contributions | |
aches | -0.076 |
vern | -0.075 |
earned | -0.070 |
imes | -0.070 |
ending | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
boy | +0.017 |
girl | +0.017 |
extingu | +0.016 |
Year | +0.015 |
ksh | +0.015 |
Neg logit contributions | |
aches | -0.019 |
vern | -0.019 |
gh | -0.017 |
ag | -0.017 |
imes | -0.017 |
Token | pirates |
Token ID | 27516 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
boy | +0.026 |
girl | +0.025 |
Year | +0.024 |
extingu | +0.024 |
ksh | +0.023 |
Neg logit contributions | |
aches | -0.020 |
vern | -0.019 |
earned | -0.018 |
ons | -0.018 |
imes | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +1.35e-03 |
Pos logit contributions | |
boy | +0.029 |
girl | +0.027 |
extingu | +0.027 |
Year | +0.027 |
ksh | +0.025 |
Neg logit contributions | |
aches | -0.028 |
vern | -0.027 |
gh | -0.025 |
ag | -0.025 |
ons | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +3.42e-03 |
Pos logit contributions | |
aches | +0.007 |
vern | +0.007 |
achieve | +0.007 |
ons | +0.006 |
accomplished | +0.006 |
Neg logit contributions | |
boy | -0.015 |
ksh | -0.014 |
Year | -0.014 |
girl | -0.014 |
extingu | -0.014 |
Token | It |
Token ID | 632 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
boy | +0.007 |
girl | +0.007 |
extingu | +0.007 |
Year | +0.007 |
ksh | +0.006 |
Neg logit contributions | |
vern | -0.004 |
imes | -0.004 |
earned | -0.004 |
hardly | -0.004 |
ending | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +6.53e-03 |
Pos logit contributions | |
hardly | +0.004 |
aches | +0.004 |
vern | +0.004 |
accomplished | +0.004 |
expect | +0.004 |
Neg logit contributions | |
boy | -0.005 |
Year | -0.005 |
extingu | -0.005 |
ksh | -0.005 |
asleep | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -1.83e-05 |
Pos logit contributions | |
boy | +0.014 |
girl | +0.013 |
ksh | +0.013 |
Year | +0.013 |
cy | +0.013 |
Neg logit contributions | |
vern | -0.008 |
aches | -0.007 |
supposed | -0.007 |
hardly | -0.007 |
gh | -0.007 |
Token | magical |
Token ID | 10883 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
aches | +0.000 |
vern | +0.000 |
hardly | +0.000 |
capable | +0.000 |
Days | +0.000 |
Neg logit contributions | |
ucks | -0.000 |
ksh | -0.000 |
extingu | -0.000 |
cy | -0.000 |
ASH | -0.000 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
ksh | +0.033 |
extingu | +0.029 |
boy | +0.029 |
ASH | +0.029 |
cy | +0.028 |
Neg logit contributions | |
aches | -0.031 |
vern | -0.030 |
earned | -0.028 |
expect | -0.028 |
gh | -0.028 |
Token | maid |
Token ID | 23151 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
boy | +0.179 |
extingu | +0.158 |
Sn | +0.157 |
girl | +0.146 |
pool | +0.141 |
Neg logit contributions | |
aches | -0.309 |
gh | -0.296 |
ag | -0.293 |
ending | -0.291 |
hardly | -0.289 |
Token | , |
Token ID | 11 |
Feature activation | -8.49e-03 |
Pos logit contributions | |
boy | +0.079 |
girl | +0.073 |
Year | +0.073 |
extingu | +0.071 |
ksh | +0.069 |
Neg logit contributions | |
aches | -0.056 |
vern | -0.056 |
ending | -0.054 |
ons | -0.051 |
gh | -0.051 |
Token | who |
Token ID | 508 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
aches | +0.012 |
hardly | +0.012 |
vern | +0.012 |
achieve | +0.012 |
accomplished | +0.011 |
Neg logit contributions | |
boy | -0.015 |
Year | -0.015 |
ksh | -0.014 |
extingu | -0.014 |
girl | -0.014 |
Token | thanked |
Token ID | 26280 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
boy | +0.040 |
ksh | +0.040 |
extingu | +0.040 |
Year | +0.040 |
girl | +0.039 |
Neg logit contributions | |
aches | -0.033 |
ons | -0.031 |
vern | -0.031 |
accomplished | -0.031 |
hardly | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -4.49e-06 |
Pos logit contributions | |
boy | +0.075 |
girl | +0.070 |
extingu | +0.069 |
ksh | +0.068 |
Year | +0.067 |
Neg logit contributions | |
aches | -0.039 |
vern | -0.037 |
ag | -0.033 |
ons | -0.033 |
imes | -0.033 |
Token | yes |
Token ID | 3763 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
boy | +0.006 |
girl | +0.005 |
Year | +0.005 |
extingu | +0.005 |
asleep | +0.005 |
Neg logit contributions | |
aches | -0.006 |
vern | -0.006 |
earned | -0.005 |
imes | -0.005 |
fters | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
boy | +0.089 |
girl | +0.084 |
Year | +0.074 |
extingu | +0.074 |
asleep | +0.071 |
Neg logit contributions | |
aches | -0.088 |
vern | -0.087 |
earned | -0.081 |
imes | -0.081 |
fters | -0.080 |
Token | She |
Token ID | 1375 |
Feature activation | +1.14e-03 |
Pos logit contributions | |
boy | +0.021 |
girl | +0.020 |
Year | +0.017 |
extingu | +0.017 |
asleep | +0.017 |
Neg logit contributions | |
aches | -0.020 |
vern | -0.020 |
earned | -0.018 |
fters | -0.018 |
gh | -0.018 |
Token | followed |
Token ID | 3940 |
Feature activation | -9.46e-03 |
Pos logit contributions | |
boy | +0.002 |
girl | +0.002 |
Year | +0.002 |
extingu | +0.002 |
asleep | +0.002 |
Neg logit contributions | |
aches | -0.002 |
vern | -0.002 |
hardly | -0.002 |
earned | -0.002 |
accomplished | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -2.03e-03 |
Pos logit contributions | |
vern | +0.016 |
aches | +0.016 |
earned | +0.015 |
ending | +0.014 |
imes | +0.014 |
Neg logit contributions | |
boy | -0.017 |
girl | -0.016 |
Year | -0.015 |
extingu | -0.014 |
asleep | -0.014 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
vern | +0.003 |
aches | +0.003 |
hardly | +0.003 |
ag | +0.003 |
expect | +0.003 |
Neg logit contributions | |
ksh | -0.003 |
extingu | -0.003 |
Year | -0.003 |
ASH | -0.003 |
ucks | -0.003 |
Token | maid |
Token ID | 23151 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
boy | +0.157 |
Sn | +0.154 |
girl | +0.148 |
extingu | +0.143 |
asleep | +0.142 |
Neg logit contributions | |
ag | -0.310 |
aches | -0.298 |
gh | -0.292 |
ade | -0.286 |
vern | -0.283 |
Token | through |
Token ID | 832 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
boy | +0.066 |
girl | +0.061 |
Year | +0.059 |
extingu | +0.057 |
ksh | +0.055 |
Neg logit contributions | |
aches | -0.063 |
vern | -0.061 |
earned | -0.058 |
ending | -0.058 |
ough | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | -2.37e-03 |
Pos logit contributions | |
vern | +0.035 |
aches | +0.034 |
achieve | +0.032 |
ons | +0.032 |
accomplished | +0.030 |
Neg logit contributions | |
boy | -0.071 |
ksh | -0.070 |
girl | -0.066 |
Year | -0.066 |
extingu | -0.065 |
Token | hidden |
Token ID | 7104 |
Feature activation | -5.84e-04 |
Pos logit contributions | |
accomplished | +0.004 |
ag | +0.004 |
vern | +0.003 |
achieve | +0.003 |
ade | +0.003 |
Neg logit contributions | |
extingu | -0.004 |
ksh | -0.004 |
Year | -0.003 |
boy | -0.003 |
work | -0.003 |
Token | door |
Token ID | 3420 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
aches | +0.001 |
vern | +0.001 |
ag | +0.001 |
ade | +0.001 |
earned | +0.001 |
Neg logit contributions | |
ksh | -0.001 |
boy | -0.001 |
girl | -0.001 |
Year | -0.001 |
extingu | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
aches | +0.031 |
vern | +0.030 |
earned | +0.029 |
imes | +0.029 |
fters | +0.028 |
Neg logit contributions | |
boy | -0.023 |
girl | -0.021 |
Year | -0.019 |
extingu | -0.018 |
asleep | -0.017 |
Token | " |
Token ID | 1 |
Feature activation | +7.15e-03 |
Pos logit contributions | |
aches | +0.017 |
vern | +0.017 |
earned | +0.015 |
imes | +0.015 |
ending | +0.014 |
Neg logit contributions | |
boy | -0.032 |
girl | -0.030 |
Year | -0.028 |
extingu | -0.028 |
asleep | -0.026 |
Token | I |
Token ID | 40 |
Feature activation | +8.42e-03 |
Pos logit contributions | |
boy | +0.013 |
girl | +0.012 |
Year | +0.011 |
extingu | +0.011 |
asleep | +0.011 |
Neg logit contributions | |
vern | -0.012 |
aches | -0.012 |
earned | -0.011 |
ending | -0.011 |
imes | -0.011 |
Token | am |
Token ID | 716 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
boy | +0.017 |
girl | +0.017 |
Year | +0.016 |
extingu | +0.015 |
asleep | +0.015 |
Neg logit contributions | |
vern | -0.012 |
aches | -0.012 |
earned | -0.011 |
ending | -0.010 |
gh | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
boy | +0.038 |
girl | +0.036 |
Year | +0.033 |
extingu | +0.032 |
ksh | +0.031 |
Neg logit contributions | |
aches | -0.036 |
vern | -0.036 |
imes | -0.033 |
ough | -0.032 |
fters | -0.032 |
Token | gen |
Token ID | 2429 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ksh | +0.045 |
ASH | +0.042 |
ucks | +0.042 |
Year | +0.041 |
asleep | +0.041 |
Neg logit contributions | |
vern | -0.051 |
aches | -0.049 |
gh | -0.048 |
iable | -0.044 |
else | -0.043 |
Token | ie |
Token ID | 494 |
Feature activation | +3.49e-03 |
Pos logit contributions | |
boy | +0.308 |
girl | +0.291 |
extingu | +0.284 |
Year | +0.282 |
asleep | +0.275 |
Neg logit contributions | |
aches | -0.205 |
vern | -0.191 |
ag | -0.177 |
ending | -0.177 |
iable | -0.175 |
Token | ," |
Token ID | 553 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
extingu | +0.007 |
Year | +0.007 |
ksh | +0.007 |
boy | +0.007 |
ASH | +0.006 |
Neg logit contributions | |
aches | -0.004 |
vern | -0.004 |
ending | -0.004 |
ons | -0.004 |
iable | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +9.94e-03 |
Pos logit contributions | |
Year | +0.049 |
ksh | +0.049 |
extingu | +0.048 |
boy | +0.048 |
work | +0.046 |
Neg logit contributions | |
aches | -0.030 |
vern | -0.028 |
ons | -0.027 |
imes | -0.027 |
iable | -0.027 |
Token | man |
Token ID | 582 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
ksh | +0.015 |
asleep | +0.014 |
cy | +0.013 |
extingu | +0.012 |
Year | +0.012 |
Neg logit contributions | |
aches | -0.021 |
vern | -0.019 |
gh | -0.017 |
achieve | -0.017 |
iable | -0.017 |
Token | said |
Token ID | 531 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
boy | +0.136 |
girl | +0.133 |
Year | +0.131 |
asleep | +0.127 |
extingu | +0.124 |
Neg logit contributions | |
aches | -0.107 |
vern | -0.098 |
ons | -0.095 |
ag | -0.094 |
imes | -0.093 |
Token | sometimes |
Token ID | 3360 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
aches | +0.008 |
fters | +0.007 |
vern | +0.007 |
earned | +0.007 |
hardly | +0.007 |
Neg logit contributions | |
boy | -0.012 |
girl | -0.012 |
Year | -0.011 |
extingu | -0.011 |
ksh | -0.011 |
Token | pretend |
Token ID | 16614 |
Feature activation | +6.57e-03 |
Pos logit contributions | |
boy | +0.108 |
girl | +0.103 |
Year | +0.091 |
asleep | +0.090 |
extingu | +0.089 |
Neg logit contributions | |
vern | -0.086 |
aches | -0.082 |
earned | -0.078 |
imes | -0.077 |
ending | -0.076 |
Token | to |
Token ID | 284 |
Feature activation | -7.78e-03 |
Pos logit contributions | |
boy | +0.012 |
girl | +0.011 |
asleep | +0.010 |
Year | +0.010 |
extingu | +0.009 |
Neg logit contributions | |
vern | -0.012 |
aches | -0.011 |
earned | -0.011 |
iable | -0.010 |
fters | -0.010 |
Token | be |
Token ID | 307 |
Feature activation | -2.84e-03 |
Pos logit contributions | |
aches | +0.014 |
vern | +0.013 |
ag | +0.012 |
fters | +0.012 |
earned | +0.012 |
Neg logit contributions | |
boy | -0.013 |
girl | -0.013 |
Year | -0.012 |
extingu | -0.012 |
asleep | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
aches | +0.005 |
vern | +0.005 |
imes | +0.005 |
ag | +0.005 |
earned | +0.005 |
Neg logit contributions | |
boy | -0.005 |
girl | -0.005 |
Year | -0.004 |
extingu | -0.004 |
work | -0.004 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
extingu | +0.022 |
Year | +0.021 |
ksh | +0.021 |
ASH | +0.021 |
work | +0.021 |
Neg logit contributions | |
vern | -0.019 |
Days | -0.018 |
ade | -0.018 |
else | -0.017 |
hardly | -0.017 |
Token | maid |
Token ID | 23151 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
boy | +0.160 |
girl | +0.146 |
extingu | +0.140 |
Sn | +0.134 |
Year | +0.123 |
Neg logit contributions | |
aches | -0.303 |
ag | -0.303 |
gh | -0.293 |
hardly | -0.282 |
ending | -0.276 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
boy | +0.064 |
girl | +0.060 |
Year | +0.057 |
extingu | +0.056 |
ksh | +0.052 |
Neg logit contributions | |
aches | -0.060 |
vern | -0.059 |
imes | -0.056 |
ending | -0.056 |
earned | -0.055 |
Token | |
Token ID | 220 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
vern | +0.020 |
aches | +0.019 |
earned | +0.018 |
imes | +0.018 |
ending | +0.018 |
Neg logit contributions | |
boy | -0.019 |
girl | -0.018 |
Year | -0.016 |
extingu | -0.016 |
asleep | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
aches | +0.050 |
vern | +0.049 |
earned | +0.048 |
fters | +0.047 |
iable | +0.047 |
Neg logit contributions | |
boy | -0.033 |
girl | -0.030 |
asleep | -0.024 |
Year | -0.024 |
extingu | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
aches | +0.074 |
vern | +0.074 |
earned | +0.070 |
imes | +0.069 |
iable | +0.069 |
Neg logit contributions | |
boy | -0.054 |
girl | -0.050 |
Year | -0.042 |
asleep | -0.040 |
extingu | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
vern | +0.017 |
aches | +0.016 |
achieve | +0.016 |
gh | +0.016 |
ag | +0.015 |
Neg logit contributions | |
boy | -0.032 |
ksh | -0.031 |
Year | -0.031 |
girl | -0.030 |
extingu | -0.030 |
Token | she |
Token ID | 673 |
Feature activation | -5.80e-03 |
Pos logit contributions | |
aches | +0.011 |
vern | +0.011 |
earned | +0.009 |
ending | +0.009 |
iable | +0.009 |
Neg logit contributions | |
boy | -0.034 |
girl | -0.032 |
extingu | -0.032 |
Year | -0.032 |
ksh | -0.031 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
aches | +0.010 |
vern | +0.010 |
accomplished | +0.009 |
hardly | +0.009 |
iable | +0.009 |
Neg logit contributions | |
boy | -0.010 |
extingu | -0.009 |
girl | -0.009 |
Year | -0.009 |
work | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
aches | +0.017 |
vern | +0.017 |
ons | +0.016 |
earned | +0.015 |
imes | +0.015 |
Neg logit contributions | |
boy | -0.019 |
girl | -0.018 |
Year | -0.017 |
extingu | -0.017 |
ksh | -0.017 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +9.69e-04 |
Pos logit contributions | |
ucks | +0.041 |
ksh | +0.040 |
ASH | +0.040 |
Year | +0.039 |
extingu | +0.038 |
Neg logit contributions | |
vern | -0.026 |
daring | -0.023 |
achieve | -0.023 |
else | -0.023 |
ade | -0.023 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
ksh | +0.002 |
extingu | +0.002 |
ucks | +0.002 |
ASH | +0.002 |
Claus | +0.002 |
Neg logit contributions | |
ade | -0.001 |
aches | -0.001 |
exercise | -0.001 |
amazing | -0.001 |
gh | -0.001 |
Token | maid |
Token ID | 23151 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
boy | +0.178 |
Sn | +0.174 |
girl | +0.163 |
cash | +0.161 |
Smith | +0.154 |
Neg logit contributions | |
ag | -0.290 |
gh | -0.281 |
aches | -0.267 |
hardly | -0.261 |
vern | -0.257 |
Token | swimming |
Token ID | 14899 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
boy | +0.072 |
ASH | +0.067 |
Year | +0.066 |
girl | +0.066 |
extingu | +0.065 |
Neg logit contributions | |
aches | -0.056 |
ending | -0.054 |
ons | -0.054 |
vern | -0.054 |
imes | -0.052 |
Token | around |
Token ID | 1088 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
Year | +0.059 |
boy | +0.056 |
girl | +0.053 |
extingu | +0.053 |
ksh | +0.052 |
Neg logit contributions | |
ag | -0.042 |
ade | -0.039 |
vern | -0.037 |
aches | -0.036 |
imes | -0.036 |
Token | her |
Token ID | 607 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
aches | +0.017 |
ons | +0.016 |
gh | +0.016 |
vern | +0.016 |
ag | +0.015 |
Neg logit contributions | |
boy | -0.034 |
ksh | -0.033 |
girl | -0.032 |
Year | -0.031 |
extingu | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +4.13e-03 |
Pos logit contributions | |
vern | +0.021 |
aches | +0.020 |
achieve | +0.020 |
ough | +0.019 |
ag | +0.018 |
Neg logit contributions | |
boy | -0.029 |
girl | -0.028 |
extingu | -0.028 |
Year | -0.027 |
ksh | -0.026 |
Token | Joe |
Token ID | 5689 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
boy | +0.014 |
girl | +0.013 |
Year | +0.012 |
extingu | +0.012 |
asleep | +0.011 |
Neg logit contributions | |
vern | -0.011 |
aches | -0.011 |
earned | -0.010 |
imes | -0.010 |
ending | -0.010 |
Token | waved |
Token ID | 26834 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
aches | +0.057 |
earned | +0.051 |
vern | +0.051 |
ending | +0.050 |
hardly | +0.049 |
Neg logit contributions | |
extingu | -0.070 |
boy | -0.069 |
girl | -0.066 |
Year | -0.066 |
ksh | -0.064 |
Token | goodbye |
Token ID | 24829 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
Year | +0.056 |
boy | +0.053 |
extingu | +0.052 |
girl | +0.050 |
ksh | +0.050 |
Neg logit contributions | |
ag | -0.031 |
earned | -0.030 |
vern | -0.030 |
aches | -0.028 |
ending | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -4.77e-03 |
Pos logit contributions | |
boy | +0.112 |
Year | +0.110 |
girl | +0.107 |
ucks | +0.105 |
extingu | +0.104 |
Neg logit contributions | |
earned | -0.059 |
vern | -0.057 |
hardly | -0.057 |
ending | -0.056 |
ag | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | +2.52e-03 |
Pos logit contributions | |
aches | +0.007 |
vern | +0.007 |
earned | +0.006 |
imes | +0.006 |
ag | +0.006 |
Neg logit contributions | |
boy | -0.010 |
girl | -0.009 |
Year | -0.009 |
extingu | -0.009 |
ksh | -0.008 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ksh | +0.004 |
extingu | +0.004 |
ASH | +0.003 |
Year | +0.003 |
ucks | +0.003 |
Neg logit contributions | |
aches | -0.005 |
vern | -0.005 |
else | -0.005 |
extraordinary | -0.005 |
ade | -0.004 |
Token | maid |
Token ID | 23151 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
boy | +0.168 |
extingu | +0.165 |
Sn | +0.147 |
girl | +0.141 |
ksh | +0.139 |
Neg logit contributions | |
aches | -0.313 |
ag | -0.302 |
gh | -0.290 |
ade | -0.283 |
hardly | -0.282 |
Token | , |
Token ID | 11 |
Feature activation | -8.95e-03 |
Pos logit contributions | |
boy | +0.065 |
girl | +0.060 |
Year | +0.059 |
ASH | +0.058 |
extingu | +0.058 |
Neg logit contributions | |
aches | -0.060 |
ending | -0.059 |
vern | -0.058 |
earned | -0.057 |
hardly | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | -5.29e-04 |
Pos logit contributions | |
aches | +0.013 |
hardly | +0.013 |
vern | +0.013 |
accomplished | +0.013 |
iable | +0.013 |
Neg logit contributions | |
boy | -0.016 |
Year | -0.015 |
extingu | -0.015 |
girl | -0.015 |
ksh | -0.014 |
Token | hopped |
Token ID | 45230 |
Feature activation | -9.87e-03 |
Pos logit contributions | |
aches | +0.001 |
accomplished | +0.001 |
hardly | +0.001 |
earned | +0.001 |
achieved | +0.001 |
Neg logit contributions | |
Year | -0.001 |
extingu | -0.001 |
boy | -0.001 |
ksh | -0.001 |
girl | -0.001 |
Token | back |
Token ID | 736 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
ag | +0.014 |
vern | +0.014 |
aches | +0.013 |
gh | +0.012 |
accomplished | +0.012 |
Neg logit contributions | |
boy | -0.020 |
Year | -0.019 |
girl | -0.018 |
extingu | -0.017 |
ksh | -0.017 |
Token | passport |
