TOP ACTIVATIONS
MAX = 10.809

and go home . The wig makes them itch and scratch
that . They put the wig on their heads and go
and a wig . A wig is fake hair that you
Wow , look at this wig !" Anna says . "
. But I like this wig better ." He picks a
." He picks a blue wig with sp iky hair .
, toys , and a wig . A wig is fake
itch and scratch . The wig makes them sick and sad
face , and a curly wig . He wore a big
anymore . The wig is sm elly and dirty
money was gone . His wig was falling off . He
used a hat as the wig . They used a scarf
They both grab the wig and pull it hard .
pull it hard . The wig is old and weak .
black robe and a white wig . He was a judge
each have half of the wig in their hands .
red nose , a colorful wig , and a huge bow
Hey , you broke the wig !" Anna says . "
No , you broke the wig !" Ben says . "
. She told him silly jokes and talked about all the

MIN ACTIVATIONS
MIN = -13.070

this power would come in handy . He was
a time there was a handy man who had a fancy
. The cart came in handy to carry all of the
was very happy because the handy man had helped her .
Maybe it will come in handy one day !"
<|endoftext|> Grand pa was a handy man and he had lots
is that friends come in handy in times of need .
. Then the handy man drove to the young
compassionate act would come in handy a few days later when
they would knock on the handy man 's door .
. So the handy man went to the teach
stepped back to admire his handy work . "
for my son ." The handy man said he could help
of salt could come in handy ," so he scoop ed
Mr . Lee , the handy man . He is fixing
stood back and admired their handy work . The screw was
it 's important to keep hed ges neat and tidy "
work . They trimmed the hed ges and cut the grass
spider lived in an old shed . He was very careful
big red saw near the shed . Lily wanted to touch

INTERVAL 4.839 - 10.809
CONTAINS 1.255%

the picture of the big pink elephant . Tim my said
shot ! All of a sudden , the target burst with
and started to cry . Her friends saw her crying and
with food and drinks . Her parents told her that it
Lily are twins who love music . They have a big

INTERVAL -1.130 - 4.839
CONTAINS 79.443%

it up and down . Zip , zip , zip !"
gy smiled and said , " Me too , W igg
Tim and Jen are sad and angry . They do not
outing to the opera that evening . Tom was very excited
oy ster . He lived on the beach and every day

INTERVAL -7.100 - -1.130
CONTAINS 19.043%

. Lily wanted to use it as a sword , but
shiny and hard . They want to climb on it .
said to Rose , " I 'm sorry I lost you
on many adventures and met lots of friends .
is a good thing , don 't you think ?"

INTERVAL -13.070 - -7.100
CONTAINS 0.259%

use your brain , even if you cannot use your eyes
. They had a big box of trains and tracks that
out loud , which disturbed Mill ie . Mill
were happy . They had saved their truck and their rocks
help . Is it OK if I talk to you ?"
Token and
Token ID290
Feature activation-1.78e-01

Pos logit contributions
 aids+0.058
 wig+0.056
 hair+0.056
 jokes+0.053
 song+0.051
Neg logit contributions
 Mill-0.074
 sorts-0.074
 Joey-0.070
neath-0.068
 scaven-0.068
Token go
Token ID467
Feature activation+4.64e-01

Pos logit contributions
 sorts+0.013
 Mill+0.012
 unst+0.012
neath+0.012
 Joey+0.012
Neg logit contributions
 aids-0.011
 wig-0.011
ggie-0.010
agging-0.010
 jokes-0.010
Token home
Token ID1363
Feature activation-5.66e+00

Pos logit contributions
 aids+0.038
 wig+0.037
 hair+0.037
 jokes+0.035
 song+0.034
Neg logit contributions
 sorts-0.026
 Mill-0.026
 Joey-0.024
neath-0.024
 scaven-0.023
Token.
Token ID13
Feature activation+4.33e-01

Pos logit contributions
 Mill+0.456
 sorts+0.453
 Joey+0.433
neath+0.429
 scaven+0.418
Neg logit contributions
 aids-0.329
 wig-0.317
 hair-0.315
 jokes-0.299
 song-0.286
Token The
Token ID383
Feature activation+1.59e+00

Pos logit contributions
 wig+0.035
 aids+0.034
 jokes+0.032
 hair+0.032
 song+0.032
Neg logit contributions
 Mill-0.025
 sorts-0.024
 Joey-0.024
neath-0.022
 aback-0.021
Token wig
Token ID45678
Feature activation+1.08e+01

Pos logit contributions
 aids+0.102
agged+0.091
ggie+0.083
agging+0.079
 jokes+0.079
Neg logit contributions
 hed-0.103
 sorts-0.103
 shed-0.100
 deeper-0.099
 scaven-0.098
Token makes
Token ID1838
Feature activation+3.24e+00

Pos logit contributions
 aids+0.847
 wig+0.818
 jokes+0.772
 song+0.765
ggie+0.764
Neg logit contributions
 sorts-0.597
neath-0.556
 Mill-0.547
'll-0.541
 scaven-0.539
Token them
Token ID606
Feature activation+2.60e+00

Pos logit contributions
 wig+0.233
 aids+0.228
 hair+0.213
 jokes+0.205
 cheeks+0.205
Neg logit contributions
 sorts-0.207
 Mill-0.205
 Joey-0.194
 unst-0.187
neath-0.186
Token itch
Token ID49700
Feature activation+3.96e+00

Pos logit contributions
 aids+0.169
 wig+0.162
 jokes+0.148
 hair+0.147
ggie+0.146
Neg logit contributions
 sorts-0.186
 Mill-0.182
 unst-0.180
 Joey-0.172
 scaven-0.169
Token and
Token ID290
Feature activation-1.93e-01

Pos logit contributions
 aids+0.242
 wig+0.232
 hair+0.232
 jokes+0.225
 song+0.215
Neg logit contributions
 Mill-0.309
 sorts-0.304
 Joey-0.292
neath-0.280
 scaven-0.279
Token scratch
Token ID12692
Feature activation+2.60e+00

Pos logit contributions
 sorts+0.013
 Mill+0.013
 unst+0.012
 Joey+0.012
 hed+0.012
Neg logit contributions
 aids-0.013
ggie-0.012
 wig-0.012
agging-0.011
agged-0.011
Token that
Token ID326
Feature activation+2.35e+00

Pos logit contributions
 Mill+0.100
 sorts+0.097
 Joey+0.093
 scaven+0.087
neath+0.087
Neg logit contributions
 aids-0.138
 wig-0.136
 hair-0.128
 jokes-0.123
 song-0.122
Token.
Token ID13
Feature activation+4.29e-01

Pos logit contributions
 aids+0.170
 wig+0.169
 hair+0.158
agging+0.153
 jokes+0.151
Neg logit contributions
 Mill-0.151
 sorts-0.151
 Joey-0.142
neath-0.132
 scaven-0.132
Token They
Token ID1119
Feature activation-2.18e-01

Pos logit contributions
 wig+0.033
 aids+0.033
 hair+0.031
 jokes+0.031
 song+0.030
Neg logit contributions
 Mill-0.027
 sorts-0.026
 Joey-0.025
neath-0.024
 aback-0.023
Token put
Token ID1234
Feature activation-1.03e+00

Pos logit contributions
 sorts+0.014
 Mill+0.014
 Joey+0.013
neath+0.013
 scaven+0.013
Neg logit contributions
 aids-0.016
 wig-0.015
 hair-0.015
 jokes-0.015
 song-0.014
Token the
Token ID262
Feature activation-5.15e-01

Pos logit contributions
 Mill+0.074
 sorts+0.074
 scaven+0.070
 Joey+0.069
neath+0.067
Neg logit contributions
 hair-0.069
 aids-0.068
 wig-0.067
 jokes-0.064
 song-0.060
Token wig
Token ID45678
Feature activation+1.08e+01

Pos logit contributions
 sorts+0.033
 Mill+0.033
 unst+0.032
 scaven+0.031
 Joey+0.031
Neg logit contributions
 aids-0.036
 jokes-0.032
 wig-0.032
 hair-0.032
ggie-0.031
Token on
Token ID319
Feature activation+3.25e+00

Pos logit contributions
 aids+0.802
 wig+0.775
 jokes+0.746
 hair+0.736
 song+0.698
Neg logit contributions
 Mill-0.671
 sorts-0.670
 unst-0.635
neath-0.628
 Joey-0.619
Token their
Token ID511
Feature activation+8.70e-01

Pos logit contributions
 aids+0.233
 wig+0.227
 hair+0.222
 jokes+0.216
 song+0.206
Neg logit contributions
 sorts-0.215
 Mill-0.215
 Joey-0.200
neath-0.196
 scaven-0.195
Token heads
Token ID6665
Feature activation+9.60e-01

Pos logit contributions
 aids+0.056
 Dancing+0.052
ggie+0.050
 episode+0.050
uren+0.048
Neg logit contributions
keeping-0.054
 shed-0.052
 unst-0.052
 barrel-0.049
 extingu-0.049
Token and
Token ID290
Feature activation-1.78e-01

Pos logit contributions
 aids+0.058
 wig+0.056
 hair+0.056
 jokes+0.053
 song+0.051
Neg logit contributions
 Mill-0.074
 sorts-0.074
 Joey-0.070
neath-0.068
 scaven-0.068
Token go
Token ID467
Feature activation+4.64e-01

Pos logit contributions
 sorts+0.013
 Mill+0.012
 unst+0.012
neath+0.012
 Joey+0.012
Neg logit contributions
 aids-0.011
 wig-0.011
ggie-0.010
agging-0.010
 jokes-0.010
Token and
Token ID290
Feature activation-1.99e-01

Pos logit contributions
 Mill+0.008
 sorts+0.008
neath+0.007
 unst+0.007
 Joey+0.007
Neg logit contributions
 aids-0.008
 wig-0.007
ggie-0.007
 jokes-0.007
 Dancing-0.007
Token a
Token ID257
Feature activation-3.65e-01

Pos logit contributions
 sorts+0.014
 Mill+0.014
 Joey+0.013
 scaven+0.012
 unst+0.012
Neg logit contributions
 aids-0.013
 wig-0.012
ggie-0.012
agging-0.011
agged-0.011
Token wig
Token ID45678
Feature activation+1.08e+01

Pos logit contributions
 Mill+0.026
 sorts+0.026
 Joey+0.024
 scaven+0.024
neath+0.024
Neg logit contributions
 aids-0.024
 wig-0.022
 hair-0.022
 jokes-0.022
ggie-0.020
Token.
Token ID13
Feature activation+4.29e-01

Pos logit contributions
 aids+0.789
 wig+0.736
 jokes+0.720
 hair+0.701
 song+0.686
Neg logit contributions
 Mill-0.686
 sorts-0.685
 Joey-0.625
neath-0.618
 unst-0.612
Token A
Token ID317
Feature activation+3.26e+00

Pos logit contributions
 wig+0.034
 aids+0.034
 jokes+0.031
 hair+0.031
 song+0.031
Neg logit contributions
 Mill-0.026
 sorts-0.024
 Joey-0.024
neath-0.023
'll-0.022
Token wig
Token ID45678
Feature activation+1.08e+01

Pos logit contributions
 aids+0.215
 wig+0.195
 jokes+0.193
 hair+0.192
 cheeks+0.179
Neg logit contributions
 sorts-0.236
 Mill-0.234
 scaven-0.218
 Joey-0.216
 unst-0.209
Token is
Token ID318
Feature activation-3.14e-01

Pos logit contributions
 aids+0.838
 wig+0.788
 jokes+0.768
 hair+0.758
 song+0.743
Neg logit contributions
 sorts-0.646
 Mill-0.645
neath-0.588
 Joey-0.584
 scaven-0.564
Token fake
Token ID8390
Feature activation+3.78e+00

Pos logit contributions
 Mill+0.018
 sorts+0.018
 Joey+0.016
 scaven+0.015
 Wil+0.015
Neg logit contributions
 aids-0.024
 cheeks-0.022
 wig-0.022
agged-0.022
agging-0.021
Token hair
Token ID4190
Feature activation+1.00e+01

Pos logit contributions
 aids+0.294
 wig+0.264
 jokes+0.252
agged+0.249
 hair+0.247
Neg logit contributions
 Mill-0.229
 sorts-0.226
 Joey-0.209
wood-0.202
 scaven-0.201
Token that
Token ID326
Feature activation+2.35e+00

Pos logit contributions
 aids+0.729
 wig+0.690
 jokes+0.667
 hair+0.645
 song+0.621
Neg logit contributions
 sorts-0.636
 Mill-0.636
 Joey-0.585
 unst-0.573
neath-0.571
Token you
Token ID345
Feature activation-6.73e-01

Pos logit contributions
 aids+0.162
 wig+0.157
 hair+0.154
 jokes+0.150
 song+0.141
Neg logit contributions
 Mill-0.163
 sorts-0.162
 Joey-0.152
neath-0.149
 scaven-0.149
TokenWow
Token ID22017
Feature activation-8.00e-01

Pos logit contributions
neath+0.007
 sorts+0.007
 Mill+0.007
 hed+0.006
 aback+0.006
Neg logit contributions
 aids-0.017
 jokes-0.016
agging-0.016
 cheeks-0.016
 hair-0.015
Token,
Token ID11
Feature activation-1.08e-01

Pos logit contributions
 sorts+0.072
 Mill+0.066
neath+0.064
 aback+0.063
wood+0.063
Neg logit contributions
 hair-0.042
 wig-0.041
 jokes-0.038
 aids-0.037
 cheeks-0.037
Token look
Token ID804
Feature activation+5.08e-01

Pos logit contributions
 Mill+0.006
 sorts+0.006
 Joey+0.006
 scaven+0.005
neath+0.005
Neg logit contributions
 aids-0.009
 wig-0.008
 hair-0.008
 jokes-0.008
 song-0.008
Token at
Token ID379
Feature activation+2.01e+00

Pos logit contributions
 aids+0.032
 wig+0.031
 hair+0.029
 jokes+0.029
 song+0.028
Neg logit contributions
 Mill-0.038
 sorts-0.038
 Joey-0.036
 scaven-0.035
 unst-0.035
Token this
Token ID428
Feature activation+3.91e-02

Pos logit contributions
 aids+0.136
 wig+0.134
 hair+0.131
 jokes+0.128
 song+0.119
Neg logit contributions
 sorts-0.141
 Mill-0.140
 Joey-0.130
 unst-0.130
neath-0.130
Token wig
Token ID45678
Feature activation+1.08e+01

Pos logit contributions
 aids+0.003
 wig+0.003
 jokes+0.003
 hair+0.003
 cheeks+0.003
Neg logit contributions
 sorts-0.002
 Mill-0.002
 Joey-0.002
 scaven-0.002
 unst-0.002
Token!"
Token ID2474
Feature activation-2.91e+00