Token ID | 17981 |
Feature activation | +6.34e-03 |
Pos logit contributions | |
aches | +0.019 |
vern | +0.017 |
exercise | +0.017 |
imes | +0.017 |
ade | +0.017 |
Neg logit contributions | |
ksh | -0.016 |
ucks | -0.015 |
extingu | -0.015 |
ASH | -0.014 |
Year | -0.013 |
Token | belonged |
Token ID | 19611 |
Feature activation | -7.67e-03 |
Pos logit contributions | |
extingu | +0.011 |
ksh | +0.011 |
boy | +0.010 |
girl | +0.010 |
Year | +0.010 |
Neg logit contributions | |
aches | -0.011 |
ons | -0.010 |
accomplished | -0.009 |
vern | -0.009 |
achieve | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
vern | +0.010 |
aches | +0.010 |
earned | +0.009 |
gh | +0.009 |
ending | +0.009 |
Neg logit contributions | |
boy | -0.016 |
girl | -0.016 |
Year | -0.015 |
extingu | -0.015 |
ksh | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
vern | +0.020 |
aches | +0.020 |
gh | +0.019 |
achieve | +0.018 |
earned | +0.018 |
Neg logit contributions | |
boy | -0.028 |
girl | -0.027 |
extingu | -0.026 |
ksh | -0.026 |
Year | -0.025 |
Token | magical |
Token ID | 10883 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
ucks | +0.023 |
extingu | +0.022 |
ksh | +0.022 |
ASH | +0.021 |
Year | +0.020 |
Neg logit contributions | |
vern | -0.015 |
achieve | -0.014 |
gh | -0.014 |
capable | -0.014 |
else | -0.014 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ksh | +0.026 |
ucks | +0.024 |
extingu | +0.024 |
ASH | +0.023 |
boy | +0.022 |
Neg logit contributions | |
aches | -0.019 |
vern | -0.019 |
gh | -0.018 |
ade | -0.017 |
achieve | -0.017 |
Token | maid |
Token ID | 23151 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
extingu | +0.163 |
Sn | +0.160 |
boy | +0.157 |
girl | +0.140 |
ASH | +0.135 |
Neg logit contributions | |
aches | -0.315 |
ag | -0.305 |
gh | -0.299 |
hardly | -0.294 |
vern | -0.284 |
Token | who |
Token ID | 508 |
Feature activation | +8.40e-03 |
Pos logit contributions | |
boy | +0.048 |
girl | +0.045 |
extingu | +0.043 |
Year | +0.043 |
ksh | +0.041 |
Neg logit contributions | |
aches | -0.040 |
vern | -0.039 |
ending | -0.037 |
earned | -0.036 |
imes | -0.036 |
Token | had |
Token ID | 550 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
boy | +0.016 |
girl | +0.016 |
extingu | +0.015 |
Year | +0.015 |
ksh | +0.015 |
Neg logit contributions | |
aches | -0.012 |
vern | -0.012 |
accomplished | -0.011 |
ons | -0.011 |
earned | -0.011 |
Token | been |
Token ID | 587 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
vern | +0.039 |
aches | +0.039 |
earned | +0.036 |
imes | +0.036 |
iable | +0.035 |
Neg logit contributions | |
boy | -0.052 |
girl | -0.050 |
Year | -0.045 |
extingu | -0.045 |
asleep | -0.044 |
Token | visiting |
Token ID | 10013 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
boy | +0.051 |
girl | +0.048 |
extingu | +0.045 |
Year | +0.045 |
ksh | +0.043 |
Neg logit contributions | |
vern | -0.040 |
aches | -0.040 |
gh | -0.036 |
earned | -0.036 |
ag | -0.036 |
Token | man |
Token ID | 582 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
aches | +0.005 |
vern | +0.005 |
exercise | +0.005 |
imes | +0.005 |
gh | +0.005 |
Neg logit contributions | |
ksh | -0.005 |
ucks | -0.005 |
extingu | -0.005 |
cy | -0.005 |
Year | -0.004 |
Token | watched |
Token ID | 7342 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
ksh | +0.127 |
extingu | +0.127 |
Year | +0.124 |
girl | +0.119 |
boy | +0.116 |
Neg logit contributions | |
aches | -0.086 |
ons | -0.079 |
else | -0.078 |
hardly | -0.077 |
achieved | -0.075 |
Token | as |
Token ID | 355 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
boy | +0.075 |
girl | +0.072 |
Year | +0.068 |
extingu | +0.067 |
cy | +0.067 |
Neg logit contributions | |
aches | -0.049 |
ag | -0.047 |
imes | -0.046 |
vern | -0.046 |
ough | -0.045 |
Token | she |
Token ID | 673 |
Feature activation | -3.43e-03 |
Pos logit contributions | |
aches | +0.027 |
vern | +0.025 |
hardly | +0.024 |
achieve | +0.023 |
accomplished | +0.022 |
Neg logit contributions | |
ksh | -0.057 |
Year | -0.056 |
extingu | -0.055 |
ASH | -0.054 |
ucks | -0.052 |
Token | skipped |
Token ID | 26684 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
aches | +0.005 |
accomplished | +0.004 |
achieved | +0.004 |
ons | +0.004 |
hardly | +0.004 |
Neg logit contributions | |
boy | -0.007 |
girl | -0.007 |
extingu | -0.006 |
Year | -0.006 |
ksh | -0.006 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ag | +0.031 |
vern | +0.029 |
aches | +0.028 |
gh | +0.028 |
ough | +0.027 |
Neg logit contributions | |
boy | -0.042 |
Year | -0.041 |
girl | -0.040 |
extingu | -0.038 |
ksh | -0.037 |
Token | rily |
Token ID | 28904 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
boy | +0.213 |
girl | +0.202 |
extingu | +0.183 |
Year | +0.175 |
Sn | +0.170 |
Neg logit contributions | |
aches | -0.301 |
ag | -0.281 |
hardly | -0.261 |
gh | -0.260 |
vern | -0.254 |
Token | away |
Token ID | 1497 |
Feature activation | -6.51e-03 |
Pos logit contributions | |
boy | +0.026 |
Year | +0.025 |
girl | +0.025 |
ksh | +0.024 |
extingu | +0.024 |
Neg logit contributions | |
aches | -0.020 |
gh | -0.019 |
ag | -0.019 |
vern | -0.018 |
imes | -0.018 |
Token | into |
Token ID | 656 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
aches | +0.008 |
vern | +0.008 |
hardly | +0.007 |
gh | +0.007 |
ag | +0.007 |
Neg logit contributions | |
boy | -0.013 |
Year | -0.013 |
girl | -0.013 |
ksh | -0.012 |
ASH | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -4.34e-03 |
Pos logit contributions | |
vern | +0.023 |
aches | +0.023 |
ons | +0.021 |
expect | +0.020 |
achieve | +0.020 |
Neg logit contributions | |
ksh | -0.050 |
boy | -0.049 |
Year | -0.047 |
girl | -0.047 |
Claus | -0.046 |
Token | sunset |
Token ID | 26428 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
accomplished | +0.006 |
ag | +0.006 |
aches | +0.005 |
ade | +0.005 |
exercise | +0.005 |
Neg logit contributions | |
extingu | -0.008 |
ucks | -0.007 |
ksh | -0.007 |
maid | -0.007 |
Year | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +2.52e-03 |
Pos logit contributions | |
aches | +0.001 |
vern | +0.001 |
achieve | +0.001 |
ag | +0.001 |
ons | +0.001 |
Neg logit contributions | |
boy | -0.001 |
girl | -0.001 |
Year | -0.001 |
extingu | -0.001 |
ksh | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | +8.71e-03 |
Pos logit contributions | |
boy | +0.005 |
girl | +0.004 |
extingu | +0.004 |
Year | +0.004 |
asleep | +0.004 |
Neg logit contributions | |
aches | -0.004 |
vern | -0.004 |
imes | -0.004 |
earned | -0.004 |
ough | -0.004 |
Token | even |
Token ID | 772 |
Feature activation | -7.37e-03 |
Pos logit contributions | |
extingu | +0.017 |
girl | +0.016 |
boy | +0.016 |
Year | +0.016 |
ksh | +0.015 |
Neg logit contributions | |
aches | -0.013 |
hardly | -0.011 |
accomplished | -0.011 |
achieved | -0.011 |
achieve | -0.011 |
Token | saw |
Token ID | 2497 |
Feature activation | -9.00e-03 |
Pos logit contributions | |
aches | +0.012 |
vern | +0.010 |
earned | +0.010 |
ons | +0.010 |
accomplished | +0.010 |
Neg logit contributions | |
boy | -0.013 |
girl | -0.012 |
Year | -0.012 |
extingu | -0.012 |
ksh | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
aches | +0.013 |
ons | +0.013 |
vern | +0.013 |
imes | +0.012 |
earned | +0.012 |
Neg logit contributions | |
boy | -0.016 |
girl | -0.016 |
extingu | -0.016 |
Year | -0.016 |
ksh | -0.015 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ucks | +0.037 |
ASH | +0.036 |
ksh | +0.036 |
extingu | +0.035 |
Year | +0.033 |
Neg logit contributions | |
vern | -0.023 |
aches | -0.023 |
achieve | -0.023 |
ade | -0.021 |
else | -0.021 |
Token | maid |
Token ID | 23151 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
Sn | +0.170 |
boy | +0.161 |
girl | +0.151 |
extingu | +0.148 |
ASH | +0.142 |
Neg logit contributions | |
ag | -0.302 |
aches | -0.295 |
gh | -0.290 |
hardly | -0.289 |
vern | -0.271 |
Token | ! |
Token ID | 0 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
boy | +0.066 |
ASH | +0.061 |
girl | +0.061 |
extingu | +0.061 |
ksh | +0.060 |
Neg logit contributions | |
aches | -0.057 |
ons | -0.053 |
ending | -0.052 |
imes | -0.051 |
achieve | -0.051 |
Token | |
Token ID | 220 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
vern | +0.020 |
aches | +0.020 |
imes | +0.020 |
earned | +0.019 |
ough | +0.019 |
Neg logit contributions | |
boy | -0.026 |
girl | -0.025 |
extingu | -0.024 |
Year | -0.024 |
asleep | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
vern | +0.027 |
aches | +0.027 |
earned | +0.025 |
imes | +0.024 |
fters | +0.024 |
Neg logit contributions | |
boy | -0.026 |
girl | -0.025 |
Year | -0.022 |
extingu | -0.022 |
asleep | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
aches | +0.044 |
vern | +0.044 |
earned | +0.042 |
ending | +0.041 |
imes | +0.041 |
Neg logit contributions | |
boy | -0.035 |
girl | -0.031 |
Year | -0.027 |
extingu | -0.025 |
asleep | -0.025 |
Token | swimming |
Token ID | 14899 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
boy | +0.072 |
ASH | +0.067 |
Year | +0.066 |
girl | +0.066 |
extingu | +0.065 |
Neg logit contributions | |
aches | -0.056 |
ending | -0.054 |
ons | -0.054 |
vern | -0.054 |
imes | -0.052 |
Token | around |
Token ID | 1088 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
Year | +0.059 |
boy | +0.056 |
girl | +0.053 |
extingu | +0.053 |
ksh | +0.052 |
Neg logit contributions | |
ag | -0.042 |
ade | -0.039 |
vern | -0.037 |
aches | -0.036 |
imes | -0.036 |
Token | her |
Token ID | 607 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
aches | +0.017 |
ons | +0.016 |
gh | +0.016 |
vern | +0.016 |
ag | +0.015 |
Neg logit contributions | |
boy | -0.034 |
ksh | -0.033 |
girl | -0.032 |
Year | -0.031 |
extingu | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +4.13e-03 |
Pos logit contributions | |
vern | +0.021 |
aches | +0.020 |
achieve | +0.020 |
ough | +0.019 |
ag | +0.018 |
Neg logit contributions | |
boy | -0.029 |
girl | -0.028 |
extingu | -0.028 |
Year | -0.027 |
ksh | -0.026 |
Token | The |
Token ID | 383 |
Feature activation | -4.37e-03 |
Pos logit contributions | |
boy | +0.008 |
girl | +0.008 |
Year | +0.007 |
extingu | +0.007 |
tent | +0.007 |
Neg logit contributions | |
vern | -0.005 |
earned | -0.005 |
aches | -0.005 |
ending | -0.005 |
hardly | -0.005 |
Token | mer |
Token ID | 4017 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
aches | +0.008 |
vern | +0.008 |
ag | +0.008 |
ade | +0.008 |
extraordinary | +0.008 |
Neg logit contributions | |
extingu | -0.006 |
ksh | -0.006 |
Year | -0.005 |
ASH | -0.005 |
ucks | -0.005 |
Token | maid |
Token ID | 23151 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
boy | +0.162 |
girl | +0.140 |
extingu | +0.136 |
Sn | +0.132 |
Year | +0.124 |
Neg logit contributions | |
aches | -0.317 |
ag | -0.317 |
gh | -0.303 |
hardly | -0.296 |
ending | -0.292 |
Token | smiled |
Token ID | 13541 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
boy | +0.071 |
girl | +0.068 |
extingu | +0.068 |
Year | +0.067 |
ksh | +0.064 |
Neg logit contributions | |
aches | -0.056 |
hardly | -0.053 |
vern | -0.052 |
ons | -0.051 |
ending | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | -3.98e-03 |
Pos logit contributions | |
Year | +0.085 |
boy | +0.077 |
extingu | +0.072 |
ASH | +0.071 |
poster | +0.071 |
Neg logit contributions | |
vern | -0.052 |
Her | -0.050 |
ending | -0.048 |
hardly | -0.047 |
accomplished | -0.046 |
Token | said |
Token ID | 531 |
Feature activation | +6.45e-04 |
Pos logit contributions | |
aches | +0.005 |
hardly | +0.005 |
accomplished | +0.005 |
vern | +0.004 |
ons | +0.004 |
Neg logit contributions | |
boy | -0.008 |
Year | -0.008 |
extingu | -0.008 |
girl | -0.008 |
ASH | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
boy | +0.001 |
girl | +0.001 |
Year | +0.001 |
extingu | +0.001 |
ksh | +0.001 |
Neg logit contributions | |
vern | -0.001 |
aches | -0.001 |
gh | -0.001 |
imes | -0.001 |
ending | -0.001 |
Token | rings |
Token ID | 13917 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
aches | +0.034 |
imes | +0.031 |
earned | +0.029 |
fters | +0.029 |
ons | +0.029 |
Neg logit contributions | |
boy | -0.030 |
girl | -0.028 |
Year | -0.028 |
work | -0.027 |
cy | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
aches | +0.086 |
gh | +0.075 |
vern | +0.075 |
ons | +0.073 |
ough | +0.072 |
Neg logit contributions | |
boy | -0.090 |
girl | -0.087 |
Year | -0.079 |
extingu | -0.075 |
ksh | -0.075 |
Token | and |
Token ID | 290 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
aches | +0.041 |
imes | +0.036 |
hardly | +0.034 |
fters | +0.034 |
ons | +0.034 |
Neg logit contributions | |
boy | -0.037 |
girl | -0.035 |
cy | -0.035 |
ASH | -0.032 |
maid | -0.031 |
Token | neck |
Token ID | 7393 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
aches | +0.019 |
imes | +0.016 |
ons | +0.016 |
achieve | +0.015 |
fters | +0.015 |
Neg logit contributions | |
boy | -0.019 |
girl | -0.018 |
Year | -0.018 |
ksh | -0.018 |
extingu | -0.018 |
Token | l |
Token ID | 75 |
Feature activation | +5.05e-03 |
Pos logit contributions | |
aches | +0.213 |
vern | +0.201 |
gh | +0.185 |
imes | +0.184 |
ag | +0.183 |
Neg logit contributions | |
boy | -0.256 |
girl | -0.245 |
Year | -0.225 |
extingu | -0.223 |
asleep | -0.211 |
Token | aces |
Token ID | 2114 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
boy | +0.012 |
girl | +0.012 |
Year | +0.011 |
extingu | +0.011 |
asleep | +0.010 |
Neg logit contributions | |
aches | -0.006 |
vern | -0.005 |
imes | -0.005 |
earned | -0.005 |
ag | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -5.07e-03 |
Pos logit contributions | |
vern | +0.319 |
aches | +0.317 |
earned | +0.295 |
imes | +0.291 |
ending | +0.288 |
Neg logit contributions | |
boy | -0.304 |
girl | -0.287 |
Year | -0.259 |
extingu | -0.257 |
asleep | -0.246 |
Token |
|
Token ID | 198 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
imes | +0.007 |
vern | +0.007 |
aches | +0.007 |
ough | +0.007 |
earned | +0.007 |
Neg logit contributions | |
boy | -0.009 |
girl | -0.009 |
extingu | -0.009 |
Year | -0.008 |
work | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
aches | +0.041 |
vern | +0.041 |
earned | +0.039 |
iable | +0.038 |
ending | +0.038 |
Neg logit contributions | |
boy | -0.036 |
girl | -0.034 |
Year | -0.030 |
extingu | -0.029 |
asleep | -0.028 |
Token | " |
Token ID | 1 |
Feature activation | +2.18e-03 |
Pos logit contributions | |
vern | +0.025 |
aches | +0.025 |
earned | +0.023 |
imes | +0.022 |
ending | +0.022 |
Neg logit contributions | |
boy | -0.035 |
girl | -0.034 |
Year | -0.031 |
extingu | -0.030 |
asleep | -0.029 |
Token | Wow |
Token ID | 22017 |
Feature activation | +5.04e-03 |
Pos logit contributions | |
boy | +0.004 |
asleep | +0.003 |
girl | +0.003 |
maid | +0.003 |
extingu | +0.003 |
Neg logit contributions | |
aches | -0.004 |
vern | -0.003 |
fters | -0.003 |
earned | -0.003 |
Days | -0.003 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
boy | +0.027 |
girl | +0.026 |
Year | +0.025 |
extingu | +0.025 |
asleep | +0.024 |
Neg logit contributions | |
aches | -0.021 |
vern | -0.019 |
ag | -0.018 |
earned | -0.018 |
achieve | -0.018 |
Token | rings |
Token ID | 13917 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
aches | +0.034 |
ons | +0.032 |
ag | +0.031 |
vern | +0.031 |
imes | +0.031 |
Neg logit contributions | |
Year | -0.042 |
girl | -0.042 |
boy | -0.041 |
ksh | -0.041 |
extingu | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
aches | +0.061 |
gh | +0.053 |
ag | +0.053 |
vern | +0.053 |
iable | +0.052 |
Neg logit contributions | |
boy | -0.066 |
Year | -0.063 |
girl | -0.062 |
extingu | -0.062 |
ksh | -0.060 |
Token | neck |
Token ID | 7393 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
aches | +0.023 |
ons | +0.020 |
ag | +0.019 |
Her | +0.018 |
imes | +0.018 |
Neg logit contributions | |
extingu | -0.025 |
cy | -0.024 |
ksh | -0.024 |
boy | -0.024 |
ASH | -0.024 |
Token | l |
Token ID | 75 |
Feature activation | +7.01e-03 |
Pos logit contributions | |
aches | +0.208 |
vern | +0.189 |
ons | +0.179 |
gh | +0.176 |
ag | +0.174 |
Neg logit contributions | |
boy | -0.261 |
girl | -0.250 |
Year | -0.232 |
extingu | -0.230 |
ksh | -0.226 |
Token | aces |
Token ID | 2114 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
boy | +0.020 |
girl | +0.019 |
extingu | +0.018 |
Year | +0.018 |
cottage | +0.017 |
Neg logit contributions | |
aches | -0.005 |
vern | -0.005 |
imes | -0.004 |
ag | -0.004 |
ons | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
aches | +0.328 |
vern | +0.326 |
ending | +0.298 |
earned | +0.298 |
iable | +0.297 |
Neg logit contributions | |
boy | -0.283 |
girl | -0.267 |
Year | -0.246 |
extingu | -0.239 |
ksh | -0.222 |
Token | brace |
Token ID | 22581 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
aches | +0.022 |
ons | +0.018 |
fters | +0.018 |
ag | +0.018 |
imes | +0.017 |
Neg logit contributions | |
boy | -0.020 |
girl | -0.019 |
extingu | -0.018 |
Year | -0.018 |
ksh | -0.018 |
Token | lets |
Token ID | 5289 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
aches | +0.117 |
vern | +0.116 |
earned | +0.107 |
gh | +0.105 |
imes | +0.105 |
Neg logit contributions | |
boy | -0.137 |
girl | -0.129 |
Year | -0.119 |
extingu | -0.117 |
asleep | -0.112 |
Token | and |
Token ID | 290 |
Feature activation | -8.61e-03 |
Pos logit contributions | |
aches | +0.221 |
vern | +0.217 |
imes | +0.200 |
gh | +0.198 |
ons | +0.198 |
Neg logit contributions | |
boy | -0.197 |
girl | -0.186 |
Year | -0.172 |
extingu | -0.166 |
ksh | -0.159 |
Token | ear |
Token ID | 1027 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
aches | +0.014 |
vern | +0.013 |
earned | +0.013 |
ons | +0.012 |
gh | +0.012 |
Neg logit contributions | |
boy | -0.015 |
girl | -0.014 |
Year | -0.014 |
extingu | -0.014 |
asleep | -0.013 |
Token | These |
Token ID | 4711 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
tent | +0.065 |
boy | +0.064 |
asleep | +0.064 |
extingu | +0.063 |
girl | +0.062 |
Neg logit contributions | |
earned | -0.049 |
aches | -0.048 |
vern | -0.047 |
ending | -0.047 |
iable | -0.047 |
Token | are |
Token ID | 389 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
aches | +0.059 |
vern | +0.057 |
imes | +0.054 |
ons | +0.053 |
iable | +0.053 |
Neg logit contributions | |
boy | -0.066 |
girl | -0.063 |
Year | -0.060 |
extingu | -0.059 |
asleep | -0.059 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
boy | +0.061 |
girl | +0.058 |
Year | +0.056 |
extingu | +0.055 |
asleep | +0.053 |
Neg logit contributions | |
aches | -0.046 |
vern | -0.044 |
imes | -0.041 |
iable | -0.040 |
ough | -0.039 |
Token | neck |
Token ID | 7393 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
aches | +0.015 |
ons | +0.014 |
vern | +0.013 |
ade | +0.013 |
imes | +0.013 |