Pos logit contributions
 aids+1.034
 wig+1.016
 hair+0.995
 jokes+0.977
 song+0.943
Neg logit contributions
 Mill-0.451
 sorts-0.451
 Joey-0.404
neath-0.389
 scaven-0.385
Token Anna
Token ID11735
Feature activation+4.86e+00

Pos logit contributions
 Mill+0.218
 Joey+0.210
 sorts+0.200
 Bobby+0.190
 Suz+0.189
Neg logit contributions
agging-0.188
 wig-0.185
 aids-0.182
 song-0.174
agged-0.163
Token says
Token ID1139
Feature activation+6.71e-01

Pos logit contributions
 aids+0.333
 wig+0.323
 hair+0.308
 jokes+0.303
 song+0.291
Neg logit contributions
 sorts-0.340
 Mill-0.337
 Joey-0.315
neath-0.308
 scaven-0.307
Token.
Token ID13
Feature activation+4.30e-01

Pos logit contributions
 aids+0.060
 wig+0.059
 jokes+0.053
ggie+0.052
 clown+0.052
Neg logit contributions
 Mill-0.034
 unst-0.032
 Joey-0.031
 aback-0.028
 sorts-0.028
Token "
Token ID366
Feature activation+4.92e-01

Pos logit contributions
 aids+0.037
 wig+0.036
 jokes+0.035
ggie+0.034
agging+0.033
Neg logit contributions
 Mill-0.024
 Joey-0.021
neath-0.020
 aback-0.020
 sorts-0.020
Token.
Token ID13
Feature activation+4.42e-01

Pos logit contributions
 wig+0.151
 hair+0.150
 aids+0.147
 jokes+0.142
 song+0.137
Neg logit contributions
 Mill-0.180
 sorts-0.174
neath-0.172
 Joey-0.168
 unst-0.164
Token But
Token ID887
Feature activation+1.59e+00

Pos logit contributions
 aids+0.029
 wig+0.028
 hair+0.027
 jokes+0.026
 song+0.025
Neg logit contributions
 sorts-0.032
 Mill-0.032
 Joey-0.030
neath-0.029
 scaven-0.029
Token I
Token ID314
Feature activation+7.64e-01

Pos logit contributions
 aids+0.110
 wig+0.107
 hair+0.104
 jokes+0.101
 song+0.096
Neg logit contributions
 sorts-0.109
 Mill-0.109
 Joey-0.102
neath-0.100
 scaven-0.099
Token like
Token ID588
Feature activation-1.49e-01

Pos logit contributions
 aids+0.054
 wig+0.053
 hair+0.053
 jokes+0.050
 song+0.048
Neg logit contributions
 Mill-0.052
 sorts-0.050
 Joey-0.048
neath-0.047
 scaven-0.046
Token this
Token ID428
Feature activation+3.94e-02

Pos logit contributions
 sorts+0.007
 Mill+0.007
 Joey+0.006
 scaven+0.006
 hed+0.006
Neg logit contributions
 aids-0.013
agged-0.013
 wig-0.012
ggie-0.012
agging-0.012
Token wig
Token ID45678
Feature activation+1.08e+01

Pos logit contributions
 aids+0.003
agged+0.003
 cheeks+0.002
agging+0.002
 jokes+0.002
Neg logit contributions
 sorts-0.003
 Mill-0.002
'll-0.002
!",-0.002
 Joey-0.002
Token better
Token ID1365
Feature activation-3.85e+00

Pos logit contributions
 aids+0.875
 wig+0.790
 jokes+0.752
 hair+0.745
 cheeks+0.742
Neg logit contributions
 sorts-0.628
 Mill-0.573
'll-0.548
 unst-0.533
 Joey-0.525
Token."
Token ID526
Feature activation-3.36e-01

Pos logit contributions
 sorts+0.207
 Mill+0.193
 Joey+0.178
'll+0.176
 unst+0.175
Neg logit contributions
 aids-0.333
 wig-0.296
 jokes-0.288
 cheeks-0.282
 hair-0.279
Token He
Token ID679
Feature activation+6.40e-01

Pos logit contributions
 Joey+0.017
 Mill+0.017
 sorts+0.017
 aback+0.015
 Bobby+0.015
Neg logit contributions
 aids-0.029
 wig-0.028
ggie-0.027
 song-0.027
agging-0.026
Token picks
Token ID11103
Feature activation+8.52e-02

Pos logit contributions
 aids+0.049
 wig+0.045
 song+0.044
ggie+0.044
ggy+0.042
Neg logit contributions
 sorts-0.038
neath-0.037
 scaven-0.036
'll-0.034
 Mill-0.033
Token a
Token ID257
Feature activation-3.60e-01

Pos logit contributions
 aids+0.009
 cheeks+0.008
 wig+0.008
 jokes+0.008
 song+0.008
Neg logit contributions
 sorts-0.003
 Mill-0.002
neath-0.002
 aback-0.002
 Joey-0.002
Token."
Token ID526
Feature activation-3.36e-01

Pos logit contributions
 sorts+0.207
 Mill+0.193
 Joey+0.178
'll+0.176
 unst+0.175
Neg logit contributions
 aids-0.333
 wig-0.296
 jokes-0.288
 cheeks-0.282
 hair-0.279
Token He
Token ID679
Feature activation+6.40e-01

Pos logit contributions
 Joey+0.017
 Mill+0.017
 sorts+0.017
 aback+0.015
 Bobby+0.015
Neg logit contributions
 aids-0.029
 wig-0.028
ggie-0.027
 song-0.027
agging-0.026
Token picks
Token ID11103
Feature activation+8.52e-02

Pos logit contributions
 aids+0.049
 wig+0.045
 song+0.044
ggie+0.044
ggy+0.042
Neg logit contributions
 sorts-0.038
neath-0.037
 scaven-0.036
'll-0.034
 Mill-0.033
Token a
Token ID257
Feature activation-3.60e-01

Pos logit contributions
 aids+0.009
 cheeks+0.008
 wig+0.008
 jokes+0.008
 song+0.008
Neg logit contributions
 sorts-0.003
 Mill-0.002
neath-0.002
 aback-0.002
 Joey-0.002
Token blue
Token ID4171
Feature activation+4.87e+00

Pos logit contributions
 sorts+0.023
'll+0.021
ucer+0.021
 unst+0.020
 aback+0.019
Neg logit contributions
 aids-0.026
 jokes-0.024
agged-0.023
 cheeks-0.022
agging-0.021
Token wig
Token ID45678
Feature activation+1.08e+01

Pos logit contributions
 aids+0.340
 jokes+0.286
agged+0.276
ggies+0.268
ggie+0.267
Neg logit contributions
 sorts-0.338
ucer-0.295
neath-0.294
'll-0.293
 Joey-0.288
Token with
Token ID351
Feature activation+9.41e-01

Pos logit contributions
 aids+0.947
 jokes+0.874
 wig+0.841
 cheeks+0.828
agged+0.827
Neg logit contributions
 sorts-0.516
neath-0.483
 Mill-0.483
 unst-0.480
 aback-0.458
Token sp
Token ID599
Feature activation+3.76e-01

Pos logit contributions
 aids+0.072
 wig+0.065
ggie+0.063
 jokes+0.062
ggy+0.062
Neg logit contributions
 sorts-0.059
 Mill-0.056
 Joey-0.055
neath-0.055
 ease-0.051
Tokeniky
Token ID47536
Feature activation+2.88e+00

Pos logit contributions
 aids+0.027
 wig+0.026
 jokes+0.025
 song+0.025
 hair+0.024
Neg logit contributions
 sorts-0.025
 Mill-0.023
 Joey-0.022
 scaven-0.022
aved-0.021
Token hair
Token ID4190
Feature activation+9.97e+00

Pos logit contributions
 aids+0.195
ggie+0.170
 song+0.157
 episode+0.156
 jokes+0.155
Neg logit contributions
 sorts-0.176
neath-0.175
 aback-0.171
 Mill-0.169
 Joey-0.169
Token.
Token ID13
Feature activation+4.31e-01

Pos logit contributions
 aids+1.003
 jokes+0.899
ggie+0.854
agged+0.836
 episode+0.825
Neg logit contributions
neath-0.340
 unst-0.332
 sorts-0.322
pling-0.320
 Mill-0.304
Token,
Token ID11
Feature activation-1.11e-01

Pos logit contributions
 hair+0.113
 wig+0.107
 aids+0.103
 cheeks+0.097
 jokes+0.095
Neg logit contributions
 sorts-0.189
 Mill-0.180
 Joey-0.174
 scaven-0.174
 aback-0.168
Token toys
Token ID14958
Feature activation-3.62e-01

Pos logit contributions
 Mill+0.008
 sorts+0.008
neath+0.007
 unst+0.007
 Joey+0.007
Neg logit contributions
 aids-0.007
 wig-0.007
ggie-0.007
 jokes-0.006
ggy-0.006
Token,
Token ID11
Feature activation-1.13e-01

Pos logit contributions
 sorts+0.034
 Mill+0.033
 Joey+0.033
 unst+0.031
 aback+0.031
Neg logit contributions
 hair-0.018
 wig-0.016
 aids-0.015
 cheeks-0.014
 jokes-0.014
Token and
Token ID290
Feature activation-1.99e-01

Pos logit contributions
 Mill+0.008
 sorts+0.008
neath+0.007
 unst+0.007
 Joey+0.007
Neg logit contributions
 aids-0.008
 wig-0.007
ggie-0.007
 jokes-0.007
 Dancing-0.007
Token a
Token ID257
Feature activation-3.65e-01

Pos logit contributions
 sorts+0.014
 Mill+0.014
 Joey+0.013
 scaven+0.012
 unst+0.012
Neg logit contributions
 aids-0.013
 wig-0.012
ggie-0.012
agging-0.011
agged-0.011
Token wig
Token ID45678
Feature activation+1.08e+01

Pos logit contributions
 Mill+0.026
 sorts+0.026
 Joey+0.024
 scaven+0.024
neath+0.024
Neg logit contributions
 aids-0.024
 wig-0.022
 hair-0.022
 jokes-0.022
ggie-0.020
Token.
Token ID13
Feature activation+4.29e-01

Pos logit contributions
 aids+0.789
 wig+0.736
 jokes+0.720
 hair+0.701
 song+0.686
Neg logit contributions
 Mill-0.686
 sorts-0.685
 Joey-0.625
neath-0.618
 unst-0.612
Token A
Token ID317
Feature activation+3.26e+00

Pos logit contributions
 wig+0.034
 aids+0.034
 jokes+0.031
 hair+0.031
 song+0.031
Neg logit contributions
 Mill-0.026
 sorts-0.024
 Joey-0.024
neath-0.023
'll-0.022
Token wig
Token ID45678
Feature activation+1.08e+01

Pos logit contributions
 aids+0.215
 wig+0.195
 jokes+0.193
 hair+0.192
 cheeks+0.179
Neg logit contributions
 sorts-0.236
 Mill-0.234
 scaven-0.218
 Joey-0.216
 unst-0.209
Token is
Token ID318
Feature activation-3.14e-01

Pos logit contributions
 aids+0.838
 wig+0.788
 jokes+0.768
 hair+0.758
 song+0.743
Neg logit contributions
 sorts-0.646
 Mill-0.645
neath-0.588
 Joey-0.584
 scaven-0.564
Token fake
Token ID8390
Feature activation+3.78e+00

Pos logit contributions
 Mill+0.018
 sorts+0.018
 Joey+0.016
 scaven+0.015
 Wil+0.015
Neg logit contributions
 aids-0.024
 cheeks-0.022
 wig-0.022
agged-0.022
agging-0.021
Token itch
Token ID49700
Feature activation+3.96e+00

Pos logit contributions
 aids+0.169
 wig+0.162
 jokes+0.148
 hair+0.147
ggie+0.146
Neg logit contributions
 sorts-0.186
 Mill-0.182
 unst-0.180
 Joey-0.172
 scaven-0.169
Token and
Token ID290
Feature activation-1.93e-01

Pos logit contributions
 aids+0.242
 wig+0.232
 hair+0.232
 jokes+0.225
 song+0.215
Neg logit contributions
 Mill-0.309
 sorts-0.304
 Joey-0.292
neath-0.280
 scaven-0.279
Token scratch
Token ID12692
Feature activation+2.60e+00

Pos logit contributions
 sorts+0.013
 Mill+0.013
 unst+0.012
 Joey+0.012
 hed+0.012
Neg logit contributions
 aids-0.013
ggie-0.012
 wig-0.012
agging-0.011
agged-0.011
Token.
Token ID13
Feature activation+4.36e-01

Pos logit contributions
 aids+0.166
 wig+0.161
 hair+0.159
 jokes+0.154
 song+0.146
Neg logit contributions
 Mill-0.193
 sorts-0.192
 Joey-0.180
 scaven-0.178
neath-0.177
Token The
Token ID383
Feature activation+1.58e+00

Pos logit contributions
 wig+0.035
 aids+0.033
 hair+0.031
 song+0.031
 jokes+0.031
Neg logit contributions
 Mill-0.026
 sorts-0.025
 Joey-0.024
neath-0.024
 aback-0.022
Token wig
Token ID45678
Feature activation+1.08e+01

Pos logit contributions
 aids+0.092
agged+0.081
ggie+0.075
Her+0.072
 Her+0.071
Neg logit contributions
 hed-0.108
 sorts-0.108
 shed-0.104
 deeper-0.103
 unst-0.103
Token makes
Token ID1838
Feature activation+3.22e+00

Pos logit contributions
 aids+0.840
 wig+0.816
ggie+0.770
 jokes+0.755
 song+0.748
Neg logit contributions
 sorts-0.591
neath-0.555
'll-0.550
 unst-0.537
 scaven-0.528
Token them
Token ID606
Feature activation+2.60e+00

Pos logit contributions
 wig+0.235
 aids+0.228
 hair+0.212
 cheeks+0.205
agging+0.204
Neg logit contributions
 sorts-0.203
 Mill-0.200
 Joey-0.190
neath-0.183
 unst-0.182
Token sick
Token ID6639
Feature activation+3.13e-01

Pos logit contributions
 aids+0.178
 wig+0.171
 jokes+0.156
 hair+0.155
ggie+0.154
Neg logit contributions
 sorts-0.177
 Mill-0.173
 unst-0.173
 Joey-0.162
 scaven-0.161
Token and
Token ID290
Feature activation-2.05e-01

Pos logit contributions
 aids+0.022
 wig+0.022
 hair+0.020
 jokes+0.020
ggie+0.020
Neg logit contributions
 sorts-0.020
 Mill-0.020
 Joey-0.019
 unst-0.019
neath-0.018
Token sad
Token ID6507
Feature activation+4.01e+00

Pos logit contributions
 sorts+0.014
 Mill+0.013
 unst+0.013
 Joey+0.013
 scaven+0.012
Neg logit contributions
 aids-0.014
 wig-0.014
ggie-0.013
 hair-0.012
agging-0.012
Token face
Token ID1986
Feature activation+6.87e+00

Pos logit contributions
 aids+0.168
agged+0.143
 jokes+0.142
 Dancing+0.141
ggie+0.140
Neg logit contributions
 Mill-0.177
 Joey-0.173
 sorts-0.169
 barrel-0.169
 extingu-0.165
Token,
Token ID11
Feature activation-2.09e-01

Pos logit contributions
 aids+0.663
 jokes+0.617
 wig+0.602
agged+0.601
 Dancing+0.596
Neg logit contributions
pling-0.229
 Mill-0.227
 Wil-0.197
 Joey-0.196
neath-0.192
Token and
Token ID290
Feature activation-2.72e-01

Pos logit contributions
 Mill+0.011
 Joey+0.010
 sorts+0.010
neath+0.010
 unst+0.009
Neg logit contributions
 aids-0.018
 wig-0.016
ggie-0.016
 jokes-0.015
 Dancing-0.015
Token a
Token ID257
Feature activation-4.37e-01

Pos logit contributions
 sorts+0.015
 Mill+0.015
 Joey+0.014
neath+0.013
 scaven+0.013
Neg logit contributions
 aids-0.022
 wig-0.021
agging-0.020
agged-0.020
ggie-0.019
Token curly
Token ID45731
Feature activation+7.25e+00

Pos logit contributions
 Mill+0.031
 sorts+0.030
 Joey+0.029
 scaven+0.029
 unst+0.028
Neg logit contributions
 aids-0.027
agged-0.026
 jokes-0.024
ggie-0.024
agging-0.023
Token wig
Token ID45678
Feature activation+1.07e+01

Pos logit contributions
 aids+0.401
 jokes+0.335
 Dancing+0.333
azes+0.319
 episode+0.315
Neg logit contributions
 Mill-0.495
 Joey-0.478
 unst-0.455
!",-0.445
 sorts-0.442
Token.
Token ID13
Feature activation+3.63e-01

Pos logit contributions
 aids+0.878
 jokes+0.785
 wig+0.781
 song+0.750
 Dancing+0.745
Neg logit contributions
 Mill-0.556
 sorts-0.553
 unst-0.521
pling-0.514
aved-0.509
Token He
Token ID679
Feature activation+5.70e-01

Pos logit contributions
 wig+0.026
 aids+0.026
 song+0.025
 hair+0.024
 jokes+0.024
Neg logit contributions
 Mill-0.024
 Joey-0.023
 sorts-0.022
 Bobby-0.021
neath-0.021
Token wore
Token ID12408
Feature activation+4.86e+00

Pos logit contributions
 aids+0.044
agging+0.043
 wig+0.041
agged+0.040
 hair+0.039
Neg logit contributions
 sorts-0.032
 Mill-0.030
 scaven-0.029
 Joey-0.029
'll-0.029
Token a
Token ID257
Feature activation-4.03e-01

Pos logit contributions
 aids+0.397
 wig+0.372
 cheeks+0.362
agging+0.358
 song+0.353
Neg logit contributions
 Mill-0.258
 sorts-0.247
 Joey-0.245
neath-0.233
 aback-0.225
Token big
Token ID1263
Feature activation-6.47e-01

Pos logit contributions
 sorts+0.021
 barrel+0.021
 treasure+0.020
 Mill+0.020
'll+0.020
Neg logit contributions
 aids-0.031
 jokes-0.027
azes-0.026
 cheeks-0.025
ggie-0.025
Token anymore
Token ID7471
Feature activation+5.66e+00

Pos logit contributions
 aids+0.133
 wig+0.129
 hair+0.122
 cheeks+0.119
 jokes+0.116
Neg logit contributions
 sorts-0.127
 unst-0.121
 Mill-0.117
'll-0.115
 aback-0.115
Token.
Token ID13
Feature activation+3.29e-01

Pos logit contributions
 aids+0.438
 wig+0.433
 hair+0.408
ggie+0.380
 blond+0.378
Neg logit contributions
 sorts-0.337
 Mill-0.329
 Joey-0.309
 scaven-0.294
 unst-0.284
Token
Token ID198
Feature activation-2.28e-01

Pos logit contributions
 wig+0.029
 aids+0.028
ggie+0.026
 jokes+0.026
 haircut+0.026
Neg logit contributions
 Mill-0.017
 sorts-0.016
 Joey-0.015
neath-0.015
 aback-0.014
Token
Token ID198
Feature activation-2.11e-01

Pos logit contributions
 sorts+0.015
 Mill+0.015
 Joey+0.014
neath+0.014
 scaven+0.013
Neg logit contributions
 aids-0.016
 wig-0.016
 hair-0.016
 jokes-0.015
 cheeks-0.015
TokenThe
Token ID464
Feature activation+1.07e+00

Pos logit contributions
 sorts+0.014
 Mill+0.014
neath+0.013
 Joey+0.013
 unst+0.013
Neg logit contributions
 aids-0.014
 wig-0.014
 hair-0.014
 jokes-0.014
 cheeks-0.013
Token wig
Token ID45678
Feature activation+1.07e+01

Pos logit contributions
 aids+0.064
 wig+0.060
 hair+0.058
 jokes+0.055
ggie+0.054
Neg logit contributions
 sorts-0.079
 Mill-0.078
 Joey-0.075
 scaven-0.074
 unst-0.073
Token is
Token ID318
Feature activation-3.79e-01

Pos logit contributions
 aids+0.874
 wig+0.858
 blond+0.814
ggie+0.811
 song+0.809
Neg logit contributions
 sorts-0.512
'll-0.479
neath-0.467
 scaven-0.442
 will-0.427
Token sm
Token ID895
Feature activation-1.57e+00

Pos logit contributions
 unst+0.025
 sorts+0.023
 Mill+0.022
 Joey+0.022
 handy+0.021
Neg logit contributions
 wig-0.026
 aids-0.025
 cheeks-0.025
 Dancing-0.023
uren-0.023
Tokenelly
Token ID6148
Feature activation+3.15e-02

Pos logit contributions
 sorts+0.097
 Mill+0.094
 Joey+0.088
neath+0.086
 scaven+0.085
Neg logit contributions
 aids-0.122
 wig-0.118
 hair-0.114
 jokes-0.112
 song-0.108
Token and
Token ID290
Feature activation-2.31e-01

Pos logit contributions
 aids+0.002
 wig+0.002
 hair+0.002
 jokes+0.002
 song+0.002
Neg logit contributions
 sorts-0.002
 Mill-0.002
 Joey-0.002
 scaven-0.002
 unst-0.002
Token dirty
Token ID11841
Feature activation-1.81e+00

Pos logit contributions
 sorts+0.017
 Mill+0.017
 Joey+0.016
 unst+0.015
neath+0.015
Neg logit contributions
 aids-0.015
 wig-0.015
 hair-0.014
 jokes-0.014
ggie-0.013
Token money
Token ID1637
Feature activation-3.89e+00

Pos logit contributions
 aids+0.357
 wig+0.331
 hair+0.308
 jokes+0.300
agging+0.292
Neg logit contributions
 sorts-0.449
 Mill-0.446
 Joey-0.428
 scaven-0.420
 unst-0.406
Token was
Token ID373
Feature activation-3.79e-01

Pos logit contributions
 sorts+0.300
 Mill+0.300
 Joey+0.278
neath+0.270
 scaven+0.264
Neg logit contributions
 aids-0.237
 wig-0.235
 hair-0.234
 jokes-0.220
 cheeks-0.213
Token gone
Token ID3750
Feature activation-1.40e+00

Pos logit contributions
 Mill+0.024
 sorts+0.024
 unst+0.023
 Joey+0.023
neath+0.022
Neg logit contributions
 aids-0.027
 wig-0.027
 hair-0.026
 jokes-0.026
 cheeks-0.025
Token.
Token ID13
Feature activation+2.94e-01

Pos logit contributions
 sorts+0.122
 Mill+0.120
neath+0.114
 Joey+0.114
pling+0.112
Neg logit contributions
 hair-0.066
 aids-0.062
 song-0.059
 wig-0.058
 jokes-0.057
Token His
Token ID2399
Feature activation+6.01e+00

Pos logit contributions
 aids+0.018
 wig+0.017
 hair+0.017
 jokes+0.016
 song+0.016
Neg logit contributions
 Mill-0.023
 sorts-0.023
 Joey-0.022
neath-0.021
 scaven-0.021
Token wig
Token ID45678
Feature activation+1.07e+01

Pos logit contributions
 aids+0.358
 wig+0.329
 hair+0.306
 jokes+0.303
agging+0.291
Neg logit contributions
 sorts-0.454
 Mill-0.454
 Joey-0.434
 scaven-0.430
 unst-0.419
Token was
Token ID373
Feature activation-3.21e-01

Pos logit contributions
 aids+0.775
 wig+0.753
 hair+0.729
 jokes+0.717
 song+0.683
Neg logit contributions
 Mill-0.694
 sorts-0.693
 Joey-0.647
neath-0.634
 scaven-0.630
Token falling
Token ID7463
Feature activation+1.12e+00

Pos logit contributions
 Mill+0.020
 sorts+0.020
 Joey+0.019
 unst+0.019
neath+0.019
Neg logit contributions
 aids-0.023
 wig-0.023
 jokes-0.022
 hair-0.022
 song-0.021
Token off
Token ID572
Feature activation+7.64e-01

Pos logit contributions
 hair+0.072
 aids+0.068
 song+0.063
 wig+0.063
 cheeks+0.062
Neg logit contributions
 sorts-0.083
 Mill-0.078
 Joey-0.073
 scaven-0.072
 awaits-0.069
Token.
Token ID13
Feature activation+3.56e-01

Pos logit contributions
 aids+0.047
 hair+0.044
 wig+0.044
 jokes+0.042
 song+0.041
Neg logit contributions
 sorts-0.058
 Mill-0.058
 unst-0.054
 Joey-0.054
 scaven-0.053
Token He
Token ID679
Feature activation+5.59e-01

Pos logit contributions
 aids+0.021
 wig+0.021
 hair+0.020
 jokes+0.020
 song+0.019
Neg logit contributions
 Mill-0.028
 sorts-0.027
 Joey-0.026
neath-0.025
 scaven-0.025
Token used
Token ID973
Feature activation-5.35e+00

Pos logit contributions
 Mill+0.024
 sorts+0.024
 Joey+0.023
neath+0.022
 unst+0.022
Neg logit contributions
 aids-0.021
 wig-0.021
 hair-0.020
 jokes-0.020
 song-0.018
Token a
Token ID257
Feature activation-4.68e-01

Pos logit contributions
 Mill+0.380
 sorts+0.374
 Joey+0.358
neath+0.352
 scaven+0.350
Neg logit contributions
 aids-0.358
 hair-0.350
 wig-0.343
 jokes-0.337
 song-0.313
Token hat
Token ID6877
Feature activation+3.57e+00

Pos logit contributions
 sorts+0.034
 Mill+0.034
 scaven+0.032
 Joey+0.032
 unst+0.031
Neg logit contributions
 aids-0.030
 wig-0.028
 jokes-0.027
 hair-0.027
 cheeks-0.025
Token as
Token ID355
Feature activation+3.33e+00

Pos logit contributions
 aids+0.237
 wig+0.231
 hair+0.226
 jokes+0.219
 song+0.209
Neg logit contributions
 Mill-0.254
 sorts-0.254
 Joey-0.239
neath-0.234
 scaven-0.233
Token the
Token ID262
Feature activation-6.46e-01

Pos logit contributions
 aids+0.212
 hair+0.205
 wig+0.204
 jokes+0.200
 song+0.188
Neg logit contributions
 Mill-0.245
 sorts-0.244
 Joey-0.230
neath-0.228
 scaven-0.224
Token wig
Token ID45678
Feature activation+1.07e+01

Pos logit contributions
 sorts+0.051
 Mill+0.051
 Joey+0.048
 scaven+0.047
 unst+0.047
Neg logit contributions
 aids-0.037
 wig-0.035
 hair-0.033
 jokes-0.033
ggie-0.030
Token.
Token ID13
Feature activation+3.06e-01

Pos logit contributions
 aids+0.753
 wig+0.726
 hair+0.695
 jokes+0.689
 song+0.655
Neg logit contributions
 Mill-0.709
 sorts-0.708
 Joey-0.659
 unst-0.647
neath-0.646
Token They
Token ID1119
Feature activation-3.60e-01

Pos logit contributions
 aids+0.021
 wig+0.020
 hair+0.019
 jokes+0.019
 song+0.018
Neg logit contributions
 Mill-0.022
 sorts-0.021
 Joey-0.020
neath-0.020
 scaven-0.020
Token used
Token ID973
Feature activation-5.38e+00

Pos logit contributions
 Mill+0.026
 sorts+0.026
 Joey+0.025
neath+0.024
 unst+0.024
Neg logit contributions
 aids-0.023
 wig-0.023
 hair-0.022
 jokes-0.022
 song-0.020
Token a
Token ID257
Feature activation-4.85e-01

Pos logit contributions
 Mill+0.383
 sorts+0.379
 Joey+0.360
neath+0.353
 scaven+0.352
Neg logit contributions
 aids-0.359
 hair-0.349
 wig-0.347
 jokes-0.336
 song-0.314
Token scarf
Token ID36953
Feature activation+1.12e+00

Pos logit contributions
 sorts+0.035
 Mill+0.034
 scaven+0.032
 unst+0.032
 Joey+0.032
Neg logit contributions
 aids-0.031
 jokes-0.028
 wig-0.028
 hair-0.027
 cheeks-0.026
Token
Token ID198
Feature activation-2.52e-01

Pos logit contributions
 Mill+0.018
 sorts+0.018
 Joey+0.017
neath+0.016
 scaven+0.016
Neg logit contributions
 aids-0.017
 wig-0.016
 hair-0.016
 jokes-0.015
 song-0.014
TokenThey
Token ID2990
Feature activation+7.32e-01

Pos logit contributions
 sorts+0.017
 Mill+0.016
neath+0.015
 scaven+0.015
 Joey+0.015
Neg logit contributions
 aids-0.018
 wig-0.017
 hair-0.017
 jokes-0.016
 cheeks-0.016
Token both
Token ID1111
Feature activation-9.64e-02

Pos logit contributions
 aids+0.044
 wig+0.044
 hair+0.043
 jokes+0.041
 cheeks+0.038
Neg logit contributions
 Mill-0.057
 sorts-0.057
 Joey-0.054
 unst-0.051
neath-0.051
Token grab
Token ID5552
Feature activation+1.02e-01