Neg logit contributions | |
extingu | -0.019 |
boy | -0.018 |
ksh | -0.018 |
ASH | -0.017 |
girl | -0.017 |
Token | l |
Token ID | 75 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
aches | +0.211 |
vern | +0.208 |
earned | +0.192 |
imes | +0.190 |
ending | +0.188 |
Neg logit contributions | |
boy | -0.221 |
girl | -0.209 |
extingu | -0.193 |
Year | -0.193 |
asleep | -0.183 |
Token | aces |
Token ID | 2114 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
boy | +0.026 |
girl | +0.025 |
extingu | +0.024 |
Year | +0.023 |
cottage | +0.022 |
Neg logit contributions | |
aches | -0.014 |
vern | -0.013 |
imes | -0.012 |
ons | -0.012 |
ag | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -5.77e-03 |
Pos logit contributions | |
vern | +0.297 |
aches | +0.297 |
earned | +0.272 |
imes | +0.270 |
iable | +0.269 |
Neg logit contributions | |
boy | -0.307 |
girl | -0.291 |
Year | -0.271 |
extingu | -0.266 |
asleep | -0.249 |
Token | brace |
Token ID | 22581 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
aches | +0.010 |
vern | +0.009 |
earned | +0.009 |
fters | +0.009 |
imes | +0.009 |
Neg logit contributions | |
boy | -0.010 |
girl | -0.009 |
extingu | -0.009 |
Year | -0.009 |
asleep | -0.008 |
Token | lets |
Token ID | 5289 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
aches | +0.113 |
vern | +0.112 |
earned | +0.103 |
imes | +0.101 |
ending | +0.101 |
Neg logit contributions | |
boy | -0.128 |
girl | -0.121 |
Year | -0.112 |
extingu | -0.111 |
asleep | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e-03 |
Pos logit contributions | |
aches | +0.192 |
vern | +0.190 |
earned | +0.173 |
imes | +0.173 |
ending | +0.170 |
Neg logit contributions | |
boy | -0.211 |
girl | -0.200 |
Year | -0.186 |
extingu | -0.184 |
asleep | -0.172 |
Token | You |
Token ID | 921 |
Feature activation | -8.32e-03 |
Pos logit contributions | |
boy | +0.002 |
girl | +0.002 |
extingu | +0.002 |
Year | +0.002 |
asleep | +0.002 |
Neg logit contributions | |
vern | -0.002 |
ough | -0.002 |
aches | -0.002 |
imes | -0.002 |
earned | -0.002 |
Token | fish |
Token ID | 5916 |
Feature activation | +4.95e-03 |
Pos logit contributions | |
ons | +0.029 |
aches | +0.028 |
ade | +0.027 |
imes | +0.025 |
vern | +0.024 |
Neg logit contributions | |
ksh | -0.034 |
Amen | -0.031 |
ASH | -0.030 |
extingu | -0.030 |
Year | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
boy | +0.009 |
girl | +0.008 |
Year | +0.008 |
extingu | +0.008 |
ksh | +0.008 |
Neg logit contributions | |
aches | -0.008 |
vern | -0.008 |
imes | -0.007 |
ons | -0.007 |
gh | -0.007 |
Token | some |
Token ID | 617 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
aches | +0.056 |
imes | +0.049 |
ons | +0.048 |
vern | +0.048 |
hardly | +0.047 |
Neg logit contributions | |
boy | -0.062 |
Year | -0.060 |
girl | -0.059 |
extingu | -0.058 |
ksh | -0.058 |
Token | l |
Token ID | 300 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
aches | +0.021 |
vern | +0.020 |
imes | +0.019 |
earned | +0.019 |
ag | +0.019 |
Neg logit contributions | |
boy | -0.022 |
girl | -0.021 |
Year | -0.020 |
extingu | -0.020 |
ksh | -0.019 |
Token | ily |
Token ID | 813 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
aches | +0.015 |
vern | +0.014 |
iable | +0.014 |
earned | +0.014 |
achieve | +0.014 |
Neg logit contributions | |
boy | -0.030 |
girl | -0.030 |
extingu | -0.028 |
asleep | -0.028 |
duck | -0.027 |
Token | pads |
Token ID | 21226 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
aches | +0.026 |
vern | +0.025 |
imes | +0.024 |
ons | +0.024 |
earned | +0.023 |
Neg logit contributions | |
boy | -0.026 |
girl | -0.024 |
extingu | -0.023 |
Year | -0.023 |
ksh | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
vern | +0.365 |
aches | +0.363 |
earned | +0.344 |
fters | +0.338 |
ending | +0.336 |
Neg logit contributions | |
boy | -0.239 |
girl | -0.223 |
extingu | -0.193 |
Year | -0.191 |
asleep | -0.186 |
Token | even |
Token ID | 772 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
aches | +0.028 |
imes | +0.026 |
earned | +0.025 |
ons | +0.024 |
ough | +0.024 |
Neg logit contributions | |
boy | -0.028 |
Year | -0.027 |
extingu | -0.026 |
ksh | -0.026 |
girl | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +7.70e-03 |
Pos logit contributions | |
aches | +0.038 |
earned | +0.034 |
imes | +0.034 |
ag | +0.033 |
vern | +0.033 |
Neg logit contributions | |
boy | -0.038 |
Year | -0.037 |
girl | -0.036 |
extingu | -0.036 |
work | -0.033 |
Token | frog |
Token ID | 21264 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
ucks | +0.013 |
Year | +0.013 |
extingu | +0.013 |
ksh | +0.012 |
ASH | +0.012 |
Neg logit contributions | |
vern | -0.012 |
aches | -0.012 |
gh | -0.012 |
ade | -0.011 |
hardly | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
boy | +0.044 |
girl | +0.042 |
Year | +0.041 |
extingu | +0.040 |
ksh | +0.038 |
Neg logit contributions | |
aches | -0.033 |
vern | -0.031 |
imes | -0.030 |
gh | -0.029 |
ons | -0.029 |
Token | want |
Token ID | 765 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
boy | +0.005 |
girl | +0.005 |
Year | +0.005 |
extingu | +0.004 |
ksh | +0.004 |
Neg logit contributions | |
aches | -0.004 |
vern | -0.004 |
achieve | -0.004 |
hardly | -0.004 |
expect | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
aches | +0.036 |
vern | +0.035 |
earned | +0.032 |
gh | +0.031 |
imes | +0.031 |
Neg logit contributions | |
boy | -0.061 |
girl | -0.059 |
Year | -0.055 |
extingu | -0.054 |
ksh | -0.053 |
Token | make |
Token ID | 787 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
vern | +0.035 |
imes | +0.035 |
ending | +0.034 |
aches | +0.033 |
earned | +0.033 |
Neg logit contributions | |
boy | -0.031 |
girl | -0.029 |
extingu | -0.027 |
Year | -0.026 |
t | -0.026 |
Token | neck |
Token ID | 7393 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
aches | +0.053 |
vern | +0.050 |
ons | +0.048 |
ag | +0.047 |
ough | +0.046 |
Neg logit contributions | |
boy | -0.065 |
girl | -0.064 |
fly | -0.059 |
cy | -0.059 |
Year | -0.058 |
Token | l |
Token ID | 75 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
aches | +0.174 |
vern | +0.169 |
earned | +0.151 |
fters | +0.149 |
ag | +0.148 |
Neg logit contributions | |
boy | -0.278 |
girl | -0.267 |
Year | -0.248 |
extingu | -0.248 |
asleep | -0.237 |
Token | aces |
Token ID | 2114 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
boy | +0.028 |
girl | +0.027 |
Year | +0.026 |
asleep | +0.025 |
extingu | +0.025 |
Neg logit contributions | |
vern | -0.007 |
aches | -0.006 |
earned | -0.005 |
fters | -0.005 |
iable | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -5.36e-03 |
Pos logit contributions | |
vern | +0.309 |
aches | +0.307 |
earned | +0.284 |
imes | +0.280 |
iable | +0.279 |
Neg logit contributions | |
boy | -0.295 |
girl | -0.279 |
Year | -0.255 |
extingu | -0.251 |
asleep | -0.236 |
Token | brace |
Token ID | 22581 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
aches | +0.009 |
vern | +0.008 |
earned | +0.008 |
fters | +0.008 |
ons | +0.008 |
Neg logit contributions | |
boy | -0.009 |
girl | -0.009 |
Year | -0.008 |
extingu | -0.008 |
ksh | -0.008 |
Token | lets |
Token ID | 5289 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
aches | +0.110 |
vern | +0.109 |
earned | +0.100 |
imes | +0.098 |
ag | +0.098 |
Neg logit contributions | |
boy | -0.128 |
girl | -0.121 |
Year | -0.111 |
extingu | -0.110 |
asleep | -0.105 |
Token | with |
Token ID | 351 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
aches | +0.198 |
vern | +0.196 |
imes | +0.178 |
earned | +0.178 |
ag | +0.176 |
Neg logit contributions | |
boy | -0.212 |
girl | -0.201 |
Year | -0.188 |
extingu | -0.183 |
ksh | -0.171 |
Token | them |
Token ID | 606 |
Feature activation | -8.58e-03 |
Pos logit contributions | |
boy | +0.026 |
girl | +0.024 |
Year | +0.022 |
extingu | +0.022 |
asleep | +0.021 |
Neg logit contributions | |
aches | -0.026 |
vern | -0.026 |
earned | -0.024 |
imes | -0.023 |
ag | -0.023 |
Token | you |
Token ID | 345 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
boy | +0.041 |
girl | +0.039 |
extingu | +0.036 |
Year | +0.035 |
asleep | +0.034 |
Neg logit contributions | |
vern | -0.039 |
aches | -0.039 |
earned | -0.036 |
iable | -0.035 |
imes | -0.035 |
Token | tie |
Token ID | 9839 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
vern | +0.021 |
aches | +0.021 |
imes | +0.019 |
earned | +0.019 |
ending | +0.019 |
Neg logit contributions | |
boy | -0.031 |
girl | -0.029 |
Year | -0.027 |
extingu | -0.027 |
asleep | -0.026 |
Token | my |
Token ID | 616 |
Feature activation | -3.99e-04 |
Pos logit contributions | |
aches | +0.078 |
vern | +0.077 |
earned | +0.071 |
imes | +0.070 |
iable | +0.070 |
Neg logit contributions | |
boy | -0.089 |
girl | -0.085 |
Year | -0.078 |
extingu | -0.078 |
asleep | -0.073 |
Token | sho |
Token ID | 7354 |
Feature activation | -8.57e-02 |
Pos logit contributions | |
vern | +0.001 |
aches | +0.001 |
earned | +0.001 |
gh | +0.001 |
ag | +0.001 |
Neg logit contributions | |
boy | -0.001 |
girl | -0.001 |
extingu | -0.001 |
Year | -0.001 |
work | -0.001 |
Token | el |
Token ID | 417 |
Feature activation | -3.22e-03 |
Pos logit contributions | |
vern | +0.162 |
aches | +0.161 |
fters | +0.152 |
Days | +0.150 |
achieve | +0.149 |
Neg logit contributions | |
boy | -0.132 |
girl | -0.124 |
cy | -0.113 |
Year | -0.110 |
extingu | -0.108 |
Token | aces |
Token ID | 2114 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
vern | +0.005 |
aches | +0.005 |
fters | +0.005 |
ending | +0.005 |
iable | +0.005 |
Neg logit contributions | |
boy | -0.006 |
girl | -0.005 |
extingu | -0.005 |
Year | -0.005 |
asleep | -0.005 |
Token | for |
Token ID | 329 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
vern | +0.287 |
aches | +0.285 |
earned | +0.265 |
imes | +0.261 |
ending | +0.259 |
Neg logit contributions | |
boy | -0.285 |
girl | -0.270 |
Year | -0.243 |
extingu | -0.241 |
asleep | -0.232 |
Token | me |
Token ID | 502 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
vern | +0.041 |
aches | +0.040 |
earned | +0.039 |
ending | +0.038 |
imes | +0.037 |
Neg logit contributions | |
boy | -0.027 |
girl | -0.025 |
Year | -0.023 |
asleep | -0.022 |
extingu | -0.021 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
vern | +0.029 |
aches | +0.028 |
fters | +0.027 |
earned | +0.026 |
Days | +0.026 |
Neg logit contributions | |
boy | -0.029 |
girl | -0.027 |
asleep | -0.025 |
Year | -0.024 |
extingu | -0.024 |
Token | |
Token ID | 220 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
boy | +0.032 |
girl | +0.031 |
extingu | +0.029 |
Year | +0.028 |
asleep | +0.027 |
Neg logit contributions | |
aches | -0.031 |
vern | -0.031 |
earned | -0.029 |
imes | -0.029 |
ons | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
aches | +0.029 |
vern | +0.029 |
earned | +0.028 |
fters | +0.027 |
gh | +0.027 |
Neg logit contributions | |
boy | -0.025 |
girl | -0.024 |
Year | -0.021 |
extingu | -0.021 |
asleep | -0.020 |
Token | he |
Token ID | 339 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
aches | +0.021 |
hardly | +0.017 |
achieve | +0.015 |
ons | +0.014 |
gh | +0.014 |
Neg logit contributions | |
ksh | -0.093 |
extingu | -0.092 |
Year | -0.089 |
boy | -0.088 |
girl | -0.088 |
Token | found |
Token ID | 1043 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
aches | +0.030 |
hardly | +0.027 |
accomplished | +0.027 |
gh | +0.026 |
ons | +0.026 |
Neg logit contributions | |
extingu | -0.035 |
boy | -0.034 |
girl | -0.033 |
Year | -0.032 |
ksh | -0.031 |
Token | two |
Token ID | 734 |
Feature activation | -3.35e-03 |
Pos logit contributions | |
vern | +0.110 |
aches | +0.109 |
earned | +0.101 |
imes | +0.100 |
ons | +0.099 |
Neg logit contributions | |
boy | -0.105 |
girl | -0.100 |
Year | -0.094 |
extingu | -0.090 |
ksh | -0.087 |
Token | little |
Token ID | 1310 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
aches | +0.006 |
vern | +0.006 |
imes | +0.005 |
ons | +0.005 |
earned | +0.005 |
Neg logit contributions | |
boy | -0.006 |
Year | -0.005 |
girl | -0.005 |
extingu | -0.005 |
ksh | -0.005 |
Token | m |
Token ID | 285 |
Feature activation | -7.25e-03 |
Pos logit contributions | |
Year | +0.064 |
ksh | +0.062 |
extingu | +0.061 |
hyd | +0.059 |
Amen | +0.059 |
Neg logit contributions | |
ons | -0.067 |
imes | -0.063 |
old | -0.061 |
aches | -0.061 |
else | -0.059 |
Token | ittens |
Token ID | 34978 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
vern | +0.009 |
aches | +0.008 |
fters | +0.007 |
earned | +0.007 |
iable | +0.007 |
Neg logit contributions | |
boy | -0.016 |
girl | -0.016 |
extingu | -0.015 |
Year | -0.015 |
asleep | -0.014 |
Token | lying |
Token ID | 9105 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
aches | +0.274 |
vern | +0.261 |
ons | +0.257 |
imes | +0.253 |
ending | +0.249 |
Neg logit contributions | |
boy | -0.293 |
girl | -0.280 |
Year | -0.260 |
extingu | -0.252 |
ksh | -0.240 |
Token | in |
Token ID | 287 |
Feature activation | -4.03e-04 |
Pos logit contributions | |
boy | +0.039 |
Year | +0.037 |
girl | +0.037 |
extingu | +0.037 |
ksh | +0.035 |
Neg logit contributions | |
aches | -0.031 |
ons | -0.029 |
imes | -0.029 |
ag | -0.028 |
gh | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
aches | +0.000 |
vern | +0.000 |
ons | +0.000 |
Every | +0.000 |
hardly | +0.000 |
Neg logit contributions | |
ksh | -0.001 |
boy | -0.001 |
girl | -0.001 |
work | -0.001 |
maid | -0.001 |
Token | snow |
Token ID | 6729 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
aches | +0.031 |
earned | +0.029 |
ade | +0.028 |
ag | +0.028 |
ough | +0.027 |
Neg logit contributions | |
boy | -0.033 |
maid | -0.033 |
extingu | -0.032 |
work | -0.032 |
Year | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
girl | +0.044 |
boy | +0.044 |
Year | +0.040 |
Uh | +0.040 |
ucks | +0.039 |
Neg logit contributions | |
aches | -0.035 |
ons | -0.031 |
ade | -0.031 |
gh | -0.031 |
ough | -0.029 |
Token | seat |
Token ID | 5852 |
Feature activation | -7.11e-03 |
Pos logit contributions | |
boy | +0.103 |
girl | +0.103 |
extingu | +0.101 |
Year | +0.100 |
ksh | +0.099 |
Neg logit contributions | |
aches | -0.093 |
earned | -0.084 |
ons | -0.083 |
ag | -0.082 |
iable | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +6.87e-03 |
Pos logit contributions | |
aches | +0.010 |
ag | +0.009 |
gh | +0.009 |
ons | +0.009 |
earned | +0.009 |
Neg logit contributions | |
boy | -0.013 |
girl | -0.013 |
Year | -0.013 |
extingu | -0.012 |
ksh | -0.012 |
Token | After |
Token ID | 2293 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
boy | +0.013 |
girl | +0.013 |
extingu | +0.012 |
Year | +0.012 |
work | +0.012 |
Neg logit contributions | |
vern | -0.009 |
imes | -0.009 |
aches | -0.009 |
earned | -0.009 |
ough | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +9.62e-03 |
Pos logit contributions | |
aches | +0.047 |
vern | +0.044 |
gh | +0.043 |
ons | +0.041 |
achieve | +0.041 |
Neg logit contributions | |
boy | -0.066 |
girl | -0.064 |
extingu | -0.060 |
ksh | -0.060 |
cy | -0.058 |
Token | few |
Token ID | 1178 |
Feature activation | -4.96e-03 |
Pos logit contributions | |
ucks | +0.019 |
extingu | +0.019 |
Year | +0.018 |
ASH | +0.018 |
boy | +0.017 |
Neg logit contributions | |
gh | -0.012 |
Days | -0.012 |
aches | -0.012 |
vern | -0.012 |
hardly | -0.011 |
Token | attempts |
Token ID | 6370 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
aches | +0.008 |
vern | +0.008 |
earned | +0.007 |
gh | +0.007 |
imes | +0.007 |
Neg logit contributions | |
boy | -0.009 |
girl | -0.009 |
extingu | -0.008 |
Year | -0.008 |
asleep | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
vern | +0.268 |
aches | +0.267 |
earned | +0.246 |
imes | +0.242 |
ending | +0.241 |
Neg logit contributions | |
boy | -0.293 |
girl | -0.279 |
Year | -0.255 |
extingu | -0.253 |
asleep | -0.240 |
Token | the |
Token ID | 262 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
aches | +0.026 |
hardly | +0.024 |
iable | +0.022 |
imes | +0.022 |
ons | +0.022 |
Neg logit contributions | |
extingu | -0.045 |
ksh | -0.045 |
Year | -0.044 |
ucks | -0.043 |
boy | -0.043 |
Token | engine |
Token ID | 3113 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
aches | +0.032 |
vern | +0.029 |
exercise | +0.029 |
ag | +0.028 |
earned | +0.028 |
Neg logit contributions | |
ksh | -0.025 |
extingu | -0.024 |
ucks | -0.024 |
maid | -0.024 |
cy | -0.024 |
Token | started |
Token ID | 2067 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
extingu | +0.023 |
girl | +0.022 |
Year | +0.022 |
boy | +0.022 |
ksh | +0.022 |
Neg logit contributions | |
aches | -0.019 |
ending | -0.017 |
achieve | -0.017 |
accomplished | -0.017 |
gh | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
vern | +0.032 |
aches | +0.032 |
gh | +0.031 |
hardly | +0.030 |
ending | +0.029 |
Neg logit contributions | |
boy | -0.072 |
girl | -0.071 |
Year | -0.067 |
cy | -0.064 |
extingu | -0.063 |
Token | some |
Token ID | 617 |
Feature activation | -1.02e-03 |
Pos logit contributions | |
vern | +0.083 |
aches | +0.083 |
earned | +0.077 |
imes | +0.076 |
ending | +0.075 |
Neg logit contributions | |
boy | -0.075 |
girl | -0.070 |
Year | -0.064 |
extingu | -0.063 |
asleep | -0.060 |
Token | spark |
Token ID | 9009 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
vern | +0.002 |
aches | +0.002 |
earned | +0.002 |
imes | +0.002 |
fters | +0.002 |
Neg logit contributions | |
boy | -0.002 |
girl | -0.002 |
Year | -0.002 |
extingu | -0.001 |
asleep | -0.001 |
Token | ly |
Token ID | 306 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
boy | +0.028 |
girl | +0.026 |
Year | +0.025 |
extingu | +0.025 |
asleep | +0.023 |
Neg logit contributions | |
aches | -0.024 |
vern | -0.022 |
imes | -0.021 |
ag | -0.021 |
earned | -0.021 |
Token | neck |
Token ID | 7393 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Year | +0.059 |
boy | +0.059 |
ksh | +0.058 |
extingu | +0.056 |
Claus | +0.055 |
Neg logit contributions | |
aches | -0.052 |
ade | -0.047 |
ons | -0.046 |
imes | -0.044 |
ough | -0.043 |
Token | l |
Token ID | 75 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
aches | +0.180 |
vern | +0.178 |
earned | +0.163 |
imes | +0.162 |
ending | +0.160 |
Neg logit contributions | |
boy | -0.211 |
girl | -0.200 |
Year | -0.185 |
extingu | -0.182 |
asleep | -0.174 |
Token | aces |
Token ID | 2114 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
boy | +0.055 |
girl | +0.053 |
extingu | +0.051 |
asleep | +0.050 |
Year | +0.050 |
Neg logit contributions | |
vern | -0.014 |
aches | -0.014 |
earned | -0.012 |
fters | -0.011 |
iable | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
vern | +0.309 |
aches | +0.307 |
earned | +0.294 |
fters | +0.285 |
imes | +0.283 |
Neg logit contributions | |
boy | -0.244 |
girl | -0.232 |
extingu | -0.205 |