Pos logit contributions
 sorts+0.007
 Mill+0.007
 Joey+0.006
neath+0.006
 scaven+0.006
Neg logit contributions
 aids-0.007
 wig-0.006
 hair-0.006
 jokes-0.006
 song-0.006
Token the
Token ID262
Feature activation-6.54e-01

Pos logit contributions
 aids+0.007
 hair+0.007
 wig+0.007
 jokes+0.007
 song+0.006
Neg logit contributions
 Mill-0.007
 sorts-0.007
 Joey-0.006
 scaven-0.006
neath-0.006
Token wig
Token ID45678
Feature activation+1.07e+01

Pos logit contributions
 sorts+0.045
 unst+0.043
ucer+0.042
 aback+0.041
erek+0.041
Neg logit contributions
 aids-0.044
 jokes-0.037
agged-0.035
 cheeks-0.034
 Dancing-0.034
Token and
Token ID290
Feature activation-3.32e-01

Pos logit contributions
 aids+0.710
 wig+0.692
 hair+0.675
 jokes+0.653
 song+0.622
Neg logit contributions
 Mill-0.759
 sorts-0.757
 Joey-0.713
neath-0.697
 scaven-0.694
Token pull
Token ID2834
Feature activation-1.39e+00

Pos logit contributions
 sorts+0.023
 Mill+0.023
neath+0.022
 Joey+0.021
 unst+0.021
Neg logit contributions
 aids-0.023
 wig-0.021
 jokes-0.020
 hair-0.020
 song-0.020
Token it
Token ID340
Feature activation-1.26e+00

Pos logit contributions
 Mill+0.092
 sorts+0.090
 Joey+0.084
 scaven+0.084
neath+0.080
Neg logit contributions
 hair-0.103
 aids-0.102
 wig-0.100
 jokes-0.096
 song-0.091
Token hard
Token ID1327
Feature activation-2.65e+00

Pos logit contributions
 sorts+0.069
 Mill+0.068
 unst+0.064
 Joey+0.062
neath+0.062
Neg logit contributions
 aids-0.105
 wig-0.102
 hair-0.097
 jokes-0.097
 cheeks-0.093
Token.
Token ID13
Feature activation+2.70e-01

Pos logit contributions
 sorts+0.194
 Mill+0.193
 Joey+0.182
neath+0.178
 scaven+0.177
Neg logit contributions
 aids-0.172
 wig-0.166
 hair-0.160
 jokes-0.156
 song-0.148
Token pull
Token ID2834
Feature activation-1.39e+00

Pos logit contributions
 sorts+0.023
 Mill+0.023
neath+0.022
 Joey+0.021
 unst+0.021
Neg logit contributions
 aids-0.023
 wig-0.021
 jokes-0.020
 hair-0.020
 song-0.020
Token it
Token ID340
Feature activation-1.26e+00

Pos logit contributions
 Mill+0.092
 sorts+0.090
 Joey+0.084
 scaven+0.084
neath+0.080
Neg logit contributions
 hair-0.103
 aids-0.102
 wig-0.100
 jokes-0.096
 song-0.091
Token hard
Token ID1327
Feature activation-2.65e+00

Pos logit contributions
 sorts+0.069
 Mill+0.068
 unst+0.064
 Joey+0.062
neath+0.062
Neg logit contributions
 aids-0.105
 wig-0.102
 hair-0.097
 jokes-0.097
 cheeks-0.093
Token.
Token ID13
Feature activation+2.70e-01

Pos logit contributions
 sorts+0.194
 Mill+0.193
 Joey+0.182
neath+0.178
 scaven+0.177
Neg logit contributions
 aids-0.172
 wig-0.166
 hair-0.160
 jokes-0.156
 song-0.148
Token The
Token ID383
Feature activation+1.42e+00

Pos logit contributions
 wig+0.022
 aids+0.020
agging+0.019
 song+0.019
 jokes+0.019
Neg logit contributions
 Mill-0.016
neath-0.016
 sorts-0.015
 Joey-0.015
 scaven-0.014
Token wig
Token ID45678
Feature activation+1.06e+01

Pos logit contributions
 aids+0.080
agged+0.066
ggie+0.059
anna+0.058
 jokes+0.058
Neg logit contributions
 sorts-0.099
 supplies-0.095
ucer-0.095
erek-0.094
 box-0.094
Token is
Token ID318
Feature activation-4.80e-01

Pos logit contributions
 aids+0.821
 wig+0.781
 song+0.739
 jokes+0.736
ggie+0.726
Neg logit contributions
 sorts-0.614
neath-0.583
 unst-0.565
'll-0.551
 scaven-0.549
Token old
Token ID1468
Feature activation-1.95e+00

Pos logit contributions
 unst+0.030
 sorts+0.026
 Mill+0.026
 deeper+0.026
 Joey+0.026
Neg logit contributions
 aids-0.037
 wig-0.034
 Dancing-0.031
 cheeks-0.031
 jokes-0.031
Token and
Token ID290
Feature activation-3.61e-01

Pos logit contributions
 sorts+0.128
 Mill+0.125
 Joey+0.117
 scaven+0.116
 unst+0.115
Neg logit contributions
 aids-0.142
 wig-0.134
 jokes-0.128
 hair-0.128
 song-0.121
Token weak
Token ID4939
Feature activation-8.16e-01

Pos logit contributions
 sorts+0.025
 Mill+0.025
 unst+0.024
 Joey+0.023
neath+0.023
Neg logit contributions
 aids-0.025
 wig-0.023
 jokes-0.022
ggie-0.022
 hair-0.021
Token.
Token ID13
Feature activation+2.37e-01

Pos logit contributions
 sorts+0.053
 Mill+0.051
 Joey+0.048
 unst+0.048
 scaven+0.048
Neg logit contributions
 aids-0.059
 wig-0.057
 jokes-0.053
 hair-0.053
ggie-0.051
Token black
Token ID2042
Feature activation+3.82e+00

Pos logit contributions
 Mill+0.035
 sorts+0.033
 scaven+0.033
 Joey+0.032
 unst+0.031
Neg logit contributions
 aids-0.038
 jokes-0.034
agged-0.033
 wig-0.032
 hair-0.031
Token robe
Token ID33192
Feature activation+4.94e+00

Pos logit contributions
 aids+0.239
 jokes+0.212
ggie+0.206
 Dancing+0.199
 wig+0.191
Neg logit contributions
 Mill-0.269
 sorts-0.267
 Joey-0.251
 extingu-0.249
 scaven-0.248
Token and
Token ID290
Feature activation-3.57e-01

Pos logit contributions
 aids+0.405
 jokes+0.382
 wig+0.373
 Dancing+0.355
 song+0.355
Neg logit contributions
 sorts-0.255
 Mill-0.249
neath-0.237
pling-0.236
 scaven-0.231
Token a
Token ID257
Feature activation-5.32e-01

Pos logit contributions
 Mill+0.019
 sorts+0.018
 Joey+0.017
neath+0.017
 scaven+0.016
Neg logit contributions
 aids-0.030
agging-0.028
 wig-0.028
 jokes-0.027
 song-0.027
Token white
Token ID2330
Feature activation+2.57e+00

Pos logit contributions
 Mill+0.035
 shed+0.033
 scaven+0.032
 sorts+0.031
pling+0.031
Neg logit contributions
 aids-0.037
agged-0.034
 jokes-0.033
ggie-0.031
agging-0.030
Token wig
Token ID45678
Feature activation+1.06e+01

Pos logit contributions
 aids+0.166
 jokes+0.147
ggie+0.141
 Dancing+0.140
agged+0.138
Neg logit contributions
 Mill-0.179
 sorts-0.165
 extingu-0.163
 barrel-0.162
 shed-0.162
Token.
Token ID13
Feature activation+2.44e-01

Pos logit contributions
 aids+0.836
 jokes+0.772
 wig+0.759
 hair+0.728
 song+0.723
Neg logit contributions
 Mill-0.593
 sorts-0.589
pling-0.553
neath-0.548
 unst-0.542
Token He
Token ID679
Feature activation+4.32e-01

Pos logit contributions
 aids+0.016
 wig+0.016
 hair+0.015
 jokes+0.015
 song+0.014
Neg logit contributions
 Mill-0.018
 sorts-0.017
 Joey-0.017
neath-0.016
 unst-0.016
Token was
Token ID373
Feature activation-4.12e-01

Pos logit contributions
 aids+0.034
 wig+0.032
agging+0.031
 hair+0.031
 jokes+0.031
Neg logit contributions
 Mill-0.026
 sorts-0.025
 Joey-0.024
 scaven-0.023
neath-0.023
Token a
Token ID257
Feature activation-5.59e-01

Pos logit contributions
 Mill+0.027
 Joey+0.025
 sorts+0.025
 Wil+0.023
 Bobby+0.023
Neg logit contributions
 aids-0.029
 cheeks-0.027
 wig-0.027
 song-0.026
 jokes-0.026
Token judge
Token ID5052
Feature activation+2.90e+00

Pos logit contributions
 Mill+0.037
 scaven+0.036
 sorts+0.036
 Joey+0.034
 unst+0.033
Neg logit contributions
 aids-0.040
agged-0.037
 jokes-0.034
 cheeks-0.033
agging-0.033
Token each
Token ID1123
Feature activation+1.07e-01

Pos logit contributions
 Mill+0.021
 sorts+0.021
 Joey+0.020
 scaven+0.019
neath+0.019
Neg logit contributions
 aids-0.030
 wig-0.029
 hair-0.029
 jokes-0.028
 song-0.027
Token have
Token ID423
Feature activation+2.15e+00

Pos logit contributions
 aids+0.008
 wig+0.008
 jokes+0.007
 hair+0.007
 cheeks+0.007
Neg logit contributions
 sorts-0.007
 Mill-0.006
 unst-0.006
 Joey-0.006
neath-0.006
Token half
Token ID2063
Feature activation-2.63e+00

Pos logit contributions
 aids+0.150
 wig+0.145
 hair+0.137
 jokes+0.137
 song+0.131
Neg logit contributions
 sorts-0.147
 Mill-0.145
 Joey-0.135
 unst-0.134
 scaven-0.133
Token of
Token ID286
Feature activation+1.37e-01

Pos logit contributions
 sorts+0.173
 Mill+0.171
 Joey+0.162
 unst+0.160
 scaven+0.157
Neg logit contributions
 aids-0.190
 wig-0.180
 jokes-0.172
 hair-0.169
 song-0.164
Token the
Token ID262
Feature activation-7.59e-01

Pos logit contributions
 aids+0.010
 wig+0.010
 hair+0.009
 jokes+0.009
 song+0.009
Neg logit contributions
 sorts-0.009
 Mill-0.009
 Joey-0.008
neath-0.008
 scaven-0.008
Token wig
Token ID45678
Feature activation+1.05e+01

Pos logit contributions
 sorts+0.057
 supplies+0.053
 unst+0.052
 treasures+0.051
 hed+0.051
Neg logit contributions
 aids-0.043
agged-0.036
ggie-0.034
 jokes-0.034
Her-0.033
Token in
Token ID287
Feature activation+1.60e+00

Pos logit contributions
 aids+0.713
 wig+0.693
 hair+0.660
 jokes+0.652
 song+0.618
Neg logit contributions
 sorts-0.738
 Mill-0.731
 Joey-0.683
 unst-0.672
neath-0.672
Token their
Token ID511
Feature activation+6.12e-01

Pos logit contributions
 aids+0.114
 wig+0.111
 hair+0.108
 jokes+0.106
 song+0.100
Neg logit contributions
 sorts-0.107
 Mill-0.107
 Joey-0.100
neath-0.097
 scaven-0.096
Token hands
Token ID2832
Feature activation+1.70e+00

Pos logit contributions
 aids+0.044
bee+0.042
agging+0.040
ggie+0.040
 jokes+0.039
Neg logit contributions
 sorts-0.036
 shed-0.033
 unst-0.032
 scaven-0.031
 supplies-0.030
Token.
Token ID13
Feature activation+1.70e-01

Pos logit contributions
 aids+0.124
 wig+0.120
 jokes+0.112
 hair+0.112
ggie+0.106
Neg logit contributions
 sorts-0.110
 Mill-0.108
 Joey-0.102
neath-0.099
 unst-0.099
Token
Token ID198
Feature activation-3.92e-01

Pos logit contributions
 wig+0.014
 aids+0.014
 jokes+0.013
agging+0.013
ggie+0.013
Neg logit contributions
 Mill-0.010
 sorts-0.009
 Joey-0.009
neath-0.009
 aback-0.008
Token red
Token ID2266
Feature activation+3.03e+00

Pos logit contributions
 sorts+0.067
 Mill+0.066
 Joey+0.062
 scaven+0.061
 unst+0.060
Neg logit contributions
 aids-0.050
 wig-0.044
 jokes-0.044
ggie-0.042
 hair-0.042
Token nose
Token ID9686
Feature activation+4.32e+00

Pos logit contributions
 aids+0.193
 jokes+0.167
ggie+0.157
 Dancing+0.154
 wig+0.154
Neg logit contributions
 Mill-0.219
 sorts-0.218
 Joey-0.207
 scaven-0.202
neath-0.202
Token,
Token ID11
Feature activation-3.53e-01

Pos logit contributions
 aids+0.348
 wig+0.328
 jokes+0.326
 hair+0.303
 song+0.301
Neg logit contributions
 Mill-0.230
 sorts-0.228
 Joey-0.216
neath-0.216
 unst-0.213
Token a
Token ID257
Feature activation-6.15e-01

Pos logit contributions
 Mill+0.022
 Joey+0.020
 sorts+0.020
neath+0.019
 unst+0.019
Neg logit contributions
 aids-0.027
 wig-0.024
ggie-0.023
 jokes-0.023
agging-0.023
Token colorful
Token ID20239
Feature activation-1.68e-01

Pos logit contributions
 Mill+0.042
 sorts+0.039
 Joey+0.039
 scaven+0.038
 unst+0.037
Neg logit contributions
 aids-0.042
agged-0.038
 jokes-0.037
ggie-0.034
agging-0.034
Token wig
Token ID45678
Feature activation+1.05e+01

Pos logit contributions
 Mill+0.012
 sorts+0.011
 Joey+0.011
 scaven+0.011
 shed+0.010
Neg logit contributions
 aids-0.011
 jokes-0.010
agged-0.009
ggie-0.009
 Dancing-0.009
Token,
Token ID11
Feature activation-3.69e-01

Pos logit contributions
 aids+0.873
 jokes+0.812
 wig+0.788
 song+0.771
 hair+0.745
Neg logit contributions
 Mill-0.565
 sorts-0.539
pling-0.518
 Joey-0.512
neath-0.507
Token and
Token ID290
Feature activation-4.53e-01