asleep | -0.204 |
Year | -0.194 |
Token | sil |
Token ID | 3313 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
aches | +0.018 |
vern | +0.017 |
ons | +0.016 |
imes | +0.016 |
earned | +0.016 |
Neg logit contributions | |
boy | -0.018 |
girl | -0.017 |
Year | -0.017 |
extingu | -0.017 |
ksh | -0.016 |
Token | ky |
Token ID | 2584 |
Feature activation | -8.90e-04 |
Pos logit contributions | |
boy | +0.021 |
girl | +0.020 |
Year | +0.019 |
extingu | +0.017 |
cy | +0.016 |
Neg logit contributions | |
vern | -0.047 |
aches | -0.046 |
imes | -0.044 |
earned | -0.043 |
achieve | -0.043 |
Token | scar |
Token ID | 10153 |
Feature activation | -8.56e-02 |
Pos logit contributions | |
aches | +0.001 |
vern | +0.001 |
gh | +0.001 |
ons | +0.001 |
ough | +0.001 |
Neg logit contributions | |
boy | -0.002 |
girl | -0.001 |
Year | -0.001 |
extingu | -0.001 |
asleep | -0.001 |
Token | ves |
Token ID | 1158 |
Feature activation | -8.04e-02 |
Pos logit contributions | |
vern | +0.083 |
earned | +0.081 |
aches | +0.080 |
imes | +0.073 |
ending | +0.072 |
Neg logit contributions | |
boy | -0.202 |
girl | -0.195 |
extingu | -0.183 |
Year | -0.181 |
asleep | -0.179 |
Token | together |
Token ID | 1978 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
aches | +0.088 |
vern | +0.086 |
gh | +0.077 |
earned | +0.076 |
iable | +0.075 |
Neg logit contributions | |
boy | -0.131 |
girl | -0.127 |
Year | -0.120 |
extingu | -0.116 |
ksh | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | -5.32e-04 |
Pos logit contributions | |
boy | +0.021 |
girl | +0.019 |
extingu | +0.017 |
Year | +0.017 |
asleep | +0.017 |
Neg logit contributions | |
vern | -0.022 |
aches | -0.022 |
earned | -0.021 |
imes | -0.021 |
fters | -0.021 |
Token | After |
Token ID | 2293 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
imes | +0.001 |
vern | +0.001 |
ough | +0.001 |
aches | +0.001 |
earned | +0.001 |
Neg logit contributions | |
boy | -0.001 |
girl | -0.001 |
extingu | -0.001 |
Year | -0.001 |
asleep | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
aches | +0.045 |
vern | +0.044 |
gh | +0.042 |
ons | +0.041 |
achieve | +0.040 |
Neg logit contributions | |
boy | -0.067 |
girl | -0.065 |
extingu | -0.061 |
ksh | -0.060 |
Year | -0.059 |
Token | few |
Token ID | 1178 |
Feature activation | -5.69e-03 |
Pos logit contributions | |
boy | +0.021 |
girl | +0.020 |
Year | +0.020 |
extingu | +0.020 |
asleep | +0.019 |
Neg logit contributions | |
vern | -0.019 |
aches | -0.018 |
gh | -0.018 |
fters | -0.017 |
iable | -0.017 |
Token | attempts |
Token ID | 6370 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
vern | +0.009 |
aches | +0.009 |
earned | +0.009 |
iable | +0.009 |
ending | +0.009 |
Neg logit contributions | |
boy | -0.010 |
girl | -0.010 |
Year | -0.009 |
extingu | -0.009 |
asleep | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
vern | +0.267 |
aches | +0.266 |
earned | +0.245 |
imes | +0.242 |
ending | +0.240 |
Neg logit contributions | |
boy | -0.291 |
girl | -0.277 |
Year | -0.254 |
extingu | -0.251 |
asleep | -0.238 |
Token | they |
Token ID | 484 |
Feature activation | -7.39e-04 |
Pos logit contributions | |
aches | +0.025 |
hardly | +0.024 |
imes | +0.023 |
iable | +0.022 |
ons | +0.021 |
Neg logit contributions | |
extingu | -0.040 |
ksh | -0.039 |
Year | -0.039 |
boy | -0.039 |
ucks | -0.039 |
Token | finally |
Token ID | 3443 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
aches | +0.001 |
vern | +0.001 |
iable | +0.001 |
accomplished | +0.001 |
imes | +0.001 |
Neg logit contributions | |
boy | -0.001 |
girl | -0.001 |
Year | -0.001 |
extingu | -0.001 |
asleep | -0.001 |
Token | got |
Token ID | 1392 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
vern | +0.034 |
aches | +0.033 |
earned | +0.031 |
fters | +0.030 |
ending | +0.030 |
Neg logit contributions | |
boy | -0.046 |
girl | -0.043 |
extingu | -0.039 |
Year | -0.038 |
asleep | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
aches | +0.035 |
vern | +0.035 |
imes | +0.032 |
iable | +0.032 |
earned | +0.031 |
Neg logit contributions | |
boy | -0.039 |
girl | -0.037 |
Year | -0.035 |
extingu | -0.035 |
ksh | -0.032 |
Token | 's |
Token ID | 338 |
Feature activation | -9.28e-03 |
Pos logit contributions | |
boy | +0.003 |
girl | +0.003 |
Year | +0.002 |
extingu | +0.002 |
asleep | +0.002 |
Neg logit contributions | |
vern | -0.003 |
aches | -0.003 |
earned | -0.002 |
imes | -0.002 |
ending | -0.002 |
Token | tie |
Token ID | 9839 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
aches | +0.013 |
vern | +0.013 |
earned | +0.012 |
achieve | +0.012 |
ough | +0.012 |
Neg logit contributions | |
boy | -0.019 |
girl | -0.018 |
Year | -0.017 |
extingu | -0.017 |
asleep | -0.016 |
Token | your |
Token ID | 534 |
Feature activation | -9.00e-03 |
Pos logit contributions | |
aches | +0.078 |
vern | +0.077 |
ons | +0.072 |
ag | +0.070 |
iable | +0.070 |
Neg logit contributions | |
boy | -0.104 |
girl | -0.101 |
cottage | -0.092 |
extingu | -0.092 |
Year | -0.092 |
Token | sho |
Token ID | 7354 |
Feature activation | -8.70e-02 |
Pos logit contributions | |
vern | +0.017 |
aches | +0.016 |
ending | +0.015 |
earned | +0.015 |
imes | +0.015 |
Neg logit contributions | |
boy | -0.015 |
girl | -0.014 |
Year | -0.012 |
extingu | -0.012 |
asleep | -0.012 |
Token | el |
Token ID | 417 |
Feature activation | -2.48e-03 |
Pos logit contributions | |
aches | +0.174 |
vern | +0.172 |
fters | +0.165 |
Days | +0.164 |
achieve | +0.164 |
Neg logit contributions | |
boy | -0.117 |
girl | -0.109 |
cy | -0.107 |
Year | -0.100 |
extingu | -0.099 |
Token | aces |
Token ID | 2114 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
vern | +0.002 |
aches | +0.002 |
fters | +0.002 |
iable | +0.002 |
ending | +0.002 |
Neg logit contributions | |
boy | -0.006 |
girl | -0.006 |
extingu | -0.006 |
Year | -0.006 |
asleep | -0.005 |
Token | together |
Token ID | 1978 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
vern | +0.319 |
aches | +0.318 |
earned | +0.297 |
imes | +0.294 |
ending | +0.291 |
Neg logit contributions | |
boy | -0.241 |
girl | -0.226 |
Year | -0.202 |
extingu | -0.200 |
asleep | -0.187 |
Token | so |
Token ID | 523 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
boy | +0.022 |
girl | +0.021 |
extingu | +0.019 |
Year | +0.019 |
ksh | +0.017 |
Neg logit contributions | |
aches | -0.022 |
vern | -0.022 |
ough | -0.020 |
imes | -0.020 |
earned | -0.020 |
Token | they |
Token ID | 484 |
Feature activation | -2.65e-03 |
Pos logit contributions | |
vern | +0.055 |
aches | +0.054 |
earned | +0.051 |
imes | +0.050 |
fters | +0.049 |
Neg logit contributions | |
boy | -0.055 |
girl | -0.052 |
Year | -0.047 |
extingu | -0.047 |
asleep | -0.045 |
Token | won |
Token ID | 1839 |
Feature activation | -3.88e-03 |
Pos logit contributions | |
aches | +0.004 |
vern | +0.004 |
earned | +0.004 |
iable | +0.004 |
imes | +0.004 |
Neg logit contributions | |
boy | -0.005 |
girl | -0.004 |
Year | -0.004 |
extingu | -0.004 |
asleep | -0.004 |
Token | 't |
Token ID | 470 |
Feature activation | -6.35e-03 |
Pos logit contributions | |
vern | +0.004 |
aches | +0.004 |
earned | +0.004 |
imes | +0.004 |
ending | +0.004 |
Neg logit contributions | |
boy | -0.009 |
girl | -0.009 |
Year | -0.008 |
extingu | -0.008 |
asleep | -0.008 |
Token | Its |
Token ID | 6363 |
Feature activation | -9.10e-03 |
Pos logit contributions | |
vern | +0.024 |
aches | +0.024 |
ough | +0.023 |
earned | +0.022 |
ag | +0.022 |
Neg logit contributions | |
boy | -0.027 |
girl | -0.027 |
extingu | -0.025 |
Year | -0.024 |
asleep | -0.024 |
Token | bright |
Token ID | 6016 |
Feature activation | -5.39e-03 |
Pos logit contributions | |
vern | +0.018 |
aches | +0.017 |
earned | +0.016 |
fters | +0.016 |
ending | +0.016 |
Neg logit contributions | |
boy | -0.015 |
girl | -0.014 |
extingu | -0.012 |
Year | -0.011 |
asleep | -0.011 |
Token | colors |
Token ID | 7577 |
Feature activation | -7.04e-02 |
Pos logit contributions | |
aches | +0.010 |
vern | +0.010 |
earned | +0.009 |
imes | +0.009 |
ag | +0.009 |
Neg logit contributions | |
boy | -0.008 |
girl | -0.008 |
Year | -0.007 |
extingu | -0.007 |
asleep | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
vern | +0.123 |
aches | +0.120 |
earned | +0.114 |
fters | +0.112 |
imes | +0.112 |
Neg logit contributions | |
boy | -0.123 |
girl | -0.116 |
extingu | -0.102 |
Year | -0.102 |
asleep | -0.099 |
Token | l |
Token ID | 300 |
Feature activation | -3.65e-03 |
Pos logit contributions | |
aches | +0.021 |
vern | +0.020 |
ons | +0.019 |
gh | +0.019 |
earned | +0.019 |
Neg logit contributions | |
boy | -0.021 |
girl | -0.020 |
Year | -0.019 |
extingu | -0.019 |
asleep | -0.018 |
Token | aces |
Token ID | 2114 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
fters | +0.005 |
vern | +0.005 |
earned | +0.005 |
aches | +0.005 |
iable | +0.005 |
Neg logit contributions | |
boy | -0.007 |
girl | -0.007 |
cy | -0.006 |
extingu | -0.006 |
asleep | -0.006 |
Token | made |
Token ID | 925 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
vern | +0.287 |
aches | +0.277 |
earned | +0.270 |
fters | +0.267 |
imes | +0.266 |
Neg logit contributions | |
boy | -0.275 |
girl | -0.259 |
asleep | -0.225 |
work | -0.223 |
extingu | -0.219 |
Token | it |
Token ID | 340 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
boy | +0.023 |
girl | +0.022 |
extingu | +0.022 |
Year | +0.022 |
ksh | +0.021 |
Neg logit contributions | |
aches | -0.019 |
vern | -0.018 |
ag | -0.017 |
ons | -0.017 |
imes | -0.016 |
Token | look |
Token ID | 804 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
aches | +0.022 |
vern | +0.022 |
earned | +0.020 |
imes | +0.020 |
ending | +0.020 |
Neg logit contributions | |
boy | -0.020 |
girl | -0.019 |
Year | -0.017 |
extingu | -0.017 |
asleep | -0.016 |
Token | very |
Token ID | 845 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
boy | +0.052 |
girl | +0.049 |
Year | +0.047 |
extingu | +0.046 |
asleep | +0.043 |
Neg logit contributions | |
aches | -0.040 |
vern | -0.039 |
earned | -0.036 |
iable | -0.036 |
gh | -0.035 |
Token | nice |
Token ID | 3621 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
vern | +0.058 |
aches | +0.057 |
earned | +0.052 |
imes | +0.051 |
iable | +0.051 |
Neg logit contributions | |
boy | -0.067 |
girl | -0.064 |
Year | -0.059 |
extingu | -0.059 |
asleep | -0.056 |
Token | brace |
Token ID | 22581 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
aches | +0.006 |
achieve | +0.005 |
vern | +0.005 |
fters | +0.005 |
expect | +0.005 |
Neg logit contributions | |
boy | -0.008 |
Year | -0.007 |
girl | -0.007 |
ksh | -0.007 |
cy | -0.007 |
Token | lets |
Token ID | 5289 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
aches | +0.089 |
vern | +0.089 |
earned | +0.082 |
imes | +0.080 |
ending | +0.080 |
Neg logit contributions | |
boy | -0.102 |
girl | -0.096 |
Year | -0.089 |
extingu | -0.087 |
asleep | -0.084 |
Token | and |
Token ID | 290 |
Feature activation | -4.74e-03 |
Pos logit contributions | |
aches | +0.202 |
vern | +0.199 |
imes | +0.182 |
ag | +0.182 |
gh | +0.180 |
Neg logit contributions | |
boy | -0.172 |
girl | -0.162 |
Year | -0.152 |
extingu | -0.146 |
ksh | -0.138 |
Token | neck |
Token ID | 7393 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
aches | +0.008 |
vern | +0.007 |
ons | +0.006 |
earned | +0.006 |
achieve | +0.006 |
Neg logit contributions | |
boy | -0.009 |
Year | -0.008 |
girl | -0.008 |
asleep | -0.008 |
ksh | -0.008 |
Token | l |
Token ID | 75 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
aches | +0.171 |
vern | +0.170 |
earned | +0.155 |
imes | +0.153 |
gh | +0.151 |
Neg logit contributions | |
boy | -0.214 |
girl | -0.204 |
Year | -0.188 |
extingu | -0.186 |
asleep | -0.179 |
Token | aces |
Token ID | 2114 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
boy | +0.057 |
girl | +0.054 |
extingu | +0.052 |
asleep | +0.052 |
Year | +0.051 |
Neg logit contributions | |
vern | -0.014 |
aches | -0.013 |
earned | -0.012 |
fters | -0.011 |
iable | -0.011 |
Token | with |
Token ID | 351 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
vern | +0.323 |
aches | +0.321 |
earned | +0.306 |
imes | +0.300 |
fters | +0.298 |
Neg logit contributions | |
boy | -0.232 |
girl | -0.217 |
extingu | -0.190 |
Year | -0.187 |
asleep | -0.182 |
Token | copper |
Token ID | 15317 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
boy | +0.040 |
girl | +0.038 |
Year | +0.036 |
extingu | +0.035 |
asleep | +0.033 |
Neg logit contributions | |
aches | -0.041 |
vern | -0.040 |
imes | -0.037 |
earned | -0.037 |
ag | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -8.40e-03 |
Pos logit contributions | |
boy | +0.042 |
girl | +0.040 |
Year | +0.038 |
extingu | +0.036 |
ksh | +0.034 |
Neg logit contributions | |
aches | -0.042 |
vern | -0.040 |
imes | -0.038 |
ons | -0.037 |
earned | -0.037 |
Token | They |
Token ID | 1119 |
Feature activation | -1.67e-03 |
Pos logit contributions | |
aches | +0.012 |
imes | +0.012 |
ough | +0.011 |
vern | +0.011 |
earned | +0.011 |
Neg logit contributions | |
boy | -0.015 |
girl | -0.015 |
work | -0.015 |
extingu | -0.014 |
Year | -0.014 |
Token | think |
Token ID | 892 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
aches | +0.003 |
vern | +0.003 |
earned | +0.002 |
imes | +0.002 |
iable | +0.002 |
Neg logit contributions | |
boy | -0.003 |
girl | -0.003 |
Year | -0.003 |
extingu | -0.003 |
asleep | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -2.17e-03 |
Pos logit contributions | |
boy | +0.021 |
girl | +0.020 |
Year | +0.019 |
extingu | +0.019 |
ksh | +0.018 |
Neg logit contributions | |
vern | -0.015 |
aches | -0.015 |
ons | -0.014 |
ending | -0.013 |
iable | -0.013 |
Token | There |
Token ID | 1318 |
Feature activation | +6.54e-03 |
Pos logit contributions | |
vern | +0.004 |
aches | +0.004 |
earned | +0.003 |
gh | +0.003 |
fters | +0.003 |
Neg logit contributions | |
boy | -0.004 |
girl | -0.004 |
Year | -0.003 |
extingu | -0.003 |
asleep | -0.003 |
Token | were |
Token ID | 547 |
Feature activation | +9.18e-03 |
Pos logit contributions | |
boy | +0.012 |
girl | +0.012 |
Year | +0.011 |
extingu | +0.011 |
asleep | +0.010 |
Neg logit contributions | |
aches | -0.010 |
vern | -0.010 |
earned | -0.009 |
imes | -0.009 |
gh | -0.009 |
Token | neck |
Token ID | 7393 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
boy | +0.018 |
extingu | +0.018 |
girl | +0.017 |
Year | +0.017 |
ksh | +0.017 |
Neg logit contributions | |
aches | -0.013 |
vern | -0.011 |
ons | -0.011 |
imes | -0.011 |
gh | -0.011 |
Token | l |
Token ID | 75 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
aches | +0.156 |
vern | +0.139 |
ons | +0.134 |
gh | +0.128 |
ade | +0.127 |
Neg logit contributions | |
boy | -0.227 |
girl | -0.216 |
extingu | -0.209 |
Year | -0.204 |
ksh | -0.198 |
Token | aces |
Token ID | 2114 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
boy | +0.071 |
girl | +0.068 |
Year | +0.064 |
extingu | +0.064 |
asleep | +0.061 |
Neg logit contributions | |
aches | -0.014 |
vern | -0.013 |
earned | -0.011 |
ending | -0.011 |
imes | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -5.61e-03 |
Pos logit contributions | |
aches | +0.315 |
vern | +0.313 |
earned | +0.292 |
ending | +0.290 |
iable | +0.289 |
Neg logit contributions | |
boy | -0.242 |
girl | -0.226 |
Year | -0.208 |
extingu | -0.204 |
ksh | -0.187 |
Token | rings |
Token ID | 13917 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
aches | +0.010 |
vern | +0.009 |
ons | +0.009 |
earned | +0.009 |
gh | +0.008 |
Neg logit contributions | |
boy | -0.010 |
extingu | -0.009 |
girl | -0.009 |
Year | -0.009 |
ksh | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
aches | +0.034 |
vern | +0.032 |
gh | +0.030 |
iable | +0.030 |
ag | +0.030 |
Neg logit contributions | |
boy | -0.034 |
girl | -0.032 |
Year | -0.031 |
extingu | -0.030 |
ksh | -0.028 |
Token | spark |
Token ID | 9009 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
boy | +0.053 |
girl | +0.050 |
Year | +0.048 |
extingu | +0.047 |
ksh | +0.045 |
Neg logit contributions | |
aches | -0.046 |
vern | -0.044 |
imes | -0.042 |
ons | -0.041 |
earned | -0.041 |
Token | les |
Token ID | 829 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
boy | +0.039 |
girl | +0.037 |
Year | +0.035 |
extingu | +0.035 |
cottage | +0.033 |
Neg logit contributions | |
aches | -0.033 |
vern | -0.030 |
ag | -0.030 |
ons | -0.030 |
imes | -0.029 |
Token | quickly |
Token ID | 2952 |
Feature activation | -9.46e-03 |
Pos logit contributions | |
aches | +0.009 |
vern | +0.009 |
ons | +0.008 |
ending | +0.008 |
ade | +0.008 |
Neg logit contributions | |
boy | -0.012 |
girl | -0.012 |
Year | -0.011 |
extingu | -0.011 |
asleep | -0.011 |
Token | tied |
Token ID | 8165 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
vern | +0.018 |
aches | +0.017 |
earned | +0.017 |
imes | +0.016 |
ag | +0.016 |
Neg logit contributions | |
boy | -0.015 |
girl | -0.014 |
extingu | -0.013 |
Year | -0.012 |
asleep | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
aches | +0.045 |
vern | +0.045 |
imes | +0.042 |
ons | +0.041 |
gh | +0.041 |
Neg logit contributions | |
boy | -0.060 |
girl | -0.058 |
Year | -0.056 |
extingu | -0.054 |
cottage | -0.052 |
Token | sho |
Token ID | 7354 |
Feature activation | -8.19e-02 |
Pos logit contributions | |
aches | +0.031 |
vern | +0.031 |
ending | +0.029 |
iable | +0.029 |
earned | +0.029 |
Neg logit contributions | |
boy | -0.025 |
girl | -0.024 |
asleep | -0.020 |
extingu | -0.019 |
t | -0.019 |
Token | el |
Token ID | 417 |
Feature activation | +3.23e-03 |
Pos logit contributions | |
aches | +0.183 |
vern | +0.179 |
achieve | +0.176 |
fters | +0.175 |
accomplished | +0.170 |
Neg logit contributions | |
boy | -0.094 |
cy | -0.092 |
girl | -0.088 |
extingu | -0.078 |
eddy | -0.076 |
Token | aces |
Token ID | 2114 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
boy | +0.007 |
girl | +0.007 |
extingu | +0.007 |
asleep | +0.007 |
t | +0.006 |
Neg logit contributions | |
vern | -0.003 |
aches | -0.003 |
achieve | -0.003 |
fters | -0.003 |
iable | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -6.98e-03 |
Pos logit contributions | |
aches | +0.374 |
vern | +0.368 |
affles | +0.360 |
earned | +0.355 |
fters | +0.354 |
Neg logit contributions | |
boy | -0.173 |
girl | -0.160 |
asleep | -0.138 |
extingu | -0.128 |
work | -0.119 |
Token | ran |
Token ID | 4966 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
vern | +0.012 |
aches | +0.012 |
earned | +0.011 |
imes | +0.011 |
ending | +0.011 |
Neg logit contributions | |
boy | -0.012 |
girl | -0.012 |
extingu | -0.010 |
Year | -0.010 |
asleep | -0.010 |
Token | away |
Token ID | 1497 |
Feature activation | -1.19e-03 |
Pos logit contributions | |
vern | +0.042 |
aches | +0.041 |
ag | +0.039 |
gh | +0.038 |
earned | +0.038 |
Neg logit contributions | |
boy | -0.046 |
girl | -0.043 |
Year | -0.041 |
extingu | -0.040 |
work | -0.037 |
Token | from |
Token ID | 422 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
vern | +0.002 |
aches | +0.002 |
achieve | +0.002 |
gh | +0.002 |
ag | +0.002 |
Neg logit contributions | |
boy | -0.002 |
girl | -0.002 |
Year | -0.002 |
ksh | -0.002 |
extingu | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -3.60e-03 |
Pos logit contributions | |
boy | +0.032 |
girl | +0.031 |
extingu | +0.029 |
Year | +0.029 |
ksh | +0.028 |
Neg logit contributions | |
aches | -0.024 |
vern | -0.022 |
imes | -0.021 |
fters | -0.021 |
earned | -0.021 |
Token | her |
Token ID | 607 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
vern | +0.080 |
aches | +0.080 |
earned | +0.073 |
imes | +0.072 |
fters | +0.071 |
Neg logit contributions | |
boy | -0.091 |
girl | -0.086 |
Year | -0.080 |
extingu | -0.079 |
asleep | -0.074 |
Token | mum |
Token ID | 25682 |
Feature activation | -2.05e-03 |
Pos logit contributions | |
vern | +0.036 |
aches | +0.036 |
earned | +0.033 |
gh | +0.032 |
imes | +0.032 |
Neg logit contributions | |
boy | -0.036 |
girl | -0.034 |
Year | -0.031 |
extingu | -0.031 |
asleep | -0.029 |
Token | 's |
Token ID | 338 |
Feature activation | -7.42e-03 |
Pos logit contributions | |
vern | +0.004 |
aches | +0.003 |
earned | +0.003 |
fters | +0.003 |
imes | +0.003 |
Neg logit contributions | |
boy | -0.004 |
girl | -0.004 |
extingu | -0.003 |
Year | -0.003 |
asleep | -0.003 |
Token | shoe |
Token ID | 17292 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
vern | +0.012 |
aches | +0.012 |
earned | +0.011 |
ough | +0.011 |
gh | +0.011 |
Neg logit contributions | |
boy | -0.013 |
girl | -0.012 |
Year | -0.012 |
extingu | -0.011 |
ksh | -0.011 |
Token | l |
Token ID | 300 |
Feature activation | +3.18e-04 |
Pos logit contributions | |
vern | +0.098 |
aches | +0.097 |
earned | +0.090 |
imes | +0.089 |
fters | +0.089 |
Neg logit contributions | |
boy | -0.089 |
girl | -0.084 |
Year | -0.074 |
extingu | -0.074 |
asleep | -0.073 |
Token | aces |
Token ID | 2114 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
boy | +0.001 |
girl | +0.001 |
asleep | +0.001 |
extingu | +0.001 |
work | +0.001 |
Neg logit contributions | |
aches | -0.000 |
vern | -0.000 |
earned | -0.000 |
hardly | -0.000 |
iable | -0.000 |
Token | together |
Token ID | 1978 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
aches | +0.314 |
vern | +0.310 |
earned | +0.294 |
affles | +0.292 |
fters | +0.290 |
Neg logit contributions | |
boy | -0.230 |
girl | -0.219 |
asleep | -0.205 |
work | -0.187 |
extingu | -0.185 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
boy | +0.025 |
girl | +0.024 |
asleep | +0.021 |
extingu | +0.020 |
Year | +0.020 |
Neg logit contributions | |
vern | -0.033 |
aches | -0.032 |
earned | -0.031 |
fters | -0.030 |
ending | -0.030 |
Token | One |
Token ID | 1881 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
aches | +0.026 |
vern | +0.025 |
fters | +0.023 |
gh | +0.023 |
ending | +0.023 |
Neg logit contributions | |
boy | -0.019 |
girl | -0.017 |
Year | -0.015 |
asleep | -0.014 |
extingu | -0.013 |
Token | day |
Token ID | 1110 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
boy | +0.022 |
girl | +0.021 |
Year | +0.017 |
cy | +0.017 |
asleep | +0.016 |
Neg logit contributions | |
vern | -0.021 |
aches | -0.020 |
fters | -0.019 |
iable | -0.019 |
imes | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
boy | +0.032 |
girl | +0.031 |
Year | +0.023 |
asleep | +0.022 |
tent | +0.021 |
Neg logit contributions | |
vern | -0.047 |
aches | -0.046 |
earned | -0.043 |
fters | -0.042 |
ag | -0.042 |
Token | pped |
Token ID | 1496 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
vern | +0.002 |
aches | +0.002 |
earned | +0.002 |
iable | +0.002 |
imes | +0.002 |
Neg logit contributions | |
boy | -0.006 |
girl | -0.006 |
extingu | -0.006 |
asleep | -0.006 |
Year | -0.005 |
Token | on |
Token ID | 319 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
vern | +0.058 |
aches | +0.057 |
earned | +0.054 |
imes | +0.053 |
ending | +0.053 |
Neg logit contributions | |
boy | -0.041 |
girl | -0.038 |
extingu | -0.033 |
Year | -0.033 |
asleep | -0.032 |
Token | her |
Token ID | 607 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
vern | +0.084 |
aches | +0.084 |
gh | +0.076 |
earned | +0.076 |
fters | +0.075 |
Neg logit contributions | |
boy | -0.107 |
girl | -0.102 |
Year | -0.095 |
extingu | -0.094 |
work | -0.090 |
Token | sho |
Token ID | 7354 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
vern | +0.054 |
aches | +0.052 |
ending | +0.052 |
imes | +0.051 |
fters | +0.050 |
Neg logit contributions | |
boy | -0.031 |
girl | -0.029 |
t | -0.027 |
asleep | -0.025 |
tent | -0.022 |
Token | el |
Token ID | 417 |
Feature activation | +3.45e-04 |
Pos logit contributions | |
vern | +0.197 |
aches | +0.195 |
achieve | +0.189 |
fters | +0.188 |
Days | +0.187 |
Neg logit contributions | |
cy | -0.090 |
boy | -0.085 |
girl | -0.080 |
ASH | -0.076 |
ucks | -0.072 |
Token | aces |
Token ID | 2114 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
boy | +0.001 |
girl | +0.001 |
t | +0.001 |
asleep | +0.001 |
extingu | +0.001 |
Neg logit contributions | |
vern | -0.000 |
fters | -0.000 |
achieve | -0.000 |
iable | -0.000 |
accomplished | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
aches | +0.451 |
affles | +0.451 |
vern | +0.439 |
earned | +0.432 |
fters | +0.425 |
Neg logit contributions | |
boy | -0.098 |
girl | -0.083 |
asleep | -0.081 |
t | -0.060 |
extingu | -0.045 |
Token | dropped |
Token ID | 5710 |
Feature activation | +8.93e-03 |
Pos logit contributions | |
vern | +0.024 |
aches | +0.022 |
earned | +0.022 |
ending | +0.021 |
imes | +0.021 |
Neg logit contributions | |
boy | -0.022 |
girl | -0.021 |
asleep | -0.018 |
t | -0.018 |
extingu | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
boy | +0.022 |
Year | +0.021 |
girl | +0.021 |
cottage | +0.020 |
Claus | +0.020 |
Neg logit contributions | |
aches | -0.008 |
imes | -0.007 |
vern | -0.007 |
ons | -0.007 |
ag | -0.006 |
Token | pencil |
Token ID | 21613 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
vern | +0.047 |
aches | +0.046 |
ending | +0.044 |
earned | +0.043 |
fters | +0.043 |
Neg logit contributions | |
boy | -0.040 |
girl | -0.038 |
asleep | -0.032 |
Year | -0.032 |
extingu | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
vern | +0.090 |
aches | +0.090 |
earned | +0.085 |
fters | +0.083 |
imes | +0.083 |
Neg logit contributions | |
boy | -0.072 |
girl | -0.067 |
extingu | -0.060 |
asleep | -0.059 |
Year | -0.056 |
Token | like |
Token ID | 588 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
aches | +0.028 |
vern | +0.027 |
imes | +0.025 |
earned | +0.025 |
ons | +0.025 |
Neg logit contributions | |
boy | -0.026 |
girl | -0.024 |
Year | -0.022 |
extingu | -0.022 |
asleep | -0.021 |
Token | bright |
Token ID | 6016 |
Feature activation | -4.34e-03 |
Pos logit contributions | |
boy | +0.018 |
girl | +0.017 |
extingu | +0.016 |
Year | +0.015 |
ksh | +0.015 |
Neg logit contributions | |
aches | -0.017 |
vern | -0.017 |
imes | -0.016 |
ons | -0.016 |
gh | -0.015 |
Token | yellow |
Token ID | 7872 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
aches | +0.008 |
vern | +0.008 |
ons | +0.008 |
imes | +0.008 |
earned | +0.008 |
Neg logit contributions | |
boy | -0.007 |
girl | -0.006 |
extingu | -0.006 |
Year | -0.005 |
ksh | -0.005 |
Token | neck |
Token ID | 7393 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
aches | +0.039 |
vern | +0.038 |
earned | +0.036 |
imes | +0.036 |
ons | +0.036 |
Neg logit contributions | |
boy | -0.035 |
girl | -0.033 |
extingu | -0.030 |
Year | -0.030 |
asleep | -0.028 |
Token | l |
Token ID | 75 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
aches | +0.195 |
vern | +0.194 |
earned | +0.180 |
imes | +0.177 |
ending | +0.176 |
Neg logit contributions | |
boy | -0.189 |
girl | -0.179 |
Year | -0.162 |
extingu | -0.161 |
asleep | -0.153 |
Token | aces |
Token ID | 2114 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
boy | +0.037 |
girl | +0.036 |
Year | +0.033 |
extingu | +0.033 |
asleep | +0.032 |
Neg logit contributions | |
vern | -0.032 |
aches | -0.032 |
earned | -0.029 |
iable | -0.029 |
fters | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
vern | +0.327 |
aches | +0.324 |
earned | +0.310 |
gh | +0.303 |
fters | +0.303 |
Neg logit contributions | |
boy | -0.217 |
girl | -0.206 |
asleep | -0.183 |
extingu | -0.175 |
work | -0.174 |
Token | flower |
Token ID | 15061 |
Feature activation | -3.53e-03 |
Pos logit contributions | |
aches | +0.022 |
vern | +0.020 |
imes | +0.019 |
earned | +0.019 |
ons | +0.019 |
Neg logit contributions | |
boy | -0.022 |
girl | -0.020 |
extingu | -0.020 |
Year | -0.020 |
work | -0.018 |
Token | crown |
Token ID | 12389 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
aches | +0.006 |
vern | +0.006 |
imes | +0.006 |
earned | +0.005 |
ons | +0.005 |
Neg logit contributions | |
boy | -0.006 |
girl | -0.006 |
Year | -0.005 |
extingu | -0.005 |
asleep | -0.005 |
Token | s |
Token ID | 82 |
Feature activation | -7.36e-03 |
Pos logit contributions | |
vern | +0.020 |
aches | +0.020 |
earned | +0.019 |
imes | +0.018 |
ending | +0.018 |
Neg logit contributions | |
boy | -0.020 |
girl | -0.019 |
Year | -0.017 |
extingu | -0.017 |
asleep | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
aches | +0.012 |
vern | +0.012 |
imes | +0.011 |
gh | +0.011 |
earned | +0.010 |
Neg logit contributions | |
boy | -0.014 |
girl | -0.013 |
Year | -0.012 |
extingu | -0.012 |
ksh | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
vern | +0.032 |
aches | +0.031 |
earned | +0.030 |
ending | +0.029 |
imes | +0.028 |
Neg logit contributions | |
boy | -0.037 |
girl | -0.036 |
Year | -0.032 |
asleep | -0.032 |
extingu | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
aches | +0.049 |
vern | +0.048 |
iable | +0.046 |
imes | +0.046 |
fters | +0.046 |
Neg logit contributions | |
boy | -0.035 |
girl | -0.034 |
asleep | -0.028 |
t | -0.027 |
Year | -0.025 |
Token | tie |
Token ID | 9839 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
imes | +0.021 |
earned | +0.020 |
vern | +0.020 |
affles | +0.020 |
ending | +0.020 |
Neg logit contributions | |
boy | -0.018 |
girl | -0.018 |
t | -0.016 |
Sn | -0.014 |
duck | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -9.27e-03 |
Pos logit contributions | |
vern | +0.089 |
aches | +0.087 |
earned | +0.083 |
ending | +0.082 |
imes | +0.081 |
Neg logit contributions | |
boy | -0.085 |
girl | -0.081 |
asleep | -0.071 |
extingu | -0.070 |
Year | -0.068 |
Token | l |
Token ID | 300 |
Feature activation | -3.50e-04 |
Pos logit contributions | |
aches | +0.017 |
vern | +0.017 |
earned | +0.015 |
fters | +0.015 |
imes | +0.015 |
Neg logit contributions | |
boy | -0.015 |
girl | -0.014 |
Year | -0.013 |
extingu | -0.013 |
asleep | -0.012 |
Token | aces |
Token ID | 2114 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
iable | +0.000 |
achieve | +0.000 |
vern | +0.000 |
aches | +0.000 |
earned | +0.000 |
Neg logit contributions | |
girl | -0.001 |
boy | -0.001 |
asleep | -0.001 |
tent | -0.001 |
te | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
affles | +0.333 |
aches | +0.327 |
vern | +0.319 |
fters | +0.315 |
earned | +0.312 |
Neg logit contributions | |
boy | -0.210 |
girl | -0.198 |
asleep | -0.181 |
work | -0.158 |
t | -0.155 |
Token | She |
Token ID | 1375 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
vern | +0.028 |
aches | +0.027 |
earned | +0.025 |
fters | +0.025 |
ending | +0.025 |
Neg logit contributions | |
boy | -0.024 |
girl | -0.023 |
Year | -0.019 |
asleep | -0.019 |
extingu | -0.018 |
Token | thought |
Token ID | 1807 |
Feature activation | -5.33e-03 |
Pos logit contributions | |
vern | +0.029 |
aches | +0.028 |
earned | +0.026 |
imes | +0.026 |
ending | +0.026 |
Neg logit contributions | |
boy | -0.028 |
girl | -0.027 |
Year | -0.023 |
extingu | -0.023 |
asleep | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
vern | +0.010 |
earned | +0.010 |
aches | +0.010 |
iable | +0.009 |
achieve | +0.009 |
Neg logit contributions | |
boy | -0.008 |
girl | -0.008 |
asleep | -0.008 |
t | -0.007 |
de | -0.007 |
Token | thought |
Token ID | 1807 |
Feature activation | -6.34e-03 |
Pos logit contributions | |
vern | +0.022 |
aches | +0.021 |
earned | +0.020 |
imes | +0.020 |
ending | +0.020 |
Neg logit contributions | |
boy | -0.019 |
girl | -0.018 |
Year | -0.016 |
extingu | -0.015 |
asleep | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -8.70e-03 |
Pos logit contributions | |
vern | +0.124 |
aches | +0.122 |
earned | +0.114 |
imes | +0.112 |
fters | +0.112 |
Neg logit contributions | |
boy | -0.120 |
girl | -0.114 |
extingu | -0.102 |
Year | -0.102 |
asleep | -0.099 |
Token | your |
Token ID | 534 |
Feature activation | +1.81e-04 |
Pos logit contributions | |
vern | +0.014 |
aches | +0.013 |
earned | +0.012 |
imes | +0.012 |
ending | +0.012 |
Neg logit contributions | |
boy | -0.016 |
girl | -0.016 |
Year | -0.014 |
extingu | -0.014 |
asleep | -0.014 |
Token | feet |
Token ID | 3625 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
boy | +0.000 |
extingu | +0.000 |
girl | +0.000 |
Year | +0.000 |
work | +0.000 |
Neg logit contributions | |
aches | -0.000 |
vern | -0.000 |
gh | -0.000 |
earned | -0.000 |
ough | -0.000 |
Token | with |
Token ID | 351 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
vern | +0.162 |
aches | +0.162 |
earned | +0.150 |
imes | +0.148 |
iable | +0.147 |
Neg logit contributions | |
boy | -0.149 |
girl | -0.141 |
Year | -0.128 |
extingu | -0.126 |
asleep | -0.119 |
Token | l |
Token ID | 300 |
Feature activation | +4.13e-03 |
Pos logit contributions | |
boy | +0.053 |
girl | +0.051 |
Year | +0.046 |
extingu | +0.046 |
asleep | +0.044 |
Neg logit contributions | |
vern | -0.048 |
aches | -0.048 |
earned | -0.045 |
imes | -0.044 |
ending | -0.043 |
Token | aces |
Token ID | 2114 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
boy | +0.010 |
girl | +0.009 |
asleep | +0.009 |
extingu | +0.009 |
Year | +0.009 |
Neg logit contributions | |
aches | -0.003 |
iable | -0.003 |
earned | -0.003 |
vern | -0.003 |
gh | -0.003 |
Token | ." |
Token ID | 526 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
aches | +0.304 |
vern | +0.303 |
earned | +0.286 |
imes | +0.282 |
fters | +0.282 |
Neg logit contributions | |
boy | -0.239 |
girl | -0.225 |
asleep | -0.199 |
extingu | -0.195 |
Year | -0.193 |
Token | Her |
Token ID | 2332 |
Feature activation | -1.66e-03 |
Pos logit contributions | |
boy | +0.041 |
girl | +0.039 |
extingu | +0.038 |
Year | +0.037 |
work | +0.036 |
Neg logit contributions | |
vern | -0.026 |
ons | -0.025 |
aches | -0.025 |
imes | -0.025 |
earned | -0.024 |
Token | son |
Token ID | 3367 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
gh | +0.002 |
vern | +0.002 |
hardly | +0.002 |
ittens | +0.002 |
odi | +0.002 |
Neg logit contributions | |
Year | -0.003 |
extingu | -0.003 |
ucks | -0.003 |
ksh | -0.003 |
hyd | -0.003 |
Token | nodded |
Token ID | 14464 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
boy | +0.025 |
girl | +0.025 |
Year | +0.024 |
extingu | +0.024 |
asleep | +0.023 |
Neg logit contributions | |
aches | -0.027 |
vern | -0.025 |
gh | -0.024 |
hardly | -0.024 |
ending | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -2.59e-03 |
Pos logit contributions | |
boy | +0.047 |
Year | +0.047 |
girl | +0.044 |
ksh | +0.043 |
tent | +0.042 |
Neg logit contributions | |
gh | -0.037 |
Her | -0.036 |
vern | -0.036 |
ag | -0.035 |
hardly | -0.033 |
Token | are |
Token ID | 389 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
vern | +0.013 |
aches | +0.012 |
earned | +0.012 |
imes | +0.011 |
fters | +0.011 |
Neg logit contributions | |
boy | -0.015 |
girl | -0.014 |
extingu | -0.012 |
Year | -0.012 |
asleep | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
boy | +0.074 |
girl | +0.070 |
Year | +0.065 |
extingu | +0.065 |
asleep | +0.060 |
Neg logit contributions | |
vern | -0.072 |
aches | -0.072 |
iable | -0.064 |
fters | -0.064 |
earned | -0.064 |
Token | good |
Token ID | 922 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
Year | +0.045 |
ksh | +0.044 |
boy | +0.044 |
extingu | +0.044 |
ucks | +0.043 |
Neg logit contributions | |
vern | -0.030 |
gh | -0.025 |
aches | -0.025 |
capable | -0.024 |
supposed | -0.024 |
Token | friend |
Token ID | 1545 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
vern | +0.049 |
ending | +0.046 |
aches | +0.046 |
ough | +0.046 |
ag | +0.045 |
Neg logit contributions | |
ksh | -0.045 |
Year | -0.043 |
fly | -0.039 |
work | -0.039 |
ASH | -0.038 |
Token | for |
Token ID | 329 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
vern | +0.028 |
aches | +0.027 |
earned | +0.026 |
imes | +0.025 |
ending | +0.025 |
Neg logit contributions | |
boy | -0.027 |
girl | -0.026 |
Year | -0.024 |
extingu | -0.024 |
asleep | -0.022 |
Token | whist |
Token ID | 32262 |
Feature activation | +8.29e-02 |
Pos logit contributions | |
aches | +0.019 |
vern | +0.018 |
fters | +0.017 |
iable | +0.017 |
gh | +0.017 |
Neg logit contributions | |
boy | -0.025 |
girl | -0.024 |
extingu | -0.023 |
Year | -0.022 |
cy | -0.021 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
boy | +0.127 |
girl | +0.119 |
Year | +0.106 |
extingu | +0.106 |
asleep | +0.100 |
Neg logit contributions | |
vern | -0.161 |
aches | -0.161 |
earned | -0.150 |
imes | -0.148 |
ending | -0.147 |
Token | ." |
Token ID | 526 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
boy | +0.029 |
girl | +0.028 |
Year | +0.027 |
extingu | +0.026 |
cottage | +0.025 |
Neg logit contributions | |
aches | -0.025 |
vern | -0.025 |
ag | -0.023 |
gh | -0.023 |
earned | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
boy | +0.032 |
girl | +0.031 |
Year | +0.028 |
extingu | +0.028 |
asleep | +0.026 |
Neg logit contributions | |
vern | -0.033 |
aches | -0.033 |
earned | -0.030 |
imes | -0.030 |
ending | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
aches | +0.042 |
vern | +0.042 |
earned | +0.040 |
iable | +0.039 |
fters | +0.039 |
Neg logit contributions | |
boy | -0.036 |
girl | -0.033 |
Year | -0.029 |
extingu | -0.029 |
asleep | -0.028 |
Token | They |
Token ID | 2990 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
vern | +0.027 |
aches | +0.027 |
imes | +0.026 |
fters | +0.025 |
earned | +0.025 |
Neg logit contributions | |
boy | -0.047 |
girl | -0.044 |
Year | -0.039 |
extingu | -0.039 |
duck | -0.037 |
Token | We |
Token ID | 775 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
boy | +0.031 |
girl | +0.031 |
asleep | +0.029 |
maid | +0.028 |
cottage | +0.027 |
Neg logit contributions | |
ough | -0.035 |
earned | -0.035 |
vern | -0.034 |
imes | -0.033 |