Pos logit contributions
 Mill+0.019
 Joey+0.018
neath+0.018
 sorts+0.017
 unst+0.017
Neg logit contributions
 aids-0.031
 wig-0.028
 jokes-0.028
ggie-0.027
agging-0.027
Token a
Token ID257
Feature activation-6.21e-01

Pos logit contributions
 Mill+0.027
 sorts+0.027
 Joey+0.025
neath+0.024
 scaven+0.023
Neg logit contributions
 aids-0.035
 wig-0.034
 jokes-0.032
agging-0.031
 hair-0.031
Token huge
Token ID3236
Feature activation-1.55e+00

Pos logit contributions
 Mill+0.043
 sorts+0.042
 Joey+0.040
 scaven+0.039
 unst+0.039
Neg logit contributions
 aids-0.040
agged-0.037
 jokes-0.035
ggie-0.034
agging-0.034
Token bow
Token ID9563
Feature activation-1.01e+00

Pos logit contributions
 Mill+0.121
 sorts+0.120
 Joey+0.115
 scaven+0.110
 unst+0.109
Neg logit contributions
 aids-0.089
agged-0.076
ggie-0.075
 jokes-0.074
Her-0.072
TokenHey
Token ID10814
Feature activation+1.63e+00

Pos logit contributions
 sorts+0.026
 Mill+0.025
neath+0.025
 unst+0.023
 Joey+0.023
Neg logit contributions
 aids-0.039
 wig-0.037
 hair-0.037
 jokes-0.037
 cheeks-0.035
Token,
Token ID11
Feature activation-3.93e-01

Pos logit contributions
 aids+0.117
 wig+0.111
 hair+0.108
 jokes+0.106
 song+0.101
Neg logit contributions
 Mill-0.109
 sorts-0.108
 Joey-0.103
 scaven-0.099
neath-0.099
Token you
Token ID345
Feature activation-9.65e-01

Pos logit contributions
 Mill+0.027
 sorts+0.027
 Joey+0.026
neath+0.025
 scaven+0.025
Neg logit contributions
 aids-0.027
 wig-0.026
 hair-0.025
 jokes-0.025
 song-0.024
Token broke
Token ID6265
Feature activation-1.73e+00

Pos logit contributions
 sorts+0.078
 Mill+0.077
 Joey+0.072
neath+0.070
wood+0.069
Neg logit contributions
 wig-0.057
 aids-0.057
 hair-0.056
 jokes-0.054
 cheeks-0.049
Token the
Token ID262
Feature activation-8.19e-01

Pos logit contributions
 sorts+0.114
 Mill+0.112
 Joey+0.103
 scaven+0.102
neath+0.101
Neg logit contributions
 wig-0.126
 hair-0.125
 aids-0.125
 jokes-0.117
 song-0.111
Token wig
Token ID45678
Feature activation+1.05e+01

Pos logit contributions
 sorts+0.064
 unst+0.062
ucer+0.060
 scaven+0.060
 hed+0.060
Neg logit contributions
 aids-0.044
agged-0.036
 jokes-0.035
ggie-0.033
 Dancing-0.032
Token!"
Token ID2474
Feature activation-3.21e+00

Pos logit contributions
 aids+0.974
 wig+0.962
 hair+0.957
 jokes+0.913
 song+0.899
Neg logit contributions
 Mill-0.474
 sorts-0.468
 Joey-0.437
neath-0.419
 scaven-0.401
Token Anna
Token ID11735
Feature activation+4.57e+00

Pos logit contributions
 Mill+0.245
 Joey+0.235
 sorts+0.232
neath+0.222
 Bobby+0.220
Neg logit contributions
 wig-0.200
agging-0.190
 aids-0.186
 song-0.172
ggie-0.172
Token says
Token ID1139
Feature activation+3.59e-01

Pos logit contributions
 aids+0.314
 wig+0.306
 hair+0.283
 jokes+0.280
 song+0.276
Neg logit contributions
 sorts-0.315
 Mill-0.307
 Joey-0.288
 aback-0.285
neath-0.285
Token.
Token ID13
Feature activation+1.17e-01

Pos logit contributions
 aids+0.031
 wig+0.031
 jokes+0.028
 clown+0.027
ggie+0.027
Neg logit contributions
 unst-0.018
 Mill-0.018
 Joey-0.016
 aback-0.016
 sorts-0.015
Token "
Token ID366
Feature activation+1.76e-01

Pos logit contributions
 aids+0.009
 wig+0.009
 jokes+0.008
ggie+0.008
 haircut+0.008
Neg logit contributions
 Mill-0.007
neath-0.007
 sorts-0.007
 Joey-0.007
 aback-0.007
TokenNo
Token ID2949
Feature activation+2.79e+00

Pos logit contributions
neath+0.035
 sorts+0.035
 unst+0.034
 aback+0.033
 Mill+0.033
Neg logit contributions
 aids-0.042
 hair-0.037
 jokes-0.037
 cheeks-0.037
 wig-0.036
Token,
Token ID11
Feature activation-5.00e-01

Pos logit contributions
 aids+0.224
 wig+0.205
 hair+0.199
 jokes+0.193
 Dancing+0.190
Neg logit contributions
 Mill-0.168
 sorts-0.163
 Joey-0.157
 scaven-0.151
 unst-0.148
Token you
Token ID345
Feature activation-1.08e+00

Pos logit contributions
 Mill+0.024
 Joey+0.024
 unst+0.023
 sorts+0.022
neath+0.021
Neg logit contributions
 aids-0.042
agged-0.040
agging-0.039
 hair-0.038
 wig-0.037
Token broke
Token ID6265
Feature activation-1.84e+00

Pos logit contributions
 Mill+0.071
 sorts+0.070
 Joey+0.065
neath+0.062
 scaven+0.061
Neg logit contributions
 wig-0.080
 hair-0.079
 aids-0.079
 jokes-0.076
 cheeks-0.071
Token the
Token ID262
Feature activation-9.21e-01

Pos logit contributions
 sorts+0.113
 Mill+0.112
 Joey+0.104
neath+0.102
 scaven+0.101
Neg logit contributions
 aids-0.141
 wig-0.138
 hair-0.135
 jokes-0.131
 song-0.125
Token wig
Token ID45678
Feature activation+1.04e+01

Pos logit contributions
 sorts+0.077
 unst+0.073
ucer+0.073
 supplies+0.071
 hed+0.071
Neg logit contributions
 aids-0.045
agged-0.034
 jokes-0.033
 Dancing-0.031
ggie-0.031
Token!"
Token ID2474
Feature activation-3.32e+00

Pos logit contributions
 aids+0.913
 wig+0.902
 hair+0.890
 jokes+0.857
 song+0.833
Neg logit contributions
 Mill-0.521
 sorts-0.517
 Joey-0.476
neath-0.463
 scaven-0.450
Token Ben
Token ID3932
Feature activation-5.67e-01

Pos logit contributions
 Mill+0.219
 Joey+0.210
neath+0.201
 sorts+0.195
 Bobby+0.191
Neg logit contributions
 wig-0.243
 aids-0.239
 song-0.223
ggie-0.216
agging-0.212
Token says
Token ID1139
Feature activation+2.48e-01

Pos logit contributions
 aback+0.026
 sorts+0.025
 unst+0.022
'll+0.021
 hed+0.021
Neg logit contributions
 aids-0.050
 wig-0.049
ggie-0.046
 song-0.046
agged-0.045
Token.
Token ID13
Feature activation+1.91e-02

Pos logit contributions
 wig+0.023
 aids+0.023
 blond+0.021
 jokes+0.021
ggie+0.021
Neg logit contributions
 unst-0.011
 Mill-0.010
 aback-0.009
 Joey-0.009
 deeper-0.009
Token "
Token ID366
Feature activation+6.55e-02

Pos logit contributions
 wig+0.002
 aids+0.002
 haircut+0.002
 hair+0.002
ggie+0.002
Neg logit contributions
 Mill-0.001
 Joey-0.001
 aback-0.001
 sorts-0.001
 handy-0.001
Token.
Token ID13
Feature activation+4.41e-01

Pos logit contributions
 Mill+0.160
 sorts+0.159
 Joey+0.150
 scaven+0.146
 unst+0.145
Neg logit contributions
 aids-0.155
 wig-0.152
 hair-0.145
 jokes-0.141
 song-0.134
Token She
Token ID1375
Feature activation-6.04e-01

Pos logit contributions
 aids+0.024
 hair+0.023
 wig+0.023
 jokes+0.022
 cheeks+0.020
Neg logit contributions
 sorts-0.036
 Mill-0.035
 scaven-0.033
neath-0.033
 unst-0.033
Token told
Token ID1297
Feature activation-7.84e-02

Pos logit contributions
 sorts+0.042
 Mill+0.042
 Joey+0.040
neath+0.039
 scaven+0.039
Neg logit contributions
 aids-0.041
 wig-0.040
 hair-0.039
 jokes-0.038
 song-0.036
Token him
Token ID683
Feature activation-2.30e+00

Pos logit contributions
 Mill+0.004
 sorts+0.004
 Joey+0.004
neath+0.004
 scaven+0.004
Neg logit contributions
 aids-0.007
 wig-0.006
 hair-0.006
 jokes-0.006
 song-0.006
Token silly
Token ID14397
Feature activation+3.42e+00

Pos logit contributions
 Mill+0.163
 sorts+0.159
 Joey+0.154
 scaven+0.146
 unst+0.145
Neg logit contributions
 aids-0.153
 wig-0.152
 hair-0.143
 jokes-0.138
 song-0.134
Token jokes
Token ID14532
Feature activation+1.02e+01

Pos logit contributions
 aids+0.173
 wig+0.168
 hair+0.153
ggie+0.143
agged+0.141
Neg logit contributions
 sorts-0.295
 Mill-0.293
 Joey-0.286
 scaven-0.266
wood-0.264
Token and
Token ID290
Feature activation-1.75e-01

Pos logit contributions
 aids+0.669
 wig+0.648
 hair+0.632
 jokes+0.621
 song+0.587
Neg logit contributions
 Mill-0.738
 sorts-0.734
 Joey-0.690
neath-0.680
 scaven-0.676
Token talked
Token ID6619
Feature activation+4.77e+00

Pos logit contributions
 sorts+0.012
 Mill+0.012
 Joey+0.012
 scaven+0.011
neath+0.011
Neg logit contributions
 aids-0.012
 wig-0.011
 hair-0.011
 jokes-0.011
 song-0.010
Token about
Token ID546
Feature activation+3.84e+00

Pos logit contributions
 aids+0.308
 wig+0.296
 hair+0.292
 jokes+0.287
 song+0.271
Neg logit contributions
 Mill-0.349
 sorts-0.348
 Joey-0.327
neath-0.324
 scaven-0.320
Token all
Token ID477
Feature activation-2.52e+00

Pos logit contributions
 aids+0.260
 jokes+0.252
 wig+0.251
 hair+0.249
 song+0.231
Neg logit contributions
 sorts-0.265
 Mill-0.265
neath-0.249
 unst-0.245
 Joey-0.243
Token the
Token ID262
Feature activation-5.16e-01

Pos logit contributions
 Mill+0.166
 sorts+0.159
 scaven+0.155
 unst+0.155
neath+0.153
Neg logit contributions
 aids-0.180
 wig-0.169
 hair-0.169
 jokes-0.169
 song-0.158
Token this
Token ID428
Feature activation-8.82e-01

Pos logit contributions
 aids+0.140
 wig+0.133
 hair+0.132
 jokes+0.130
 song+0.122
Neg logit contributions
 sorts-0.149
 Mill-0.148
neath-0.139
 Joey-0.137
 scaven-0.135
Token power
Token ID1176
Feature activation-2.20e+00

Pos logit contributions
 sorts+0.057
 Mill+0.057
 Joey+0.053
neath+0.051
 scaven+0.051
Neg logit contributions
 aids-0.065
 wig-0.063
 hair-0.061
 jokes-0.060
 song-0.057
Token would
Token ID561
Feature activation-1.66e+00

Pos logit contributions
 Mill+0.148
 sorts+0.144
 Joey+0.138
 scaven+0.136
neath+0.135
Neg logit contributions
 aids-0.154
 hair-0.146
 jokes-0.144
 wig-0.143
 song-0.139
Token come
Token ID1282
Feature activation-5.55e-01

Pos logit contributions
 sorts+0.138
 Mill+0.136
neath+0.131
 scaven+0.130
 Joey+0.129
Neg logit contributions
 aids-0.088
 wig-0.082
 jokes-0.082
 hair-0.081
 song-0.079
Token in
Token ID287
Feature activation+1.33e+00

Pos logit contributions
 sorts+0.039
 Mill+0.036
 scaven+0.035
neath+0.035
 Joey+0.034
Neg logit contributions
 aids-0.038
 hair-0.037
 jokes-0.035
 wig-0.035
 song-0.034
Token handy
Token ID15728
Feature activation-1.29e+01

Pos logit contributions
 hair+0.071
 aids+0.070
 jokes+0.064
 wig+0.062
 song+0.061
Neg logit contributions
pling-0.105
 sorts-0.104
aved-0.104
 Mill-0.104
ucer-0.104
Token.
Token ID13
Feature activation+5.53e-03

Pos logit contributions
 Mill+0.915
 sorts+0.914
 Joey+0.858
neath+0.842
 scaven+0.837
Neg logit contributions
 aids-0.856
 wig-0.829
 hair-0.811
 jokes-0.787
 song-0.749
Token
Token ID220
Feature activation+1.81e-01

Pos logit contributions
 aids+0.000
 hair+0.000
 wig+0.000
 jokes+0.000
 Dancing+0.000
Neg logit contributions
 sorts-0.000
 Mill-0.000
 unst-0.000
 scaven-0.000
neath-0.000
Token
Token ID198
Feature activation-4.81e-01

Pos logit contributions
 aids+0.010
 hair+0.009
 wig+0.008
 jokes+0.008
 Dancing+0.008
Neg logit contributions
 sorts-0.015
 Mill-0.015
 scaven-0.014
 unst-0.014
neath-0.014
TokenHe
Token ID1544
Feature activation+5.10e-01

Pos logit contributions
 sorts+0.036
 Mill+0.036
 unst+0.034
neath+0.034
 scaven+0.034
Neg logit contributions
 aids-0.030
 wig-0.028
 hair-0.027
 jokes-0.027
ggie-0.025
Token was
Token ID373
Feature activation-5.10e-01

Pos logit contributions
 aids+0.035
 wig+0.034
 hair+0.034
 jokes+0.033
 song+0.031
Neg logit contributions
 Mill-0.035
 sorts-0.035
 Joey-0.033
neath-0.032
 unst-0.032
Token a
Token ID257
Feature activation-1.02e+00