adders | -0.032 |
Token | want |
Token ID | 765 |
Feature activation | -4.50e-03 |
Pos logit contributions | |
boy | +0.046 |
girl | +0.044 |
Year | +0.041 |
extingu | +0.040 |
asleep | +0.039 |
Neg logit contributions | |
vern | -0.036 |
aches | -0.036 |
earned | -0.033 |
imes | -0.032 |
fters | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | -5.22e-04 |
Pos logit contributions | |
vern | +0.005 |
aches | +0.005 |
earned | +0.005 |
ons | +0.004 |
ag | +0.004 |
Neg logit contributions | |
boy | -0.010 |
girl | -0.010 |
extingu | -0.009 |
Year | -0.009 |
ksh | -0.009 |
Token | see |
Token ID | 766 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
aches | +0.001 |
vern | +0.001 |
earned | +0.001 |
gh | +0.001 |
fters | +0.001 |
Neg logit contributions | |
boy | -0.001 |
girl | -0.001 |
Year | -0.001 |
extingu | -0.001 |
asleep | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +6.58e-03 |
Pos logit contributions | |
aches | +0.045 |
vern | +0.044 |
iable | +0.041 |
ons | +0.041 |
ag | +0.039 |
Neg logit contributions | |
boy | -0.066 |
girl | -0.063 |
extingu | -0.061 |
ksh | -0.060 |
Year | -0.059 |
Token | movie |
Token ID | 3807 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
extingu | +0.011 |
ksh | +0.011 |
cy | +0.010 |
ucks | +0.010 |
ipt | +0.010 |
Neg logit contributions | |
aches | -0.011 |
vern | -0.010 |
fters | -0.010 |
achieve | -0.009 |
iable | -0.009 |
Token | ." |
Token ID | 526 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
extingu | +0.140 |
boy | +0.137 |
girl | +0.136 |
Year | +0.130 |
ksh | +0.125 |
Neg logit contributions | |
aches | -0.129 |
vern | -0.123 |
achieve | -0.122 |
iable | -0.117 |
accomplished | -0.117 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
boy | +0.045 |
girl | +0.044 |
extingu | +0.042 |
Year | +0.041 |
work | +0.040 |
Neg logit contributions | |
vern | -0.038 |
aches | -0.037 |
imes | -0.036 |
earned | -0.034 |
achieve | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
vern | +0.026 |
aches | +0.026 |
earned | +0.024 |
imes | +0.024 |
ending | +0.023 |
Neg logit contributions | |
boy | -0.025 |
girl | -0.023 |
Year | -0.021 |
extingu | -0.021 |
asleep | -0.020 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
vern | +0.016 |
aches | +0.015 |
achieve | +0.013 |
earned | +0.013 |
fters | +0.013 |
Neg logit contributions | |
boy | -0.027 |
girl | -0.026 |
extingu | -0.024 |
asleep | -0.024 |
Year | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
boy | +0.025 |
girl | +0.024 |
ksh | +0.023 |
Year | +0.023 |
hyd | +0.023 |
Neg logit contributions | |
ons | -0.026 |
aches | -0.025 |
vern | -0.025 |
old | -0.024 |
ag | -0.024 |
Token | " |
Token ID | 366 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
boy | +0.013 |
girl | +0.012 |
extingu | +0.012 |
Year | +0.012 |
cottage | +0.011 |
Neg logit contributions | |
aches | -0.013 |
vern | -0.013 |
achieve | -0.012 |
imes | -0.012 |
fters | -0.012 |
Token | dog |
Token ID | 9703 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
boy | +0.054 |
girl | +0.052 |
extingu | +0.049 |
Year | +0.048 |
asleep | +0.046 |
Neg logit contributions | |
aches | -0.042 |
vern | -0.041 |
earned | -0.039 |
imes | -0.038 |
ending | -0.038 |
Token | " |
Token ID | 1 |
Feature activation | -1.60e-03 |
Pos logit contributions | |
boy | +0.051 |
girl | +0.049 |
Year | +0.045 |
extingu | +0.045 |
asleep | +0.043 |
Neg logit contributions | |
aches | -0.038 |
vern | -0.038 |
earned | -0.035 |
imes | -0.034 |
ending | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | +5.65e-03 |
Pos logit contributions | |
aches | +0.003 |
vern | +0.003 |
imes | +0.003 |
iable | +0.003 |
earned | +0.003 |
Neg logit contributions | |
boy | -0.003 |
girl | -0.002 |
extingu | -0.002 |
Year | -0.002 |
asleep | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
boy | +0.009 |
girl | +0.009 |
extingu | +0.008 |
Year | +0.008 |
cottage | +0.008 |
Neg logit contributions | |
aches | -0.010 |
vern | -0.010 |
imes | -0.009 |
fters | -0.009 |
earned | -0.009 |
Token | star |
Token ID | 7364 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
boy | +0.052 |
girl | +0.049 |
extingu | +0.047 |
Year | +0.046 |
asleep | +0.045 |
Neg logit contributions | |
aches | -0.040 |
vern | -0.038 |
earned | -0.037 |
ough | -0.036 |
imes | -0.036 |
Token | " |
Token ID | 1 |
Feature activation | -3.36e-03 |
Pos logit contributions | |
boy | +0.146 |
girl | +0.140 |
extingu | +0.132 |
Year | +0.131 |
asleep | +0.129 |
Neg logit contributions | |
aches | -0.099 |
vern | -0.097 |
imes | -0.090 |
ough | -0.089 |
earned | -0.089 |
Token | and |
Token ID | 290 |
Feature activation | +2.55e-03 |
Pos logit contributions | |
aches | +0.006 |
vern | +0.006 |
imes | +0.006 |
iable | +0.006 |
earned | +0.005 |
Neg logit contributions | |
boy | -0.005 |
extingu | -0.005 |
Year | -0.005 |
girl | -0.005 |
cottage | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
boy | +0.005 |
girl | +0.004 |
extingu | +0.004 |
Year | +0.004 |
cottage | +0.004 |
Neg logit contributions | |
aches | -0.004 |
achieve | -0.004 |
fters | -0.004 |
vern | -0.004 |
ough | -0.004 |
Token | cake |
Token ID | 30560 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
boy | +0.049 |
girl | +0.046 |
extingu | +0.044 |
Year | +0.043 |
asleep | +0.042 |
Neg logit contributions | |
aches | -0.037 |
vern | -0.036 |
earned | -0.034 |
imes | -0.034 |
ending | -0.034 |
Token | ". |
Token ID | 1911 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
boy | +0.120 |
girl | +0.114 |
extingu | +0.106 |
Year | +0.106 |
asleep | +0.102 |
Neg logit contributions | |
aches | -0.102 |
vern | -0.099 |
imes | -0.091 |
earned | -0.091 |
iable | -0.091 |
Token | care |
Token ID | 1337 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
aches | +0.006 |
vern | +0.006 |
ons | +0.006 |
gh | +0.006 |
ag | +0.006 |
Neg logit contributions | |
boy | -0.009 |
extingu | -0.008 |
girl | -0.008 |
Year | -0.008 |
ksh | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
aches | +0.072 |
vern | +0.071 |
earned | +0.064 |
fters | +0.062 |
iable | +0.062 |
Neg logit contributions | |
boy | -0.156 |
girl | -0.150 |
extingu | -0.138 |
Year | -0.137 |
asleep | -0.135 |
Token | it |
Token ID | 340 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
boy | +0.057 |
girl | +0.054 |
extingu | +0.052 |
Year | +0.050 |
ksh | +0.049 |
Neg logit contributions | |
aches | -0.043 |
vern | -0.042 |
iable | -0.038 |
ons | -0.038 |
gh | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +4.35e-03 |
Pos logit contributions | |
aches | +0.027 |
vern | +0.026 |
iable | +0.024 |
ag | +0.024 |
gh | +0.024 |
Neg logit contributions | |
boy | -0.029 |
girl | -0.028 |
extingu | -0.026 |
Year | -0.026 |
cottage | -0.024 |
Token | Happy |
Token ID | 14628 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
boy | +0.008 |
girl | +0.007 |
extingu | +0.007 |
Year | +0.007 |
asleep | +0.007 |
Neg logit contributions | |
vern | -0.007 |
aches | -0.007 |
earned | -0.007 |
imes | -0.007 |
ough | -0.007 |
Token | birthday |
Token ID | 10955 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
extingu | +0.120 |
ksh | +0.114 |
boy | +0.108 |
grizz | +0.108 |
polar | +0.106 |
Neg logit contributions | |
aches | -0.095 |
gh | -0.089 |
achieve | -0.089 |
vern | -0.088 |
ough | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | -8.81e-03 |
Pos logit contributions | |
extingu | +0.155 |
boy | +0.149 |
ksh | +0.148 |
Year | +0.144 |
cottage | +0.142 |
Neg logit contributions | |
aches | -0.090 |
vern | -0.084 |
ons | -0.084 |
gh | -0.083 |
imes | -0.078 |
Token | sweet |
Token ID | 6029 |
Feature activation | -4.45e-03 |
Pos logit contributions | |
aches | +0.011 |
achieve | +0.011 |
vern | +0.010 |
hardly | +0.010 |
imes | +0.010 |
Neg logit contributions | |
extingu | -0.018 |
ksh | -0.017 |
ASH | -0.017 |
boy | -0.016 |
Year | -0.016 |
Token | ie |
Token ID | 494 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
aches | +0.005 |
ons | +0.005 |
ade | +0.005 |
affles | +0.004 |
isi | +0.004 |
Neg logit contributions | |
extingu | -0.010 |
ksh | -0.009 |
ASH | -0.009 |
ses | -0.009 |
hyd | -0.009 |
Token | ." |
Token ID | 526 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
aches | +0.026 |
ons | +0.023 |
vern | +0.023 |
accomplished | +0.023 |
achieve | +0.022 |
Neg logit contributions | |
extingu | -0.035 |
boy | -0.033 |
ksh | -0.033 |
girl | -0.031 |
Year | -0.031 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
extingu | +0.021 |
ksh | +0.020 |
boy | +0.020 |
Year | +0.020 |
girl | +0.019 |
Neg logit contributions | |
vern | -0.015 |
Her | -0.015 |
imes | -0.014 |
ons | -0.014 |
aches | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +5.92e-03 |
Pos logit contributions | |
boy | +0.048 |
girl | +0.045 |
Year | +0.043 |
extingu | +0.041 |
asleep | +0.040 |
Neg logit contributions | |
aches | -0.041 |
vern | -0.041 |
imes | -0.038 |
gh | -0.037 |
earned | -0.037 |
Token | John |
Token ID | 1757 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
boy | +0.012 |
girl | +0.011 |
extingu | +0.011 |
work | +0.011 |
Year | +0.010 |
Neg logit contributions | |
vern | -0.008 |
imes | -0.007 |
earned | -0.007 |
ough | -0.007 |
odi | -0.007 |
Token | said |
Token ID | 531 |
Feature activation | +6.26e-03 |
Pos logit contributions | |
boy | +0.033 |
extingu | +0.033 |
Year | +0.033 |
girl | +0.032 |
asleep | +0.030 |
Neg logit contributions | |
aches | -0.026 |
ending | -0.024 |
iable | -0.024 |
vern | -0.023 |
hardly | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -3.80e-03 |
Pos logit contributions | |
boy | +0.012 |
girl | +0.011 |
Year | +0.011 |
extingu | +0.010 |
asleep | +0.010 |
Neg logit contributions | |
vern | -0.010 |
aches | -0.010 |
gh | -0.009 |
earned | -0.009 |
imes | -0.009 |
Token | � |
Token ID | 6184 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
hardly | +0.005 |
vern | +0.005 |
gh | +0.005 |
ending | +0.004 |
aches | +0.004 |
Neg logit contributions | |
boy | -0.007 |
Year | -0.007 |
cy | -0.007 |
girl | -0.007 |
extingu | -0.007 |
Token | � |
Token ID | 95 |
Feature activation | +8.98e-02 |
Pos logit contributions | |
boy | +0.089 |
girl | +0.084 |
Year | +0.078 |
extingu | +0.077 |
asleep | +0.073 |
Neg logit contributions | |
aches | -0.077 |
vern | -0.077 |
earned | -0.071 |
imes | -0.070 |
fters | -0.069 |
Token | € |
Token ID | 26391 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
boy | +0.173 |
girl | +0.163 |
Year | +0.156 |
extingu | +0.151 |
ksh | +0.145 |
Neg logit contributions | |
aches | -0.141 |
vern | -0.136 |
imes | -0.128 |
ons | -0.121 |
earned | -0.121 |
Token | � |
Token ID | 129 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
vern | +0.033 |
aches | +0.033 |
earned | +0.030 |
imes | +0.030 |
fters | +0.030 |
Neg logit contributions | |
boy | -0.039 |
girl | -0.037 |
Year | -0.034 |
extingu | -0.034 |
asleep | -0.032 |
Token | � |
Token ID | 241 |
Feature activation | +2.14e-03 |
Pos logit contributions | |
boy | +0.068 |
Year | +0.065 |
girl | +0.063 |
ksh | +0.062 |
extingu | +0.059 |
Neg logit contributions | |
vern | -0.051 |
aches | -0.051 |
ons | -0.049 |
imes | -0.048 |
earned | -0.047 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
boy | +0.004 |
girl | +0.004 |
Year | +0.003 |
extingu | +0.003 |
asleep | +0.003 |
Neg logit contributions | |
vern | -0.003 |
aches | -0.003 |
earned | -0.003 |
ending | -0.003 |
gh | -0.003 |
Token | â |
Token ID | 22940 |
Feature activation | +6.97e-02 |
Pos logit contributions | |
boy | +0.029 |
girl | +0.027 |
Year | +0.024 |
extingu | +0.024 |
asleep | +0.022 |
Neg logit contributions | |
vern | -0.025 |
aches | -0.025 |
imes | -0.023 |
earned | -0.022 |
fters | -0.022 |
Token | appeared |
Token ID | 4120 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
boy | +0.069 |
girl | +0.067 |
ksh | +0.066 |
extingu | +0.065 |
Year | +0.065 |
Neg logit contributions | |
aches | -0.062 |
ons | -0.057 |
ending | -0.057 |
vern | -0.057 |
accomplished | -0.056 |
Token | near |
Token ID | 1474 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
boy | +0.048 |
girl | +0.044 |
Year | +0.043 |
extingu | +0.040 |
ksh | +0.039 |
Neg logit contributions | |
vern | -0.049 |
aches | -0.047 |
gh | -0.045 |
ending | -0.044 |
ag | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -3.31e-03 |
Pos logit contributions | |
aches | +0.023 |
vern | +0.023 |
ons | +0.022 |
imes | +0.021 |
gh | +0.021 |
Neg logit contributions | |
boy | -0.047 |
ksh | -0.045 |
girl | -0.045 |
Year | -0.043 |
extingu | -0.043 |
Token | island |
Token ID | 7022 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
accomplished | +0.004 |
amazing | +0.004 |
aches | +0.004 |
extraordinary | +0.004 |
belong | +0.004 |
Neg logit contributions | |
ksh | -0.006 |
ucks | -0.006 |
extingu | -0.006 |
asleep | -0.006 |
Lee | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e-03 |
Pos logit contributions | |
boy | +0.074 |
girl | +0.072 |
extingu | +0.071 |
ksh | +0.071 |
Year | +0.070 |
Neg logit contributions | |
aches | -0.062 |
vern | -0.057 |
achieve | -0.056 |
accomplished | -0.054 |
ons | -0.054 |
Token | Out |
Token ID | 3806 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
boy | +0.002 |
girl | +0.002 |
Year | +0.002 |
extingu | +0.002 |
maid | +0.002 |
Neg logit contributions | |
earned | -0.001 |
imes | -0.001 |
ough | -0.001 |
vern | -0.001 |
hardly | -0.001 |
Token | stepped |
Token ID | 10764 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
boy | +0.047 |
girl | +0.044 |
Year | +0.042 |
extingu | +0.041 |
ksh | +0.040 |
Neg logit contributions | |
vern | -0.028 |
aches | -0.028 |
ending | -0.026 |
ons | -0.026 |
earned | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
boy | +0.058 |
girl | +0.054 |
Year | +0.050 |
extingu | +0.047 |
ksh | +0.046 |
Neg logit contributions | |
vern | -0.055 |
imes | -0.053 |
aches | -0.053 |
ag | -0.051 |
ough | -0.050 |
Token | tall |
Token ID | 7331 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
ucks | +0.035 |
ASH | +0.034 |
ksh | +0.034 |
Year | +0.034 |
cy | +0.033 |
Neg logit contributions | |
vern | -0.024 |
aches | -0.023 |
achieve | -0.022 |
fters | -0.021 |
else | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -3.04e-03 |
Pos logit contributions | |
aches | +0.054 |
ons | +0.046 |
fters | +0.045 |
ade | +0.044 |
expect | +0.044 |
Neg logit contributions | |
ksh | -0.065 |
ucks | -0.060 |
Sn | -0.057 |
asleep | -0.056 |
ASH | -0.056 |
Token | wise |
Token ID | 10787 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
accomplished | +0.004 |
aches | +0.004 |
vern | +0.003 |
iable | +0.003 |
else | +0.003 |
Neg logit contributions | |
Year | -0.006 |
extingu | -0.006 |
ucks | -0.006 |
maid | -0.006 |
ASH | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
vern | +0.019 |
aches | +0.019 |
earned | +0.018 |
imes | +0.018 |
fters | +0.018 |
Neg logit contributions | |
boy | -0.019 |
girl | -0.018 |
Year | -0.016 |
extingu | -0.016 |
asleep | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
aches | +0.034 |
vern | +0.034 |
earned | +0.032 |
imes | +0.031 |
iable | +0.031 |
Neg logit contributions | |
boy | -0.032 |
girl | -0.030 |
Year | -0.027 |
extingu | -0.026 |
asleep | -0.025 |
Token | The |
Token ID | 464 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
aches | +0.018 |
vern | +0.018 |
earned | +0.016 |
imes | +0.016 |
ag | +0.016 |
Neg logit contributions | |
boy | -0.037 |
girl | -0.035 |
Year | -0.033 |
extingu | -0.031 |
asleep | -0.031 |
Token | little |
Token ID | 1310 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
ucks | +0.022 |
ksh | +0.022 |
extingu | +0.021 |
asleep | +0.020 |
ASH | +0.019 |
Neg logit contributions | |
Days | -0.016 |
aches | -0.016 |
vern | -0.015 |
isy | -0.014 |
Every | -0.014 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
ksh | +0.088 |
ucks | +0.079 |
extingu | +0.079 |
projector | +0.073 |
Claus | +0.073 |
Neg logit contributions | |
aches | -0.128 |
belong | -0.126 |
Every | -0.125 |
earned | -0.122 |
ade | -0.120 |
Token | was |
Token ID | 373 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
boy | +0.078 |
extingu | +0.076 |
girl | +0.075 |
Year | +0.071 |
ksh | +0.070 |
Neg logit contributions | |
aches | -0.067 |
vern | -0.063 |
ons | -0.062 |
hardly | -0.062 |
achieve | -0.062 |
Token | sad |
Token ID | 6507 |
Feature activation | +9.96e-03 |
Pos logit contributions | |
boy | +0.029 |
girl | +0.028 |
extingu | +0.028 |
Year | +0.027 |
ksh | +0.026 |
Neg logit contributions | |
aches | -0.018 |
vern | -0.017 |
hardly | -0.016 |
accomplished | -0.016 |
supposed | -0.016 |
Token | when |
Token ID | 618 |
Feature activation | +7.03e-03 |
Pos logit contributions | |
Year | +0.019 |
boy | +0.019 |
girl | +0.018 |
extingu | +0.018 |
ksh | +0.018 |
Neg logit contributions | |
vern | -0.013 |
aches | -0.013 |
ending | -0.012 |
achieve | -0.012 |
iable | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | +4.72e-03 |
Pos logit contributions | |
boy | +0.017 |
girl | +0.016 |
extingu | +0.016 |
Year | +0.015 |
ksh | +0.015 |
Neg logit contributions | |
aches | -0.007 |
vern | -0.007 |
earned | -0.006 |
gh | -0.006 |
imes | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
extingu | +0.008 |
boy | +0.008 |
girl | +0.008 |
Year | +0.008 |
ksh | +0.007 |
Neg logit contributions | |
aches | -0.007 |
accomplished | -0.007 |
gh | -0.007 |
achieved | -0.007 |
achieve | -0.007 |
Token | time |
Token ID | 640 |
Feature activation | +6.15e-03 |
Pos logit contributions | |
boy | +0.030 |
girl | +0.029 |
extingu | +0.027 |
Year | +0.027 |
ksh | +0.026 |
Neg logit contributions | |
aches | -0.014 |
vern | -0.013 |
ag | -0.012 |
gh | -0.012 |
accomplished | -0.012 |
Token | Then |
Token ID | 3244 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
vern | +0.024 |
aches | +0.023 |
earned | +0.022 |
imes | +0.022 |
ough | +0.022 |
Neg logit contributions | |
boy | -0.021 |
girl | -0.021 |
Year | -0.019 |
extingu | -0.018 |
asleep | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
vern | +0.065 |
aches | +0.063 |
fters | +0.059 |
earned | +0.059 |
imes | +0.059 |
Neg logit contributions | |
boy | -0.056 |
girl | -0.052 |
Year | -0.044 |
extingu | -0.044 |
duck | -0.042 |
Token | Tim |
Token ID | 5045 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
vern | +0.039 |
aches | +0.039 |
earned | +0.036 |
imes | +0.036 |
ending | +0.035 |
Neg logit contributions | |
boy | -0.038 |
girl | -0.036 |
Year | -0.032 |
extingu | -0.032 |
asleep | -0.030 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
aches | +0.075 |
vern | +0.074 |
earned | +0.069 |
iable | +0.068 |
gh | +0.068 |
Neg logit contributions | |
boy | -0.084 |
girl | -0.080 |
extingu | -0.077 |
Year | -0.076 |
asleep | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
vern | +0.030 |
aches | +0.029 |
earned | +0.028 |
fters | +0.027 |
ending | +0.027 |
Neg logit contributions | |
boy | -0.029 |
girl | -0.027 |
extingu | -0.025 |
Year | -0.024 |
asleep | -0.023 |
Token | man |
Token ID | 582 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
Year | +0.021 |
ksh | +0.021 |
work | +0.020 |
ucks | +0.020 |
ASH | +0.019 |
Neg logit contributions | |
vern | -0.015 |
aches | -0.013 |
ade | -0.013 |
gh | -0.013 |
achieve | -0.013 |
Token | with |
Token ID | 351 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
boy | +0.089 |
girl | +0.086 |
ksh | +0.085 |
Year | +0.082 |
extingu | +0.079 |
Neg logit contributions | |
aches | -0.079 |
ag | -0.079 |
ons | -0.078 |
vern | -0.077 |
achieve | -0.077 |
Token | a |
Token ID | 257 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
boy | +0.036 |
girl | +0.034 |
Year | +0.032 |
extingu | +0.031 |
ksh | +0.029 |
Neg logit contributions | |
vern | -0.041 |
aches | -0.040 |
earned | -0.038 |
gh | -0.037 |
imes | -0.037 |
Token | club |
Token ID | 3430 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
Year | +0.019 |
boy | +0.018 |
ksh | +0.018 |
girl | +0.018 |
extingu | +0.017 |
Neg logit contributions | |
vern | -0.018 |
aches | -0.017 |
gh | -0.016 |
earned | -0.015 |
iable | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
vern | +0.024 |
aches | +0.023 |
earned | +0.022 |
ag | +0.022 |
gh | +0.021 |
Neg logit contributions | |
boy | -0.024 |
girl | -0.023 |
Year | -0.022 |
extingu | -0.021 |
ksh | -0.021 |
Token | He |
Token ID | 679 |
Feature activation | -4.44e-03 |
Pos logit contributions | |
vern | +0.019 |
aches | +0.019 |
earned | +0.018 |
imes | +0.018 |
ending | +0.017 |
Neg logit contributions | |
boy | -0.021 |
girl | -0.020 |
Year | -0.018 |
extingu | -0.018 |
asleep | -0.017 |
Token | To |
Token ID | 1675 |
Feature activation | +5.44e-03 |
Pos logit contributions | |
vern | +0.012 |
aches | +0.012 |
earned | +0.011 |
imes | +0.011 |
ending | +0.011 |
Neg logit contributions | |
boy | -0.016 |
girl | -0.015 |
extingu | -0.014 |
Year | -0.014 |
asleep | -0.013 |
Token | her |
Token ID | 607 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
boy | +0.009 |
girl | +0.009 |
t | +0.008 |
extingu | +0.008 |
Year | +0.007 |
Neg logit contributions | |
vern | -0.010 |
ending | -0.010 |
earned | -0.009 |
imes | -0.009 |
affles | -0.009 |
Token | surprise |
Token ID | 5975 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
vern | +0.044 |
aches | +0.044 |
earned | +0.042 |
ending | +0.041 |
gh | +0.041 |
Neg logit contributions | |
boy | -0.032 |
girl | -0.030 |
Year | -0.027 |
extingu | -0.027 |
asleep | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
boy | +0.053 |
girl | +0.050 |
Year | +0.040 |
asleep | +0.039 |
tent | +0.039 |
Neg logit contributions | |
vern | -0.070 |
aches | -0.068 |
earned | -0.067 |
ending | -0.065 |
fters | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
aches | +0.022 |
vern | +0.020 |
ons | +0.019 |
imes | +0.018 |
earned | +0.018 |
Neg logit contributions | |
boy | -0.041 |
extingu | -0.041 |
Year | -0.041 |
ksh | -0.040 |
girl | -0.039 |
Token | chest |
Token ID | 7721 |
Feature activation | +2.40e-03 |
Pos logit contributions | |
vern | +0.020 |
accomplished | +0.019 |
earned | +0.019 |
aches | +0.019 |
expect | +0.019 |
Neg logit contributions | |
extingu | -0.015 |
ksh | -0.014 |
Year | -0.014 |
work | -0.014 |
cy | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | -5.45e-03 |
Pos logit contributions | |
boy | +0.004 |
Year | +0.004 |
extingu | +0.004 |
girl | +0.004 |
ksh | +0.004 |
Neg logit contributions | |
aches | -0.004 |
vern | -0.004 |
gh | -0.004 |
ons | -0.004 |
accomplished | -0.004 |
Token | not |
Token ID | 407 |
Feature activation | -8.73e-03 |
Pos logit contributions | |
vern | +0.010 |
aches | +0.010 |
earned | +0.010 |
ending | +0.010 |
imes | +0.010 |
Neg logit contributions | |
boy | -0.009 |
girl | -0.008 |
extingu | -0.007 |
asleep | -0.007 |
Year | -0.007 |
Token | empty |
Token ID | 6565 |
Feature activation | -4.08e-03 |
Pos logit contributions | |
vern | +0.015 |
aches | +0.015 |
earned | +0.014 |
imes | +0.014 |
iable | +0.014 |
Neg logit contributions | |
boy | -0.015 |
girl | -0.014 |
Year | -0.013 |
extingu | -0.013 |
asleep | -0.012 |
Token | ! |
Token ID | 0 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
vern | +0.006 |
aches | +0.006 |
gh | +0.005 |
earned | +0.005 |
imes | +0.005 |
Neg logit contributions | |
boy | -0.008 |
girl | -0.008 |
Year | -0.007 |
extingu | -0.007 |
ksh | -0.007 |
Token | Inside |
Token ID | 14384 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
vern | +0.048 |
aches | +0.048 |
earned | +0.044 |
fters | +0.043 |
iable | +0.043 |
Neg logit contributions | |
boy | -0.050 |
girl | -0.048 |
Year | -0.043 |
extingu | -0.042 |
asleep | -0.041 |
Token | hug |
Token ID | 16225 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
vern | +0.003 |
aches | +0.002 |
ade | +0.002 |
gh | +0.002 |
ag | +0.002 |
Neg logit contributions | |
ksh | -0.003 |
Year | -0.003 |
boy | -0.003 |
extingu | -0.003 |
ucks | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e-03 |
Pos logit contributions | |
boy | +0.036 |
Year | +0.035 |
girl | +0.034 |
extingu | +0.033 |
ksh | +0.031 |
Neg logit contributions | |
vern | -0.030 |
aches | -0.030 |
gh | -0.029 |
earned | -0.029 |
ending | -0.028 |
Token | She |
Token ID | 1375 |
Feature activation | -5.18e-03 |
Pos logit contributions | |
vern | +0.002 |
aches | +0.002 |
imes | +0.002 |
ough | +0.002 |
earned | +0.002 |
Neg logit contributions | |
boy | -0.003 |
girl | -0.003 |
extingu | -0.003 |
Year | -0.002 |
work | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | +2.22e-03 |
Pos logit contributions | |
aches | +0.008 |
vern | +0.007 |
hardly | +0.007 |
accomplished | +0.007 |
ons | +0.007 |
Neg logit contributions | |
boy | -0.010 |
girl | -0.009 |
extingu | -0.009 |
Year | -0.009 |
ksh | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
boy | +0.004 |
girl | +0.004 |
extingu | +0.004 |
Year | +0.004 |
ksh | +0.004 |
Neg logit contributions | |
vern | -0.003 |
aches | -0.003 |
gh | -0.003 |
imes | -0.003 |
ending | -0.003 |
Token | Thank |
Token ID | 10449 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
boy | +0.060 |
girl | +0.056 |
extingu | +0.055 |
tent | +0.054 |
Year | +0.054 |
Neg logit contributions | |
aches | -0.042 |
earned | -0.042 |
vern | -0.042 |
ending | -0.042 |
iable | -0.041 |
Token | you |
Token ID | 345 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
boy | +0.082 |
girl | +0.078 |
extingu | +0.074 |
Year | +0.072 |
asleep | +0.071 |
Neg logit contributions | |
vern | -0.046 |
aches | -0.045 |
earned | -0.041 |
imes | -0.040 |
gh | -0.040 |
Token | for |
Token ID | 329 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
vern | +0.016 |
aches | +0.015 |
gh | +0.015 |
iable | +0.014 |
imes | +0.014 |
Neg logit contributions | |
boy | -0.020 |
girl | -0.019 |
extingu | -0.019 |
Year | -0.018 |
cy | -0.017 |
Token | being |
Token ID | 852 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
aches | +0.021 |
vern | +0.021 |
gh | +0.019 |
fters | +0.019 |
iable | +0.019 |
Neg logit contributions | |
boy | -0.030 |
girl | -0.028 |
extingu | -0.026 |
Year | -0.026 |
ksh | -0.025 |
Token | so |
Token ID | 523 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
boy | +0.020 |
girl | +0.019 |
Year | +0.018 |
extingu | +0.018 |
asleep | +0.017 |
Neg logit contributions | |
vern | -0.017 |
aches | -0.016 |
earned | -0.015 |
imes | -0.015 |
iable | -0.015 |
Token | fair |
Token ID | 3148 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
vern | +0.037 |
aches | +0.036 |
earned | +0.033 |
ending | +0.033 |
imes | +0.032 |
Neg logit contributions | |
boy | -0.050 |
girl | -0.047 |
Year | -0.044 |
extingu | -0.044 |
asleep | -0.042 |
Token | chase |
Token ID | 15505 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
extingu | +0.007 |
boy | +0.007 |
Year | +0.007 |
girl | +0.007 |
ksh | +0.007 |
Neg logit contributions | |
aches | -0.006 |
imes | -0.005 |
ons | -0.005 |
vern | -0.005 |
earned | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
aches | +0.085 |
vern | +0.082 |
imes | +0.079 |
earned | +0.078 |
ag | +0.078 |
Neg logit contributions | |
boy | -0.082 |
girl | -0.078 |
Year | -0.074 |
extingu | -0.073 |
asleep | -0.069 |
Token | butterflies |
Token ID | 44571 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
aches | +0.035 |
vern | +0.032 |
ade | +0.032 |
imes | +0.031 |
ons | +0.031 |
Neg logit contributions | |
Year | -0.031 |
ksh | -0.030 |
ucks | -0.030 |
extingu | -0.029 |
cy | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -7.88e-03 |
Pos logit contributions | |
aches | +0.120 |
vern | +0.119 |
ag | +0.109 |
imes | +0.108 |
earned | +0.108 |
Neg logit contributions | |
boy | -0.131 |
girl | -0.124 |
Year | -0.116 |
extingu | -0.115 |
ksh | -0.105 |
Token |
|
Token ID | 198 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
imes | +0.011 |
vern | +0.011 |
aches | +0.011 |
ough | +0.011 |
earned | +0.011 |
Neg logit contributions | |
boy | -0.014 |
girl | -0.014 |
extingu | -0.014 |
Year | -0.013 |
work | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
aches | +0.045 |
vern | +0.044 |
earned | +0.042 |
iable | +0.042 |
ending | +0.042 |
Neg logit contributions | |
boy | -0.037 |
girl | -0.034 |
Year | -0.030 |
extingu | -0.029 |
asleep | -0.028 |
Token | " |
Token ID | 1 |
Feature activation | +4.07e-04 |
Pos logit contributions | |
aches | +0.025 |
vern | +0.025 |
earned | +0.023 |
imes | +0.022 |
ending | +0.022 |
Neg logit contributions | |
boy | -0.036 |
girl | -0.035 |
Year | -0.032 |
extingu | -0.031 |
asleep | -0.029 |
Token | Look |
Token ID | 8567 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
boy | +0.001 |
asleep | +0.001 |
girl | +0.001 |
extingu | +0.001 |
cottage | +0.001 |
Neg logit contributions | |
aches | -0.001 |
Days | -0.001 |
fters | -0.001 |
vern | -0.001 |
iable | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +3.70e-04 |
Pos logit contributions | |
boy | +0.053 |
girl | +0.051 |
Year | +0.047 |
extingu | +0.046 |
asleep | +0.044 |
Neg logit contributions | |
aches | -0.047 |
vern | -0.047 |
imes | -0.043 |
iable | -0.043 |
earned | -0.043 |
Token | Ben |
Token ID | 3932 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
ksh | +0.001 |
Year | +0.001 |
extingu | +0.001 |
ucks | +0.001 |
boy | +0.001 |
Neg logit contributions | |
aches | -0.001 |
imes | -0.001 |
vern | -0.001 |
iable | -0.001 |
expect | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +2.37e-03 |
Pos logit contributions | |
aches | +0.032 |
gh | +0.031 |
vern | +0.031 |
ons | +0.029 |
done | +0.028 |
Neg logit contributions | |
Year | -0.071 |
ksh | -0.071 |
extingu | -0.069 |
boy | -0.069 |
asleep | -0.069 |
Token | flew |
Token ID | 13112 |
Feature activation | +1.29e-03 |
Pos logit contributions | |
vern | +0.047 |
aches | +0.046 |
earned | +0.043 |
imes | +0.043 |
fters | +0.042 |
Neg logit contributions | |
boy | -0.046 |
girl | -0.043 |
Year | -0.038 |
extingu | -0.038 |
asleep | -0.037 |
Token | away |
Token ID | 1497 |
Feature activation | -7.53e-03 |
Pos logit contributions | |
boy | +0.002 |
girl | +0.002 |
Year | +0.002 |
extingu | +0.002 |
cottage | +0.002 |
Neg logit contributions | |
aches | -0.002 |
ag | -0.002 |
vern | -0.002 |
gh | -0.002 |
iable | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
vern | +0.009 |
aches | +0.008 |
accomplished | +0.008 |
gh | +0.007 |
achieve | +0.007 |
Neg logit contributions | |
boy | -0.017 |
Year | -0.016 |
girl | -0.016 |
ksh | -0.015 |
extingu | -0.014 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
vern | +0.017 |
imes | +0.017 |
aches | +0.017 |
earned | +0.016 |
ough | +0.016 |
Neg logit contributions | |
boy | -0.016 |
extingu | -0.015 |
girl | -0.015 |
Year | -0.015 |
work | -0.014 |
Token | felt |
Token ID | 2936 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
aches | +0.045 |
vern | +0.045 |
earned | +0.042 |
ending | +0.041 |
imes | +0.041 |
Neg logit contributions | |
boy | -0.039 |
girl | -0.037 |
extingu | -0.034 |
Year | -0.034 |
asleep | -0.032 |
Token | very |
Token ID | 845 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
aches | +0.098 |
vern | +0.097 |
earned | +0.096 |
ending | +0.095 |
gh | +0.094 |
Neg logit contributions | |
boy | -0.059 |
girl | -0.055 |
asleep | -0.046 |
duck | -0.043 |
t | -0.042 |
Token | sad |
Token ID | 6507 |
Feature activation | -6.42e-03 |
Pos logit contributions | |
vern | +0.070 |
aches | +0.069 |
earned | +0.068 |
iable | +0.066 |
ons | +0.066 |
Neg logit contributions | |
boy | -0.044 |
girl | -0.041 |
duck | -0.032 |
asleep | -0.032 |
hyd | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
vern | +0.012 |
aches | +0.011 |
ending | +0.011 |
earned | +0.011 |
imes | +0.011 |
Neg logit contributions | |
boy | -0.010 |
girl | -0.009 |
Year | -0.009 |
extingu | -0.009 |
ksh | -0.008 |
Token | scared |
Token ID | 12008 |
Feature activation | -7.42e-03 |
Pos logit contributions | |
vern | +0.019 |
aches | +0.019 |
earned | +0.017 |
imes | +0.017 |
ending | +0.017 |
Neg logit contributions | |
boy | -0.019 |
girl | -0.018 |
Year | -0.016 |
extingu | -0.016 |
asleep | -0.016 |
Token | because |
Token ID | 780 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
vern | +0.014 |
aches | +0.013 |
earned | +0.012 |
fters | +0.012 |
imes | +0.012 |
Neg logit contributions | |
boy | -0.013 |
girl | -0.012 |
extingu | -0.010 |
Year | -0.010 |
asleep | -0.010 |
Token | she |
Token ID | 673 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
vern | +0.046 |
aches | +0.045 |
earned | +0.041 |
ag | +0.040 |
imes | +0.040 |
Neg logit contributions | |
boy | -0.076 |
girl | -0.073 |
Year | -0.065 |
asleep | -0.064 |
extingu | -0.063 |
Token | ! |
Token ID | 0 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
vern | +0.018 |
aches | +0.018 |
earned | +0.016 |
imes | +0.016 |
fters | +0.016 |
Neg logit contributions | |
boy | -0.017 |
girl | -0.016 |
extingu | -0.015 |
Year | -0.014 |
asleep | -0.014 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
vern | +0.037 |
aches | +0.035 |
earned | +0.034 |
imes | +0.033 |
ending | +0.033 |
Neg logit contributions | |
boy | -0.047 |
girl | -0.045 |
Year | -0.041 |
extingu | -0.041 |
asleep | -0.039 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
boy | +0.075 |
girl | +0.073 |
extingu | +0.070 |
Year | +0.068 |
work | +0.064 |
Neg logit contributions | |
vern | -0.075 |
aches | -0.073 |
imes | -0.072 |
ons | -0.071 |
gh | -0.070 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
boy | +0.022 |
girl | +0.019 |
asleep | +0.014 |
cy | +0.013 |
tent | +0.012 |
Neg logit contributions | |
aches | -0.055 |
vern | -0.055 |
earned | -0.055 |
fters | -0.054 |
ough | -0.054 |
Token | a |
Token ID | 257 |
Feature activation | -4.26e-03 |
Pos logit contributions | |
boy | +0.028 |
girl | +0.027 |
Year | +0.025 |
extingu | +0.025 |
asleep | +0.023 |
Neg logit contributions | |
vern | -0.034 |
aches | -0.034 |
earned | -0.032 |
gh | -0.031 |
ag | -0.031 |
Token | time |
Token ID | 640 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
aches | +0.005 |
vern | +0.005 |
earned | +0.005 |
imes | +0.004 |
fters | +0.004 |
Neg logit contributions | |
boy | -0.010 |
girl | -0.009 |
Year | -0.009 |
extingu | -0.009 |
asleep | -0.008 |
Token | there |
Token ID | 612 |
Feature activation | -6.18e-03 |
Pos logit contributions | |
vern | +0.026 |
aches | +0.025 |
gh | +0.024 |
imes | +0.024 |
earned | +0.023 |
Neg logit contributions | |
boy | -0.032 |
girl | -0.030 |
Year | -0.028 |
extingu | -0.028 |
asleep | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
aches | +0.012 |
vern | +0.012 |
earned | +0.012 |
gh | +0.012 |
imes | +0.011 |
Neg logit contributions | |
boy | -0.009 |
girl | -0.008 |
Year | -0.007 |
extingu | -0.007 |
asleep | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -3.19e-03 |
Pos logit contributions | |
vern | +0.032 |
aches | +0.032 |
imes | +0.030 |
earned | +0.030 |
ough | +0.029 |
Neg logit contributions | |
boy | -0.029 |
girl | -0.027 |
extingu | -0.025 |
Year | -0.025 |
asleep | -0.023 |
Token | little |
Token ID | 1310 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
vern | +0.005 |
aches | +0.005 |
Days | +0.005 |
daring | +0.004 |
ittens | +0.004 |
Neg logit contributions | |
ASH | -0.005 |
extingu | -0.005 |
work | -0.005 |
asleep | -0.005 |
ksh | -0.005 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
ASH | +0.045 |
ksh | +0.042 |
Year | +0.042 |
asleep | +0.036 |
ucks | +0.036 |
Neg logit contributions | |
ittens | -0.082 |
exercise | -0.082 |
ade | -0.082 |
imes | -0.080 |
ons | -0.078 |
Token | the |
Token ID | 262 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
aches | +0.053 |
vern | +0.051 |
imes | +0.049 |
ons | +0.048 |
ag | +0.048 |
Neg logit contributions | |
boy | -0.073 |
girl | -0.070 |
Year | -0.068 |
extingu | -0.067 |
ksh | -0.066 |
Token | floor |
Token ID | 4314 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
aches | +0.035 |
ade | +0.033 |
ons | +0.032 |
vern | +0.032 |
achieve | +0.031 |
Neg logit contributions | |
extingu | -0.032 |
ksh | -0.031 |
boy | -0.031 |
Year | -0.030 |
ucks | -0.030 |
Token | ! |
Token ID | 0 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
vern | +0.063 |
aches | +0.062 |
gh | +0.057 |
ough | +0.057 |
ag | +0.056 |
Neg logit contributions | |
boy | -0.071 |
girl | -0.068 |
Year | -0.065 |
extingu | -0.062 |
ksh | -0.059 |
Token | Tim |
Token ID | 5045 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
vern | +0.049 |
imes | +0.049 |
aches | +0.048 |
earned | +0.047 |
ough | +0.047 |
Neg logit contributions | |
boy | -0.073 |
girl | -0.071 |
extingu | -0.067 |
Year | -0.066 |
work | -0.063 |
Token | my |
Token ID | 1820 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
aches | +0.091 |
vern | +0.090 |
earned | +0.084 |
ending | +0.083 |
iable | +0.083 |
Neg logit contributions | |
boy | -0.080 |
girl | -0.075 |
extingu | -0.069 |
Year | -0.069 |
asleep | -0.065 |
Token | 's |
Token ID | 338 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
aches | +0.024 |
vern | +0.023 |
ons | +0.022 |
earned | +0.022 |
ending | +0.022 |
Neg logit contributions | |
boy | -0.024 |
girl | -0.023 |
extingu | -0.023 |
Year | -0.022 |
asleep | -0.021 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
aches | +0.038 |
vern | +0.035 |
imes | +0.034 |
gh | +0.034 |
earned | +0.034 |
Neg logit contributions | |
extingu | -0.032 |
Year | -0.031 |
ksh | -0.031 |
boy | -0.031 |
girl | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | -6.26e-03 |
Pos logit contributions | |
boy | +0.027 |
girl | +0.026 |
Year | +0.025 |
extingu | +0.025 |
asleep | +0.023 |
Neg logit contributions | |
aches | -0.025 |
ons | -0.024 |
iable | -0.023 |
ending | -0.023 |
vern | -0.023 |
Token | not |