Pos logit contributions
 sorts+0.177
 Mill+0.175
 Joey+0.163
 scaven+0.154
neath+0.152
Neg logit contributions
 aids-0.264
 wig-0.253
 hair-0.239
 cheeks-0.238
 jokes-0.235
Token time
Token ID640
Feature activation+4.04e+00

Pos logit contributions
 scaven+0.081
 sorts+0.080
 Mill+0.078
 Joey+0.075
 unst+0.071
Neg logit contributions
 aids-0.061
 wig-0.058
 hair-0.053
 jokes-0.052
 cheeks-0.051
Token there
Token ID612
Feature activation-3.26e-01

Pos logit contributions
 aids+0.210
 wig+0.207
 hair+0.207
 jokes+0.193
 cheeks+0.183
Neg logit contributions
 sorts-0.343
 Mill-0.316
neath-0.310
 scaven-0.306
 unst-0.305
Token was
Token ID373
Feature activation-7.04e-01

Pos logit contributions
 sorts+0.025
 Mill+0.024
 scaven+0.023
 unst+0.023
wood+0.023
Neg logit contributions
 hair-0.019
 aids-0.018
 wig-0.018
ggie-0.017
 jokes-0.017
Token a
Token ID257
Feature activation-7.85e-01

Pos logit contributions
 Mill+0.048
 sorts+0.047
 Joey+0.045
neath+0.043
 scaven+0.043
Neg logit contributions
 aids-0.050
 wig-0.049
 hair-0.047
 jokes-0.046
 song-0.044
Token handy
Token ID15728
Feature activation-1.28e+01

Pos logit contributions
 Mill+0.056
 sorts+0.054
 scaven+0.053
 Joey+0.053
 unst+0.049
Neg logit contributions
 aids-0.055
 wig-0.048
 jokes-0.047
 hair-0.047
 cheeks-0.045
Token man
Token ID582
Feature activation-1.21e+00

Pos logit contributions
 Mill+0.909
 sorts+0.899
 Joey+0.842
 scaven+0.805
pling+0.789
Neg logit contributions
 aids-0.867
 wig-0.828
 hair-0.809
 jokes-0.790
 cheeks-0.734
Token who
Token ID508
Feature activation+1.72e+00

Pos logit contributions
 sorts+0.080
 Mill+0.079
 Joey+0.074
 scaven+0.070
pling+0.070
Neg logit contributions
 aids-0.089
 wig-0.083
 jokes-0.082
 hair-0.080
 cheeks-0.079
Token had
Token ID550
Feature activation+9.96e-01

Pos logit contributions
 aids+0.098
 hair+0.096
 wig+0.095
 jokes+0.088
ggie+0.088
Neg logit contributions
 Mill-0.133
 Joey-0.127
 sorts-0.126
 unst-0.124
neath-0.124
Token a
Token ID257
Feature activation-6.29e-01

Pos logit contributions
 aids+0.076
 wig+0.073
 jokes+0.069
 hair+0.069
 cheeks+0.066
Neg logit contributions
 Mill-0.063
 sorts-0.062
 Joey-0.059
 scaven-0.057
neath-0.057
Token fancy
Token ID14996
Feature activation+1.73e+00

Pos logit contributions
 sorts+0.046
 Mill+0.046
 Joey+0.043
neath+0.042
 scaven+0.042
Neg logit contributions
 aids-0.041
 wig-0.040
 hair-0.039
 jokes-0.038
 song-0.036
Token.
Token ID13
Feature activation+8.21e-02

Pos logit contributions
 Mill+0.114
 sorts+0.114
 Joey+0.107
neath+0.106
 scaven+0.104
Neg logit contributions
 aids-0.108
 wig-0.105
 hair-0.103
 jokes-0.100
 song-0.096
Token The
Token ID383
Feature activation+1.24e+00

Pos logit contributions
 aids+0.005
 wig+0.005
 hair+0.005
 jokes+0.005
 song+0.005
Neg logit contributions
 sorts-0.006
 Mill-0.006
 Joey-0.006
neath-0.006
 scaven-0.006
Token cart
Token ID6383
Feature activation-1.03e+00

Pos logit contributions
 aids+0.087
 wig+0.081
 hair+0.076
 jokes+0.076
ggie+0.074
Neg logit contributions
 sorts-0.086
 Mill-0.085
 Joey-0.082
 unst-0.082
 scaven-0.080
Token came
Token ID1625
Feature activation+6.46e-01

Pos logit contributions
 Mill+0.071
 sorts+0.070
 Joey+0.067
neath+0.065
 scaven+0.064
Neg logit contributions
 aids-0.071
 wig-0.069
 hair-0.068
 jokes-0.065
 song-0.062
Token in
Token ID287
Feature activation+1.50e+00

Pos logit contributions
 hair+0.047
 aids+0.045
 wig+0.044
 jokes+0.043
 song+0.043
Neg logit contributions
 sorts-0.042
 Mill-0.040
neath-0.036
 Joey-0.036
pling-0.036
Token handy
Token ID15728
Feature activation-1.27e+01

Pos logit contributions
 hair+0.081
 jokes+0.076
 song+0.073
 aids+0.073
 wig+0.072
Neg logit contributions
pling-0.124
 Mill-0.123
ucer-0.121
aved-0.120
arp-0.118
Token to
Token ID284
Feature activation+8.28e-01

Pos logit contributions
 sorts+0.842
 Mill+0.836
 Joey+0.778
 scaven+0.768
neath+0.746
Neg logit contributions
 aids-0.915
 wig-0.888
 hair-0.842
 jokes-0.831
 Dancing-0.784
Token carry
Token ID3283
Feature activation-2.64e+00

Pos logit contributions
 hair+0.051
 wig+0.050
 aids+0.050
 jokes+0.049
 song+0.048
Neg logit contributions
 sorts-0.059
 Mill-0.058
pling-0.057
neath-0.056
 aback-0.056
Token all
Token ID477
Feature activation-2.89e+00

Pos logit contributions
 haven+0.231
ll+0.229
 scaven+0.229
 Mill+0.228
pling+0.227
Neg logit contributions
 hair-0.134
 jokes-0.100
 songs-0.096
 tricks-0.095
 aids-0.094
Token of
Token ID286
Feature activation+1.89e-04

Pos logit contributions
 scaven+0.222
 Mill+0.218
aved+0.213
pling+0.209
neath+0.209
Neg logit contributions
 hair-0.163
 aids-0.163
 jokes-0.147
 song-0.145
 wig-0.143
Token the
Token ID262
Feature activation-9.11e-01

Pos logit contributions
 hair+0.000
 jokes+0.000
 tricks+0.000
 wig+0.000
 aids+0.000
Neg logit contributions
aved-0.000
 awaits-0.000
rolley-0.000
ucer-0.000
 sorts-0.000
Token was
Token ID373
Feature activation-5.19e-01

Pos logit contributions
 aids+0.019
 wig+0.019
 hair+0.018
 jokes+0.018
 song+0.017
Neg logit contributions
 sorts-0.019
 Mill-0.019
 Joey-0.018
neath-0.018
 scaven-0.018
Token very
Token ID845
Feature activation+7.41e-01

Pos logit contributions
 sorts+0.032
 Mill+0.032
 unst+0.029
 Joey+0.029
 aback+0.028
Neg logit contributions
 wig-0.040
 aids-0.040
 jokes-0.038
 cheeks-0.037
 hair-0.037
Token happy
Token ID3772
Feature activation+9.96e-01

Pos logit contributions
 aids+0.050
 wig+0.050
 hair+0.047
 jokes+0.046
 cheeks+0.044
Neg logit contributions
 sorts-0.053
 Mill-0.053
 Joey-0.050
 unst-0.049
 aback-0.047
Token because
Token ID780
Feature activation+2.41e+00

Pos logit contributions
 aids+0.070
 wig+0.067
 hair+0.064
 jokes+0.063
 song+0.059
Neg logit contributions
 Mill-0.069
 sorts-0.069
 Joey-0.065
 scaven-0.063
neath-0.062
Token the
Token ID262
Feature activation-8.32e-01

Pos logit contributions
 hair+0.103
 aids+0.103
 jokes+0.097
 wig+0.095
 song+0.094
Neg logit contributions
aved-0.216
 scaven-0.211
 unst-0.210
 sorts-0.207
wood-0.207
Token handy
Token ID15728
Feature activation-1.27e+01

Pos logit contributions
 sorts+0.069
 Mill+0.067
 Joey+0.065
neath+0.063
aved+0.062
Neg logit contributions
 hair-0.046
 aids-0.045
 wig-0.044
 jokes-0.043
 song-0.042
Token man
Token ID582
Feature activation-1.18e+00

Pos logit contributions
 sorts+1.047
 Mill+1.045
 Joey+0.997
neath+0.977
 scaven+0.977
Neg logit contributions
 aids-0.702
 wig-0.675
 hair-0.654
 jokes-0.631
 song-0.604
Token had
Token ID550
Feature activation+9.63e-01

Pos logit contributions
 Mill+0.083
 sorts+0.083
 Joey+0.078
neath+0.076
 unst+0.076
Neg logit contributions
 aids-0.078
 wig-0.076
 hair-0.074
 jokes-0.072
 song-0.069
Token helped
Token ID4193
Feature activation-3.70e+00

Pos logit contributions
 aids+0.066
 hair+0.065
 wig+0.065
 jokes+0.063
 song+0.059
Neg logit contributions
 Mill-0.065
 sorts-0.064
neath-0.062
 Joey-0.061
 scaven-0.059
Token her
Token ID607
Feature activation+6.79e-01

Pos logit contributions
 sorts+0.249
 Mill+0.245
neath+0.232
 Joey+0.229
 scaven+0.226
Neg logit contributions
 aids-0.262
 wig-0.253
 hair-0.251
 jokes-0.245
 song-0.233
Token.
Token ID13
Feature activation+9.32e-02

Pos logit contributions
 aids+0.048
 hair+0.047
 wig+0.046
 jokes+0.045
 song+0.044
Neg logit contributions
 sorts-0.045
 Mill-0.045
 Joey-0.043
neath-0.042
 scaven-0.041
Token Maybe
Token ID6674
Feature activation-3.59e+00

Pos logit contributions
 aids+0.084
 wig+0.081
 hair+0.078
 jokes+0.076
 song+0.071
Neg logit contributions
 sorts-0.101
 Mill-0.100
 Joey-0.095
 scaven-0.093
neath-0.093
Token it
Token ID340
Feature activation-1.36e+00

Pos logit contributions
 sorts+0.255
 Mill+0.247
neath+0.232
 Joey+0.231
 scaven+0.231
Neg logit contributions
 wig-0.238
 aids-0.238
 hair-0.234
 jokes-0.225
 song-0.214
Token will
Token ID481
Feature activation-5.65e+00

Pos logit contributions
 Mill+0.097
 sorts+0.092
 Joey+0.091
keeping+0.084
 Suz+0.084
Neg logit contributions
 aids-0.090
 hair-0.088
 wig-0.085
 jokes-0.084
 song-0.078
Token come
Token ID1282
Feature activation-2.08e-01

Pos logit contributions
 sorts+0.472
 Mill+0.469
neath+0.447
 Joey+0.443
pling+0.441
Neg logit contributions
 aids-0.295
 hair-0.283
 wig-0.280
 jokes-0.276
 song-0.271
Token in
Token ID287
Feature activation+1.60e+00

Pos logit contributions
 sorts+0.016
 scaven+0.014
 Mill+0.014
 Joey+0.014
neath+0.014
Neg logit contributions
 hair-0.013
 song-0.012
 aids-0.012
 wig-0.012
 songs-0.011
Token handy
Token ID15728
Feature activation-1.26e+01

Pos logit contributions
 hair+0.089
 song+0.084
 aids+0.084
 jokes+0.080
 wig+0.078
Neg logit contributions
aved-0.123
 Mill-0.117
erek-0.117
pling-0.117
ucer-0.116
Token one
Token ID530
Feature activation+2.52e+00

Pos logit contributions
 sorts+0.689
 Mill+0.684
 Joey+0.628
 scaven+0.611
neath+0.604
Neg logit contributions
 aids-1.051
 wig-1.027
 hair-0.996
 jokes-0.978
 song-0.932
Token day
Token ID1110
Feature activation+9.33e-01

Pos logit contributions
 aids+0.180
 wig+0.176
 hair+0.172
 jokes+0.167
 song+0.161
Neg logit contributions
 Mill-0.168
 sorts-0.166
 Joey-0.156
neath-0.153
 scaven-0.151
Token!"
Token ID2474
Feature activation-3.17e+00

Pos logit contributions
 hair+0.063
 aids+0.063
 wig+0.062
 jokes+0.060
 song+0.059
Neg logit contributions
 sorts-0.062
 Mill-0.062
neath-0.059
 unst-0.058
 Joey-0.057
Token
Token ID220
Feature activation+3.09e-01

Pos logit contributions
 sorts+0.223
 Mill+0.221
 Joey+0.208
neath+0.205
 scaven+0.204
Neg logit contributions
 aids-0.214
 wig-0.209
 hair-0.205
 jokes-0.198
 song-0.189
Token
Token ID198
Feature activation-4.09e-01

Pos logit contributions
 aids+0.014
 hair+0.013
ggy+0.012
ggie+0.012
 Dancing+0.012
Neg logit contributions
 sorts-0.028
 Mill-0.026
 scaven-0.026
wood-0.025
neath-0.025
Token<|endoftext|>
Token ID50256
Feature activation+6.58e-01

Pos logit contributions
 aids+0.011
 hair+0.011
 Her+0.010
 Dancing+0.010
 His+0.010
Neg logit contributions
 sorts-0.020
aved-0.020
 unst-0.020
 scaven-0.020
 afloat-0.020
TokenGrand
Token ID23581
Feature activation-9.12e-01

Pos logit contributions
 aids+0.047
 hair+0.047
 wig+0.046
 Dancing+0.044
 jokes+0.043
Neg logit contributions
 sorts-0.040
 Mill-0.040
 unst-0.039
 scaven-0.037
 Joey-0.036
Tokenpa
Token ID8957
Feature activation-1.26e+00

Pos logit contributions
 Mill+0.052
 sorts+0.052
 Joey+0.048
neath+0.047
 scaven+0.046
Neg logit contributions
 aids-0.074
 wig-0.072
 hair-0.070
 jokes-0.069
 song-0.066
Token was
Token ID373
Feature activation-4.29e-01

Pos logit contributions
 sorts+0.099
 unst+0.098
 Mill+0.095
 aback+0.094
arp+0.094
Neg logit contributions
 hair-0.067
 wig-0.065
 jokes-0.064
 aids-0.064
 clown-0.062
Token a
Token ID257
Feature activation-5.86e-01

Pos logit contributions
 Mill+0.029
 sorts+0.028
 Joey+0.027
neath+0.026
 scaven+0.025
Neg logit contributions
 wig-0.030
 aids-0.030
 jokes-0.029
 cheeks-0.029
 song-0.028
Token handy
Token ID15728
Feature activation-1.26e+01