Token ID | 407 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
aches | +0.009 |
vern | +0.009 |
fters | +0.008 |
supposed | +0.008 |
achieve | +0.008 |
Neg logit contributions | |
boy | -0.013 |
girl | -0.012 |
extingu | -0.012 |
Year | -0.012 |
ksh | -0.011 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
aches | +0.023 |
vern | +0.023 |
iable | +0.021 |
supposed | +0.021 |
ag | +0.020 |
Neg logit contributions | |
boy | -0.028 |
girl | -0.026 |
Year | -0.026 |
extingu | -0.025 |
work | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
vern | +0.038 |
aches | +0.038 |
earned | +0.035 |
imes | +0.034 |
fters | +0.034 |
Neg logit contributions | |
boy | -0.044 |
girl | -0.042 |
Year | -0.038 |
extingu | -0.038 |
asleep | -0.036 |
Token | believe |
Token ID | 1975 |
Feature activation | -1.22e-03 |
Pos logit contributions | |
boy | +0.018 |
girl | +0.017 |
extingu | +0.016 |
Year | +0.016 |
asleep | +0.015 |
Neg logit contributions | |
vern | -0.009 |
aches | -0.008 |
imes | -0.008 |
earned | -0.008 |
ending | -0.007 |
Token | his |
Token ID | 465 |
Feature activation | -8.67e-03 |
Pos logit contributions | |
vern | +0.002 |
aches | +0.002 |
earned | +0.002 |
imes | +0.002 |
ending | +0.002 |
Neg logit contributions | |
boy | -0.002 |
girl | -0.002 |
Year | -0.002 |
extingu | -0.002 |
asleep | -0.002 |
Token | eyes |
Token ID | 2951 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
vern | +0.018 |
aches | +0.016 |
gh | +0.015 |
ag | +0.015 |
ending | +0.015 |
Neg logit contributions | |
boy | -0.013 |
girl | -0.012 |
Year | -0.012 |
ksh | -0.011 |
cy | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +5.81e-03 |
Pos logit contributions | |
aches | +0.082 |
vern | +0.081 |
earned | +0.074 |
iable | +0.074 |
gh | +0.074 |
Neg logit contributions | |
boy | -0.100 |
girl | -0.095 |
Year | -0.088 |
extingu | -0.086 |
asleep | -0.080 |
Token | |
Token ID | 220 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
boy | +0.011 |
girl | +0.011 |
extingu | +0.011 |
Year | +0.011 |
work | +0.010 |
Neg logit contributions | |
vern | -0.008 |
imes | -0.007 |
aches | -0.007 |
earned | -0.007 |
ough | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
aches | +0.024 |
vern | +0.024 |
earned | +0.023 |
fters | +0.022 |
gh | +0.022 |
Neg logit contributions | |
boy | -0.022 |
girl | -0.020 |
Year | -0.018 |
extingu | -0.018 |
asleep | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
aches | +0.042 |
vern | +0.040 |
earned | +0.039 |
imes | +0.039 |
iable | +0.038 |
Neg logit contributions | |
boy | -0.029 |
girl | -0.026 |
Year | -0.023 |
extingu | -0.020 |
asleep | -0.020 |
Token | The |
Token ID | 464 |
Feature activation | +6.23e-03 |
Pos logit contributions | |
aches | +0.026 |
vern | +0.024 |
imes | +0.023 |
ag | +0.022 |
earned | +0.022 |
Neg logit contributions | |
boy | -0.036 |
girl | -0.034 |
Year | -0.030 |
extingu | -0.028 |
cottage | -0.028 |
Token | man |
Token ID | 582 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
asleep | +0.010 |
ucks | +0.010 |
ksh | +0.010 |
cy | +0.010 |
extingu | +0.009 |
Neg logit contributions | |
vern | -0.009 |
aches | -0.009 |
Days | -0.009 |
ade | -0.009 |
gh | -0.009 |
Token | smiled |
Token ID | 13541 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
ksh | +0.128 |
extingu | +0.127 |
boy | +0.125 |
asleep | +0.124 |
girl | +0.124 |
Neg logit contributions | |
aches | -0.095 |
ons | -0.090 |
else | -0.084 |
ending | -0.083 |
accomplished | -0.083 |
Token | and |
Token ID | 290 |
Feature activation | +2.05e-03 |
Pos logit contributions | |
Year | +0.104 |
boy | +0.090 |
ASH | +0.090 |
extingu | +0.087 |
pret | +0.085 |
Neg logit contributions | |
vern | -0.057 |
ag | -0.054 |
Her | -0.053 |
; | -0.052 |
ending | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
aches | +0.018 |
ons | +0.016 |
imes | +0.016 |
vern | +0.016 |
ade | +0.015 |
Neg logit contributions | |
boy | -0.019 |
extingu | -0.019 |
girl | -0.018 |
Year | -0.018 |
ksh | -0.017 |
Token | put |
Token ID | 1234 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
aches | +0.024 |
ons | +0.020 |
imes | +0.019 |
achieve | +0.019 |
hardly | +0.019 |
Neg logit contributions | |
boy | -0.027 |
extingu | -0.027 |
Year | -0.026 |
girl | -0.025 |
ksh | -0.025 |
Token | it |
Token ID | 340 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
aches | +0.026 |
ons | +0.024 |
imes | +0.023 |
ag | +0.021 |
ade | +0.020 |
Neg logit contributions | |
boy | -0.040 |
extingu | -0.038 |
Year | -0.037 |
girl | -0.037 |
ksh | -0.036 |
Token | in |
Token ID | 287 |
Feature activation | -4.73e-03 |
Pos logit contributions | |
aches | +0.058 |
vern | +0.054 |
ag | +0.052 |
gh | +0.050 |
imes | +0.049 |
Neg logit contributions | |
boy | -0.055 |
girl | -0.051 |
Year | -0.049 |
extingu | -0.049 |
ksh | -0.045 |
Token | her |
Token ID | 607 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
aches | +0.006 |
vern | +0.006 |
gh | +0.005 |
ons | +0.005 |
imes | +0.005 |
Neg logit contributions | |
boy | -0.010 |
girl | -0.010 |
ksh | -0.009 |
Year | -0.009 |
extingu | -0.009 |
Token | mouth |
Token ID | 5422 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
aches | +0.069 |
vern | +0.066 |
earned | +0.064 |
ons | +0.062 |
imes | +0.061 |
Neg logit contributions | |
boy | -0.055 |
extingu | -0.050 |
girl | -0.050 |
ksh | -0.049 |
Year | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e-03 |
Pos logit contributions | |
aches | +0.162 |
vern | +0.161 |
earned | +0.149 |
imes | +0.147 |
ough | +0.145 |
Neg logit contributions | |
boy | -0.181 |
girl | -0.172 |
Year | -0.160 |
extingu | -0.156 |
asleep | -0.145 |
Token |
|
Token ID | 198 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
vern | +0.001 |
imes | +0.001 |
aches | +0.001 |
earned | +0.001 |
ough | +0.001 |
Neg logit contributions | |
boy | -0.002 |
girl | -0.002 |
extingu | -0.002 |
Year | -0.002 |
work | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
aches | +0.036 |
vern | +0.036 |
earned | +0.034 |
iable | +0.034 |
ending | +0.033 |
Neg logit contributions | |
boy | -0.031 |
girl | -0.029 |
Year | -0.025 |
extingu | -0.024 |
asleep | -0.024 |
Token | The |
Token ID | 464 |
Feature activation | +1.47e-03 |
Pos logit contributions | |
vern | +0.020 |
aches | +0.020 |
earned | +0.018 |
imes | +0.018 |
gh | +0.017 |
Neg logit contributions | |
boy | -0.030 |
girl | -0.029 |
Year | -0.026 |
extingu | -0.026 |
asleep | -0.025 |
Token | flower |
Token ID | 15061 |
Feature activation | +7.56e-03 |
Pos logit contributions | |
ksh | +0.002 |
extingu | +0.002 |
ucks | +0.002 |
ASH | +0.002 |
Year | +0.002 |
Neg logit contributions | |
aches | -0.003 |
imes | -0.002 |
vern | -0.002 |
ade | -0.002 |
fters | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
boy | +0.090 |
girl | +0.085 |
Year | +0.084 |
extingu | +0.080 |
work | +0.074 |
Neg logit contributions | |
vern | -0.089 |
aches | -0.087 |
ending | -0.081 |
gh | -0.080 |
earned | -0.080 |
Token | |
Token ID | 220 |
Feature activation | -9.34e-03 |
Pos logit contributions | |
boy | +0.031 |
girl | +0.029 |
Year | +0.027 |
extingu | +0.027 |
asleep | +0.025 |
Neg logit contributions | |
vern | -0.025 |
aches | -0.025 |
earned | -0.023 |
imes | -0.023 |
ending | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
aches | +0.019 |
vern | +0.018 |
earned | +0.018 |
fters | +0.017 |
gh | +0.017 |
Neg logit contributions | |
boy | -0.013 |
girl | -0.012 |
extingu | -0.011 |
asleep | -0.011 |
Year | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
aches | +0.033 |
vern | +0.032 |
earned | +0.031 |
iable | +0.031 |
ag | +0.031 |
Neg logit contributions | |
boy | -0.018 |
girl | -0.016 |
duck | -0.013 |
Sn | -0.013 |
extingu | -0.013 |
Token | M |
Token ID | 44 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
aches | +0.019 |
vern | +0.019 |
ag | +0.019 |
supposed | +0.018 |
earned | +0.018 |
Neg logit contributions | |
boy | -0.026 |
girl | -0.025 |
duck | -0.023 |
Sn | -0.022 |
Year | -0.022 |
Token | ittens |
Token ID | 34978 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
boy | +0.084 |
girl | +0.081 |
Year | +0.075 |
extingu | +0.074 |
duck | +0.072 |
Neg logit contributions | |
aches | -0.024 |
vern | -0.024 |
earned | -0.020 |
iable | -0.020 |
imes | -0.020 |
Token | went |
Token ID | 1816 |
Feature activation | -3.22e-03 |
Pos logit contributions | |
aches | +0.199 |
vern | +0.178 |
ons | +0.174 |
achieve | +0.172 |
iable | +0.171 |
Neg logit contributions | |
extingu | -0.230 |
boy | -0.225 |
ksh | -0.222 |
girl | -0.218 |
Year | -0.218 |
Token | home |
Token ID | 1363 |
Feature activation | -5.72e-03 |
Pos logit contributions | |
aches | +0.005 |
vern | +0.005 |
ag | +0.005 |
gh | +0.005 |
earned | +0.005 |
Neg logit contributions | |
boy | -0.006 |
girl | -0.005 |
ksh | -0.005 |
Year | -0.005 |
extingu | -0.005 |
Token | feeling |
Token ID | 4203 |
Feature activation | +4.39e-03 |
Pos logit contributions | |
vern | +0.009 |
aches | +0.009 |
hardly | +0.008 |
achieve | +0.008 |
accomplished | +0.008 |
Neg logit contributions | |
ksh | -0.010 |
Year | -0.010 |
boy | -0.010 |
girl | -0.009 |
extingu | -0.009 |
Token | down |
Token ID | 866 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
boy | +0.008 |
girl | +0.008 |
Year | +0.007 |
extingu | +0.007 |
asleep | +0.007 |
Neg logit contributions | |
vern | -0.007 |
aches | -0.007 |
earned | -0.006 |
imes | -0.006 |
ending | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
vern | +0.026 |
aches | +0.026 |
earned | +0.024 |
imes | +0.024 |
ag | +0.024 |
Neg logit contributions | |
boy | -0.027 |
girl | -0.026 |
Year | -0.025 |
extingu | -0.024 |
ksh | -0.023 |
Token | Here |
Token ID | 3423 |
Feature activation | -5.30e-03 |
Pos logit contributions | |
boy | +0.042 |
girl | +0.039 |
Year | +0.036 |
extingu | +0.035 |
asleep | +0.034 |
Neg logit contributions | |
vern | -0.043 |
aches | -0.042 |
earned | -0.040 |
imes | -0.040 |
ough | -0.039 |
Token | are |
Token ID | 389 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
vern | +0.010 |
aches | +0.010 |
earned | +0.010 |
ending | +0.010 |
fters | +0.010 |
Neg logit contributions | |
boy | -0.008 |
girl | -0.008 |
Year | -0.007 |
duck | -0.006 |
extingu | -0.006 |
Token | Lily |
Token ID | 20037 |
Feature activation | -8.10e-03 |
Pos logit contributions | |
boy | +0.099 |
girl | +0.095 |
Year | +0.085 |
extingu | +0.084 |
asleep | +0.082 |
Neg logit contributions | |
vern | -0.077 |
aches | -0.075 |
earned | -0.070 |
ending | -0.069 |
fters | -0.068 |
Token | 's |
Token ID | 338 |
Feature activation | +9.39e-03 |
Pos logit contributions | |
vern | +0.014 |
aches | +0.014 |
earned | +0.013 |
imes | +0.012 |
iable | +0.012 |
Neg logit contributions | |
boy | -0.014 |
girl | -0.013 |
Year | -0.013 |
extingu | -0.012 |
asleep | -0.012 |
Token | m |
Token ID | 285 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
work | +0.015 |
Year | +0.014 |
boy | +0.014 |
fly | +0.014 |
ksh | +0.014 |
Neg logit contributions | |
aches | -0.015 |
vern | -0.015 |
ag | -0.014 |
ittens | -0.014 |
gh | -0.014 |
Token | ittens |
Token ID | 34978 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
boy | +0.060 |
girl | +0.058 |
Year | +0.054 |
extingu | +0.054 |
asleep | +0.053 |
Neg logit contributions | |
vern | -0.018 |
aches | -0.017 |
earned | -0.015 |
imes | -0.014 |
ending | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
aches | +0.216 |
vern | +0.215 |
earned | +0.198 |
imes | +0.196 |
fters | +0.194 |
Neg logit contributions | |
boy | -0.223 |
girl | -0.212 |
Year | -0.193 |
extingu | -0.191 |
asleep | -0.182 |
Token | They |
Token ID | 1119 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
boy | +0.043 |
girl | +0.041 |
Year | +0.038 |
maid | +0.037 |
work | +0.037 |
Neg logit contributions | |
earned | -0.034 |
vern | -0.033 |
imes | -0.033 |
ough | -0.032 |
aches | -0.032 |
Token | are |
Token ID | 389 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
boy | +0.025 |
girl | +0.024 |
Year | +0.023 |
extingu | +0.022 |
ksh | +0.021 |
Neg logit contributions | |
aches | -0.017 |
vern | -0.017 |
earned | -0.015 |
iable | -0.015 |
fters | -0.015 |
Token | warm |
Token ID | 5814 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
boy | +0.096 |
girl | +0.090 |
Year | +0.086 |
extingu | +0.086 |
work | +0.083 |
Neg logit contributions | |
aches | -0.081 |
vern | -0.076 |
imes | -0.069 |
ag | -0.069 |
supposed | -0.068 |
Token | and |
Token ID | 290 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
ons | +0.010 |
ag | +0.009 |
aces | +0.009 |
ough | +0.009 |
earned | +0.009 |
Neg logit contributions | |
Uh | -0.019 |
extingu | -0.019 |
poster | -0.018 |
fly | -0.018 |
work | -0.018 |
Token | named |
Token ID | 3706 |
Feature activation | -3.95e-03 |
Pos logit contributions | |
boy | +0.049 |
girl | +0.047 |
Year | +0.044 |
extingu | +0.043 |
asleep | +0.041 |
Neg logit contributions | |
aches | -0.042 |
vern | -0.041 |
earned | -0.038 |
ag | -0.037 |
gh | -0.037 |
Token | Mitt |
Token ID | 16627 |
Feature activation | -8.71e-02 |
Pos logit contributions | |
vern | +0.008 |
aches | +0.008 |
earned | +0.008 |
imes | +0.008 |
ending | +0.008 |
Neg logit contributions | |
boy | -0.005 |
girl | -0.005 |
Year | -0.004 |
extingu | -0.004 |
asleep | -0.004 |
Token | ens |
Token ID | 641 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
vern | +0.141 |
aches | +0.138 |
earned | +0.126 |
achieve | +0.124 |
fters | +0.123 |
Neg logit contributions | |
boy | -0.175 |
girl | -0.170 |
extingu | -0.143 |
duck | -0.142 |
asleep | -0.140 |
Token | . |
Token ID | 13 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
vern | +0.199 |
aches | +0.196 |
earned | +0.189 |
fters | +0.187 |
ending | +0.186 |
Neg logit contributions | |
boy | -0.162 |
girl | -0.152 |
extingu | -0.134 |
Year | -0.130 |
asleep | -0.125 |
Token | Mitt |
Token ID | 16627 |
Feature activation | -8.41e-02 |
Pos logit contributions | |
vern | +0.039 |
aches | +0.038 |
iable | +0.035 |
ending | +0.035 |
fters | +0.034 |
Neg logit contributions | |
boy | -0.029 |
girl | -0.027 |
extingu | -0.023 |
Sn | -0.023 |
asleep | -0.023 |
Token | ens |
Token ID | 641 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
vern | +0.140 |
aches | +0.136 |
earned | +0.126 |
achieve | +0.124 |
fters | +0.122 |
Neg logit contributions | |
boy | -0.168 |
girl | -0.162 |
cy | -0.133 |
duck | -0.132 |
extingu | -0.130 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
vern | +0.171 |
aches | +0.168 |
earned | +0.158 |
imes | +0.156 |
fters | +0.156 |
Neg logit contributions | |
boy | -0.179 |
girl | -0.169 |
Year | -0.151 |
extingu | -0.147 |
asleep | -0.141 |
Token | to |
Token ID | 284 |
Feature activation | -9.00e-03 |
Pos logit contributions | |
vern | +0.019 |
aches | +0.018 |
iable | +0.017 |
earned | +0.017 |
fters | +0.017 |
Neg logit contributions | |
boy | -0.021 |
girl | -0.020 |
asleep | -0.018 |
Year | -0.018 |
extingu | -0.017 |
Token | play |
Token ID | 711 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
vern | +0.016 |
ending | +0.015 |
aches | +0.015 |
iable | +0.015 |
imes | +0.015 |
Neg logit contributions | |
boy | -0.015 |
girl | -0.014 |
extingu | -0.013 |
Year | -0.013 |
duck | -0.012 |
Token | with |
Token ID | 351 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
vern | +0.028 |
aches | +0.028 |
earned | +0.027 |
ending | +0.026 |
imes | +0.026 |
Neg logit contributions | |
boy | -0.016 |
girl | -0.014 |
Year | -0.012 |
extingu | -0.012 |
asleep | -0.012 |
Token | toys |
Token ID | 14958 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
boy | +0.039 |
girl | +0.036 |
t | +0.033 |
duck | +0.032 |
extingu | +0.032 |
Neg logit contributions | |
vern | -0.044 |
ending | -0.041 |
iable | -0.041 |
achieve | -0.041 |
earned | -0.040 |
Token | join |
Token ID | 4654 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
vern | +0.003 |
aches | +0.003 |
imes | +0.003 |
earned | +0.003 |
iable | +0.003 |
Neg logit contributions | |
boy | -0.003 |
girl | -0.003 |
duck | -0.003 |
t | -0.003 |
asleep | -0.003 |
Token | them |
Token ID | 606 |
Feature activation | +6.69e-03 |
Pos logit contributions | |
boy | +0.086 |
girl | +0.080 |
extingu | +0.080 |
Year | +0.076 |
ksh | +0.075 |
Neg logit contributions | |
aches | -0.052 |
vern | -0.050 |
ag | -0.050 |
imes | -0.049 |
gh | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | -8.70e-04 |
Pos logit contributions | |
boy | +0.012 |
girl | +0.011 |
Year | +0.010 |
extingu | +0.010 |
ksh | +0.009 |
Neg logit contributions | |
vern | -0.011 |
aches | -0.011 |
imes | -0.010 |
earned | -0.010 |
ag | -0.010 |
Token | but |
Token ID | 475 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
aches | +0.001 |
hardly | +0.001 |
vern | +0.001 |
imes | +0.001 |
achieve | +0.001 |
Neg logit contributions | |
Year | -0.002 |
boy | -0.002 |
extingu | -0.002 |
girl | -0.002 |
cy | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | -1.16e-04 |
Pos logit contributions | |
aches | +0.035 |
vern | +0.035 |
imes | +0.031 |
earned | +0.031 |
iable | +0.030 |
Neg logit contributions | |
boy | -0.067 |
girl | -0.065 |
extingu | -0.062 |
Year | -0.062 |
asleep | -0.058 |
Token | forgot |
Token ID | 16453 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
aches | +0.000 |
vern | +0.000 |
imes | +0.000 |
ending | +0.000 |
gh | +0.000 |
Neg logit contributions | |
boy | -0.000 |
girl | -0.000 |
extingu | -0.000 |
Year | -0.000 |
asleep | -0.000 |
Token | something |
Token ID | 1223 |
Feature activation | -3.63e-03 |
Pos logit contributions | |
vern | +0.154 |
aches | +0.151 |
earned | +0.145 |
fters | +0.142 |
ough | +0.139 |
Neg logit contributions | |
boy | -0.200 |
girl | -0.190 |
asleep | -0.176 |
extingu | -0.168 |
t | -0.165 |
Token | . |
Token ID | 13 |
Feature activation | +9.97e-03 |
Pos logit contributions | |
earned | +0.006 |
vern | +0.006 |
aches | +0.006 |
ough | +0.006 |
fters | +0.006 |
Neg logit contributions | |
boy | -0.007 |
girl | -0.006 |
duck | -0.005 |
extingu | -0.005 |
asleep | -0.005 |
Token | She |
Token ID | 1375 |
Feature activation | +6.76e-03 |
Pos logit contributions | |
boy | +0.019 |
girl | +0.018 |
extingu | +0.017 |
Year | +0.017 |
work | +0.016 |
Neg logit contributions | |
vern | -0.015 |
aches | -0.014 |
imes | -0.014 |
earned | -0.013 |
ending | -0.013 |
Token | forgot |
Token ID | 16453 |
Feature activation | -9.86e-02 |
Pos logit contributions | |
extingu | +0.013 |
Year | +0.012 |
boy | +0.012 |
girl | +0.012 |
work | +0.012 |
Neg logit contributions | |
aches | -0.010 |
hardly | -0.009 |
imes | -0.008 |
accomplished | -0.008 |
gh | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
vern | +0.144 |
aches | +0.141 |
earned | +0.136 |
fters | +0.132 |
ough | +0.129 |
Neg logit contributions | |
boy | -0.199 |
girl | -0.189 |
asleep | -0.177 |
t | -0.166 |
extingu | -0.166 |