Pos logit contributions
 Mill+0.042
 sorts+0.041
 Joey+0.040
 scaven+0.039
neath+0.037
Neg logit contributions
 aids-0.041
 wig-0.037
 jokes-0.036
 hair-0.035
agged-0.035
Token man
Token ID582
Feature activation-1.07e+00

Pos logit contributions
 Mill+0.892
 sorts+0.887
 Joey+0.832
 scaven+0.798
neath+0.790
Neg logit contributions
 aids-0.852
 wig-0.825
 hair-0.802
 jokes-0.782
 cheeks-0.725
Token and
Token ID290
Feature activation-4.29e-01

Pos logit contributions
 sorts+0.073
 Mill+0.073
 Joey+0.068
neath+0.066
 scaven+0.066
Neg logit contributions
 aids-0.075
 wig-0.073
 hair-0.070
 jokes-0.069
 cheeks-0.065
Token he
Token ID339
Feature activation+6.37e-01

Pos logit contributions
 sorts+0.032
 Mill+0.032
 Joey+0.030
neath+0.030
 unst+0.030
Neg logit contributions
 aids-0.026
 wig-0.026
 hair-0.025
 jokes-0.024
 song-0.023
Token had
Token ID550
Feature activation+1.04e+00

Pos logit contributions
 aids+0.043
 wig+0.042
 hair+0.041
 jokes+0.040
 song+0.037
Neg logit contributions
 Mill-0.045
 sorts-0.044
 Joey-0.042
 unst-0.041
neath-0.041
Token lots
Token ID6041
Feature activation-6.08e+00

Pos logit contributions
 aids+0.074
 wig+0.072
 hair+0.069
 jokes+0.068
 song+0.065
Neg logit contributions
 sorts-0.070
 Mill-0.070
 Joey-0.066
neath-0.064
 scaven-0.064
Token is
Token ID318
Feature activation-4.94e-01

Pos logit contributions
 aids+0.314
 jokes+0.280
 hair+0.269
 song+0.259
 wig+0.254
Neg logit contributions
 Mill-0.439
 Joey-0.419
 unst-0.417
 sorts-0.413
 scaven-0.410
Token that
Token ID326
Feature activation+2.15e+00

Pos logit contributions
 sorts+0.041
 Mill+0.041
neath+0.039
 unst+0.039
 scaven+0.038
Neg logit contributions
 aids-0.026
 wig-0.024
 hair-0.024
 jokes-0.024
 song-0.022
Token friends
Token ID2460
Feature activation+1.88e+00

Pos logit contributions
 jokes+0.144
 aids+0.140
 hair+0.138
 song+0.136
 wig+0.129
Neg logit contributions
 sorts-0.149
aved-0.148
 Mill-0.146
neath-0.145
rolley-0.141
Token come
Token ID1282
Feature activation-1.57e-01

Pos logit contributions
 hair+0.132
 aids+0.129
 jokes+0.129
 song+0.123
 wig+0.121
Neg logit contributions
 Mill-0.123
 sorts-0.113
 Suz-0.112
 Joey-0.111
 hed-0.109
Token in
Token ID287
Feature activation+1.66e+00

Pos logit contributions
 sorts+0.013
 Mill+0.013
 scaven+0.012
 Joey+0.012
neath+0.012
Neg logit contributions
 hair-0.008
 aids-0.008
 wig-0.007
 song-0.007
 jokes-0.007
Token handy
Token ID15728
Feature activation-1.26e+01

Pos logit contributions
 hair+0.097
 aids+0.096
 jokes+0.090
 song+0.089
 wig+0.089
Neg logit contributions
 Mill-0.127
aved-0.124
pling-0.121
ucer-0.119
arp-0.118
Token in
Token ID287
Feature activation+1.64e+00

Pos logit contributions
 Mill+0.884
 sorts+0.882
 Joey+0.828
neath+0.812
 scaven+0.807
Neg logit contributions
 aids-0.849
 wig-0.823
 hair-0.803
 jokes-0.782
 song-0.743
Token times
Token ID1661
Feature activation+1.36e+00

Pos logit contributions
 aids+0.111
 hair+0.110
 jokes+0.102
 wig+0.102
 song+0.099
Neg logit contributions
 Mill-0.113
 sorts-0.107
 Joey-0.104
pling-0.104
 scaven-0.104
Token of
Token ID286
Feature activation+1.73e-01

Pos logit contributions
 aids+0.067
 hair+0.066
 jokes+0.060
 cheeks+0.056
 face+0.056
Neg logit contributions
 Mill-0.115
 sorts-0.113
pling-0.107
 extingu-0.106
neath-0.106
Token need
Token ID761
Feature activation-3.25e+00

Pos logit contributions
 aids+0.012
 hair+0.012
 jokes+0.011
 wig+0.011
 song+0.010
Neg logit contributions
 Mill-0.012
 sorts-0.012
aved-0.011
neath-0.011
 Joey-0.011
Token.
Token ID13
Feature activation+2.09e-01

Pos logit contributions
 sorts+0.249
 Mill+0.244
neath+0.240
 scaven+0.232
pling+0.232
Neg logit contributions
 hair-0.193
 aids-0.191
 jokes-0.187
 wig-0.178
 song-0.172
Token.
Token ID13
Feature activation+3.05e-01

Pos logit contributions
 hair+0.047
 aids+0.047
 wig+0.046
 song+0.042
 jokes+0.041
Neg logit contributions
 sorts-0.076
 Mill-0.076
 Joey-0.073
neath-0.072
 scaven-0.069
Token
Token ID198
Feature activation-2.60e-01

Pos logit contributions
 aids+0.016
 hair+0.015
 wig+0.015
 jokes+0.014
 Dancing+0.013
Neg logit contributions
 sorts-0.025
 Mill-0.025
 scaven-0.024
 unst-0.024
neath-0.024
Token
Token ID198
Feature activation-2.69e-01

Pos logit contributions
 Mill+0.019
 sorts+0.019
 Joey+0.018
 unst+0.018
neath+0.018
Neg logit contributions
 aids-0.017
 wig-0.016
 hair-0.015
 jokes-0.015
 song-0.014
TokenThen
Token ID6423
Feature activation+2.90e+00

Pos logit contributions
 sorts+0.018
 Mill+0.018
neath+0.017
 Joey+0.017
 scaven+0.016
Neg logit contributions
 aids-0.019
 wig-0.019
 hair-0.018
 jokes-0.018
 cheeks-0.017
Token the
Token ID262
Feature activation-6.73e-01

Pos logit contributions
 hair+0.171
 aids+0.170
 wig+0.169
 jokes+0.162
 cheeks+0.152
Neg logit contributions
 sorts-0.228
 Mill-0.218
 scaven-0.207
 unst-0.206
neath-0.206
Token handy
Token ID15728
Feature activation-1.25e+01

Pos logit contributions
 sorts+0.050
 Mill+0.050
 Joey+0.047
neath+0.046
 scaven+0.046
Neg logit contributions
 aids-0.043
 wig-0.042
 hair-0.041
 jokes-0.040
 song-0.038
Token man
Token ID582
Feature activation-1.00e+00

Pos logit contributions
 sorts+0.996
 Mill+0.996
 Joey+0.941
neath+0.924
 scaven+0.919
Neg logit contributions
 aids-0.731
 wig-0.707
 hair-0.683
 jokes-0.663
 song-0.624
Token drove
Token ID10357
Feature activation-1.18e+00

Pos logit contributions
 sorts+0.077
 Mill+0.075
 Joey+0.071
neath+0.069
 hed+0.069
Neg logit contributions
 aids-0.060
 wig-0.059
 hair-0.058
 jokes-0.055
ggie-0.053
Token to
Token ID284
Feature activation+1.03e+00

Pos logit contributions
 sorts+0.071
 Mill+0.070
neath+0.065
 Joey+0.065
 scaven+0.065
Neg logit contributions
 aids-0.091
 hair-0.088
 wig-0.088
 jokes-0.085
 song-0.082
Token the
Token ID262
Feature activation-6.92e-01

Pos logit contributions
 hair+0.051
 aids+0.051
 wig+0.050
 jokes+0.049
 haircut+0.048
Neg logit contributions
aved-0.087
pling-0.085
arp-0.085
 sorts-0.083
ucer-0.081
Token young
Token ID1862
Feature activation-2.04e+00

Pos logit contributions
 sorts+0.052
 Mill+0.051
 Joey+0.049
neath+0.046
 Suz+0.046
Neg logit contributions
 hair-0.045
 aids-0.044
 wig-0.043
 song-0.042
 jokes-0.041
Token compassionate
Token ID32533
Feature activation+2.61e-01

Pos logit contributions
 aids+0.128
 wig+0.124
 hair+0.116
 jokes+0.112
 song+0.106
Neg logit contributions
 Mill-0.171
 sorts-0.170
 Joey-0.163
 scaven-0.159
 unst-0.156
Token act
Token ID719
Feature activation+6.46e-01

Pos logit contributions
 aids+0.015
 wig+0.015
 hair+0.014
 jokes+0.014
 song+0.013
Neg logit contributions
 sorts-0.021
 Mill-0.021
neath-0.019
 Joey-0.019
 scaven-0.019
Token would
Token ID561
Feature activation-1.11e+00

Pos logit contributions
 aids+0.043
 hair+0.041
 wig+0.040
 jokes+0.039
 song+0.038
Neg logit contributions
 Mill-0.046
 sorts-0.046
neath-0.043
 Joey-0.043
 scaven-0.042
Token come
Token ID1282
Feature activation-6.50e-02

Pos logit contributions
 sorts+0.087
 Mill+0.085
neath+0.082
 unst+0.081
 scaven+0.081
Neg logit contributions
 aids-0.065
 wig-0.062
 hair-0.062
 jokes-0.061
 song-0.059
Token in
Token ID287
Feature activation+1.75e+00

Pos logit contributions
 sorts+0.005
 Mill+0.005
 scaven+0.005
neath+0.005
 Joey+0.004
Neg logit contributions
 hair-0.004
 aids-0.004
 wig-0.004
 song-0.004
 jokes-0.003
Token handy
Token ID15728
Feature activation-1.25e+01

Pos logit contributions
 aids+0.100
 hair+0.098
 wig+0.094
 jokes+0.093
 song+0.090
Neg logit contributions
 Mill-0.134
 sorts-0.133
aved-0.131
pling-0.129
neath-0.129
Token a
Token ID257
Feature activation-4.37e-01

Pos logit contributions
 Mill+0.852
 sorts+0.851
 Joey+0.794
 scaven+0.774
neath+0.770
Neg logit contributions
 aids-0.865
 wig-0.844
 hair-0.810
 jokes-0.794
 song-0.747
Token few
Token ID1178
Feature activation+2.25e+00

Pos logit contributions
 sorts+0.029
 Mill+0.029
neath+0.028
 Joey+0.027
aved+0.027
Neg logit contributions
 aids-0.030
 wig-0.030
 hair-0.029
 song-0.028
 jokes-0.028
Token days
Token ID1528
Feature activation+6.03e-01

Pos logit contributions
 aids+0.142
 wig+0.140
 hair+0.132
 jokes+0.128
 song+0.121
Neg logit contributions
 sorts-0.170
 Mill-0.166
 Joey-0.156
 scaven-0.155
neath-0.153
Token later
Token ID1568
Feature activation-8.40e-01

Pos logit contributions
 hair+0.034
 aids+0.033
 wig+0.032
 jokes+0.030
 cheeks+0.030
Neg logit contributions
 sorts-0.047
 Mill-0.047
 Joey-0.045
neath-0.044
 unst-0.043
Token when
Token ID618
Feature activation+3.08e-01

Pos logit contributions
 sorts+0.064
 Mill+0.063
 Joey+0.060
neath+0.059
 scaven+0.059
Neg logit contributions
 aids-0.051
 wig-0.049
 hair-0.049
 jokes-0.047
 song-0.045
Token they
Token ID484
Feature activation+5.63e-01

Pos logit contributions
 sorts+0.018
 Mill+0.017
neath+0.016
 unst+0.016
 scaven+0.016
Neg logit contributions
 aids-0.016
 wig-0.016
 hair-0.016
 jokes-0.016
 song-0.015
Token would
Token ID561
Feature activation-1.11e+00

Pos logit contributions
 aids+0.038
 wig+0.037
 hair+0.037
 jokes+0.036
 song+0.034
Neg logit contributions
 sorts-0.038
 Mill-0.038
 Joey-0.036
 unst-0.035
neath-0.035
Token knock
Token ID10643
Feature activation+4.15e+00

Pos logit contributions
 sorts+0.083
 Mill+0.082
 Joey+0.078
 unst+0.078
neath+0.077
Neg logit contributions
 aids-0.070
 wig-0.066
 hair-0.066
 jokes-0.065
 song-0.062
Token on
Token ID319
Feature activation+3.13e+00

Pos logit contributions
 hair+0.272
 wig+0.259
 aids+0.258
 jokes+0.248
 clown+0.235
Neg logit contributions
 sorts-0.303
 Mill-0.295
 scaven-0.283
 aback-0.270
 Joey-0.270
Token the
Token ID262
Feature activation-6.04e-01

Pos logit contributions
 hair+0.181
 aids+0.172
 jokes+0.165
 wig+0.146
 clown+0.143
Neg logit contributions
 sorts-0.250
aved-0.242
 unst-0.239
pling-0.237
 scaven-0.237
Token handy
Token ID15728
Feature activation-1.24e+01

Pos logit contributions
 Mill+0.038
 sorts+0.038
 Joey+0.035
neath+0.034
 scaven+0.034
Neg logit contributions
 aids-0.045
 wig-0.044
 hair-0.042
 jokes-0.042
 song-0.040
Token man
Token ID582
Feature activation-9.26e-01

Pos logit contributions
 Mill+0.842
 sorts+0.841
 Joey+0.778
neath+0.765
 scaven+0.764
Neg logit contributions
 aids-0.864
 wig-0.848
 hair-0.814
 jokes-0.806
 cheeks-0.747
Token's
Token ID338
Feature activation+2.27e+00

Pos logit contributions
 Mill+0.074
 sorts+0.074
 Joey+0.070
neath+0.069
 scaven+0.068
Neg logit contributions
 aids-0.053
 wig-0.052
 hair-0.050
 jokes-0.048
 song-0.046
Token door
Token ID3420
Feature activation-2.57e+00

Pos logit contributions
 aids+0.173
 wig+0.170
 jokes+0.161
 hair+0.158
ggie+0.157
Neg logit contributions
 Mill-0.137
 sorts-0.135
 Joey-0.125
 unst-0.124
 scaven-0.123
Token.
Token ID13
Feature activation+3.75e-01

Pos logit contributions
 Mill+0.198
 sorts+0.197
 Joey+0.189
neath+0.184
 scaven+0.184
Neg logit contributions
 aids-0.154
 wig-0.147
 hair-0.147
 jokes-0.139
 song-0.134
Token
Token ID198
Feature activation-1.70e-01

Pos logit contributions
 aids+0.023
 wig+0.022
 hair+0.021
 jokes+0.021
 song+0.019
Neg logit contributions
 Mill-0.029
 sorts-0.029
 Joey-0.028
neath-0.027
 scaven-0.027
Token.
Token ID13
Feature activation+4.14e-01

Pos logit contributions
 aids+0.069
 wig+0.067
 hair+0.066
 jokes+0.064
 song+0.061
Neg logit contributions
 sorts-0.068
 Mill-0.068
 Joey-0.064
neath-0.063
 scaven-0.062
Token
Token ID198
Feature activation-1.47e-01

Pos logit contributions
 aids+0.026
 wig+0.025
 hair+0.025
 jokes+0.023
 song+0.022
Neg logit contributions
 sorts-0.031
 Mill-0.030
 scaven-0.029
 Joey-0.028
 unst-0.028
Token
Token ID198
Feature activation-1.56e-01

Pos logit contributions
 sorts+0.011
 Mill+0.011
 unst+0.010
 Joey+0.010
neath+0.010
Neg logit contributions
 aids-0.009
 wig-0.009
 hair-0.008
 jokes-0.008
ggie-0.008
TokenSo
Token ID2396
Feature activation-1.84e+00

Pos logit contributions
 sorts+0.011
 Mill+0.011
 Joey+0.010
neath+0.010
 scaven+0.010
Neg logit contributions
 aids-0.010
 wig-0.010
 hair-0.010
 jokes-0.010
 cheeks-0.009
Token the
Token ID262
Feature activation-5.49e-01

Pos logit contributions
 sorts+0.133
 Mill+0.129
 scaven+0.123
neath+0.122
 unst+0.122
Neg logit contributions
 aids-0.119
 hair-0.115
 wig-0.115
 jokes-0.111
 song-0.105
Token handy
Token ID15728
Feature activation-1.24e+01

Pos logit contributions
 sorts+0.044
 Mill+0.044
 Joey+0.042
neath+0.041
 scaven+0.040
Neg logit contributions
 aids-0.032
 wig-0.031
 hair-0.030
 jokes-0.029
 song-0.028
Token man
Token ID582
Feature activation-8.87e-01

Pos logit contributions
 Mill+0.956
 sorts+0.951
 Joey+0.895
neath+0.873
 scaven+0.869
Neg logit contributions
 aids-0.757
 wig-0.735
 hair-0.710
 jokes-0.691
 song-0.641
Token went
Token ID1816
Feature activation-1.24e+00

Pos logit contributions
 Mill+0.063
 sorts+0.063
 Joey+0.061
 hed+0.059
 unst+0.058
Neg logit contributions
 aids-0.055
 hair-0.054
 wig-0.054
 jokes-0.052
ggie-0.050
Token to
Token ID284
Feature activation+1.15e+00

Pos logit contributions
 sorts+0.090
 Mill+0.090
 Joey+0.085
neath+0.083
 scaven+0.082
Neg logit contributions
 aids-0.080
 wig-0.079
 hair-0.077
 jokes-0.073
 song-0.070
Token the
Token ID262
Feature activation-5.63e-01

Pos logit contributions
 aids+0.058
 hair+0.057
 wig+0.056
 jokes+0.055
 haircut+0.054
Neg logit contributions
aved-0.096
arp-0.094
pling-0.090
 sorts-0.090
ucer-0.089
Token teach
Token ID4545
Feature activation+2.04e+00

Pos logit contributions
 sorts+0.039
 Mill+0.039
 Joey+0.037
neath+0.036
aved+0.035
Neg logit contributions
 aids-0.039
 hair-0.038
 wig-0.038
 jokes-0.036
 song-0.036
Token stepped
Token ID10764
Feature activation-7.84e-01

Pos logit contributions
 aids+0.040
 wig+0.040
 hair+0.039
 jokes+0.037
 song+0.036
Neg logit contributions
 Mill-0.046
 sorts-0.045
 Joey-0.043
neath-0.042
 unst-0.041
Token back
Token ID736
Feature activation+7.92e-01

Pos logit contributions
 sorts+0.055
 Mill+0.052
 scaven+0.047
 Joey+0.047
pling+0.045
Neg logit contributions
 hair-0.055
 wig-0.054
 aids-0.052
 jokes-0.048
agging-0.048
Token to
Token ID284
Feature activation+1.19e+00

Pos logit contributions
 hair+0.047
 wig+0.044
 aids+0.043
 jokes+0.040
 song+0.039
Neg logit contributions
 sorts-0.061
 Mill-0.060
 Joey-0.057
neath-0.056
 unst-0.056
Token admire
Token ID21099
Feature activation-1.90e+00

Pos logit contributions
 aids+0.075
 wig+0.075
 hair+0.074
 jokes+0.072
 song+0.068
Neg logit contributions
 Mill-0.087
 sorts-0.086
pling-0.083
neath-0.082
 unst-0.082
Token his
Token ID465
Feature activation+2.23e+00

Pos logit contributions
 sorts+0.128
 Mill+0.127
 Joey+0.118
 scaven+0.116
neath+0.116
Neg logit contributions
 aids-0.134
 wig-0.131
 hair-0.129
 jokes-0.126
 song-0.119
Token handy
Token ID15728
Feature activation-1.24e+01

Pos logit contributions
 aids+0.170
 wig+0.163
 hair+0.154
 jokes+0.152
ggie+0.144
Neg logit contributions
 sorts-0.140
 Mill-0.139
 scaven-0.128
 Joey-0.127
 unst-0.125
Token work
Token ID670
Feature activation-4.66e+00

Pos logit contributions
 sorts+0.899
 Mill+0.896
 Joey+0.829
 scaven+0.818
neath+0.804
Neg logit contributions
 aids-0.803
 wig-0.775
 hair-0.745
 jokes-0.733
 Dancing-0.675
Token.
Token ID13
Feature activation+4.21e-01

Pos logit contributions
 Mill+0.340
 sorts+0.337
 Joey+0.319
neath+0.314
 scaven+0.310
Neg logit contributions
 aids-0.302
 wig-0.292
 hair-0.286
 jokes-0.277
 song-0.265
Token
Token ID198
Feature activation-1.43e-01

Pos logit contributions
 aids+0.024
 hair+0.023
 wig+0.022
 jokes+0.021
 Dancing+0.021
Neg logit contributions
 sorts-0.034
 Mill-0.033
 unst-0.032
 scaven-0.031
neath-0.031
Token
Token ID198
Feature activation-1.48e-01

Pos logit contributions
 sorts+0.012
 Mill+0.012
 unst+0.011
neath+0.011
wood+0.011
Neg logit contributions
 aids-0.008
 wig-0.007
 hair-0.007
 jokes-0.007
ggie-0.007
Token"
Token ID1
Feature activation-2.09e-01

Pos logit contributions
 Mill+0.011
 sorts+0.011
 Joey+0.011
neath+0.010
 scaven+0.010
Neg logit contributions
 aids-0.009
 wig-0.009
 hair-0.008
 jokes-0.008
 song-0.008
Token for
Token ID329
Feature activation-2.97e+00

Pos logit contributions
 aids+0.173
 hair+0.170
 wig+0.167
 song+0.167
 jokes+0.165
Neg logit contributions
 Mill-0.202
 sorts-0.196
neath-0.192
 Joey-0.188
aved-0.188
Token my
Token ID616
Feature activation+1.54e+00

Pos logit contributions
 sorts+0.187
 Mill+0.186
 Joey+0.173
neath+0.169
 scaven+0.168
Neg logit contributions
 aids-0.223
 wig-0.217
 hair-0.212
 jokes-0.207
 song-0.197
Token son
Token ID3367
Feature activation-2.22e+00

Pos logit contributions
 aids+0.096
 wig+0.093
 hair+0.092
 jokes+0.089
 song+0.084
Neg logit contributions
 sorts-0.116
 Mill-0.115
 Joey-0.108
neath-0.108
 scaven-0.105
Token."
Token ID526
Feature activation-3.48e-01

Pos logit contributions
 Mill+0.153
 sorts+0.153
 Joey+0.143
neath+0.142
 scaven+0.140
Neg logit contributions
 aids-0.151
 wig-0.147
 hair-0.145
 jokes-0.140
 song-0.133
Token The
Token ID383
Feature activation+1.58e+00

Pos logit contributions
 sorts+0.026
 Mill+0.026
 Joey+0.025
neath+0.024
 scaven+0.024
Neg logit contributions
 aids-0.022
 wig-0.021
 hair-0.020
 jokes-0.020
 song-0.019
Token handy
Token ID15728
Feature activation-1.24e+01

Pos logit contributions
 aids+0.093
 wig+0.090
 hair+0.087
 jokes+0.084
 song+0.079
Neg logit contributions
 Mill-0.127
 sorts-0.126
 Joey-0.119
neath-0.117
 scaven-0.117
Token man
Token ID582
Feature activation-8.69e-01

Pos logit contributions
 Mill+0.908
 sorts+0.897
 Joey+0.844
neath+0.819
 scaven+0.812
Neg logit contributions
 aids-0.799
 wig-0.780
 hair-0.754
 jokes-0.735
 song-0.682
Token said
Token ID531
Feature activation+1.59e-03

Pos logit contributions
 Mill+0.057
 sorts+0.057
 Joey+0.053
 scaven+0.052
neath+0.052
Neg logit contributions
 aids-0.062
 wig-0.061
 hair-0.059
 jokes-0.057
 song-0.055
Token he
Token ID339
Feature activation+8.57e-01

Pos logit contributions
 aids+0.000
 wig+0.000
 hair+0.000
 jokes+0.000
 song+0.000
Neg logit contributions
 Mill-0.000
 Joey-0.000
 unst-0.000
 sorts-0.000
 aback-0.000
Token could
Token ID714
Feature activation-1.43e+00

Pos logit contributions
 aids+0.059
 wig+0.058
 hair+0.057
 jokes+0.056
ggie+0.053
Neg logit contributions
 sorts-0.058
 Mill-0.058
 Joey-0.054
neath-0.054
 scaven-0.052
Token help
Token ID1037
Feature activation-3.00e+00

Pos logit contributions
 sorts+0.103
 Mill+0.100
 Joey+0.095
neath+0.094
 scaven+0.093
Neg logit contributions
 aids-0.092
 hair-0.092
 wig-0.089
 jokes-0.086
 song-0.083
Token of
Token ID286
Feature activation+3.91e-01

Pos logit contributions
 Mill+0.198
 sorts+0.198
neath+0.185
 scaven+0.184
 Joey+0.182
Neg logit contributions
 aids-0.156
 hair-0.148
 jokes-0.143
 wig-0.142
 cheeks-0.139
Token salt
Token ID8268
Feature activation-3.64e+00

Pos logit contributions
 hair+0.029
 wig+0.028
 jokes+0.027
 aids+0.026
 clown+0.025
Neg logit contributions
 Mill-0.027
 sorts-0.026
neath-0.025
aved-0.024
 aback-0.024
Token could
Token ID714
Feature activation-1.41e+00

Pos logit contributions
 sorts+0.233
 Mill+0.232
neath+0.213
aved+0.208
 unst+0.207
Neg logit contributions
 aids-0.258
 hair-0.257
 wig-0.256
 jokes-0.253
 cheeks-0.237
Token come
Token ID1282
Feature activation+4.54e-02

Pos logit contributions
 sorts+0.118
 Mill+0.113
 scaven+0.106
 Joey+0.105
 aback+0.105
Neg logit contributions
 aids-0.077
 hair-0.075
 wig-0.075
 jokes-0.072
 song-0.069
Token in
Token ID287
Feature activation+1.86e+00

Pos logit contributions
 hair+0.003
 song+0.003
 aids+0.003
 face+0.003
 wig+0.002
Neg logit contributions
 sorts-0.003
erek-0.003
 scaven-0.003
 awaited-0.003
 hed-0.003
Token handy
Token ID15728
Feature activation-1.24e+01

Pos logit contributions
 hair+0.104
 aids+0.097
 song+0.095
 voice+0.091
 jokes+0.090
Neg logit contributions
aved-0.139
ucer-0.131
erek-0.128
 sorts-0.127
vell-0.126
Token,"
Token ID553
Feature activation-1.71e+00

Pos logit contributions
 Mill+0.716
 sorts+0.715
 Joey+0.662
neath+0.659
 unst+0.639
Neg logit contributions
 aids-0.984
 wig-0.964
 hair-0.948
 jokes-0.922
 song-0.894
Token so
Token ID523
Feature activation+1.58e+00

Pos logit contributions
 Mill+0.126
 sorts+0.123
 Joey+0.119
neath+0.114
 scaven+0.113
Neg logit contributions
 aids-0.114
 wig-0.110
 hair-0.105
 jokes-0.103
 song-0.098
Token he
Token ID339
Feature activation+8.84e-01

Pos logit contributions
 aids+0.097
 wig+0.094
 hair+0.091
 jokes+0.088
 song+0.084
Neg logit contributions
 sorts-0.120
 Mill-0.120
 Joey-0.113
neath-0.111
 scaven-0.111
Token scoop
Token ID23529
Feature activation-4.96e-01

Pos logit contributions
 aids+0.065
 wig+0.061
 hair+0.059
 jokes+0.057
 Dancing+0.056
Neg logit contributions
 Mill-0.059
 sorts-0.057
 Joey-0.056
 scaven-0.055
 unst-0.053
Tokened
Token ID276
Feature activation-7.83e-01

Pos logit contributions
 sorts+0.042
 Mill+0.040
 scaven+0.040
 haven+0.038
 hed+0.037
Neg logit contributions
 hair-0.027
 aids-0.024
 wig-0.022
 jokes-0.022
 face-0.022
Token Mr
Token ID1770
Feature activation-5.84e+00

Pos logit contributions
 aids+0.060
 hair+0.058
 wig+0.057
 jokes+0.056
 song+0.052
Neg logit contributions
 Mill-0.068
 sorts-0.068
 Joey-0.065
 scaven-0.063
neath-0.063
Token.
Token ID13
Feature activation+4.36e-01

Pos logit contributions
 Mill+0.430
 sorts+0.429
 Joey+0.404
neath+0.395
 scaven+0.394
Neg logit contributions
 aids-0.378
 wig-0.366
 hair-0.352
 jokes-0.344
 song-0.326
Token Lee
Token ID5741
Feature activation+9.90e-01

Pos logit contributions
 aids+0.032
 wig+0.032
 hair+0.031
 jokes+0.030
 song+0.029
Neg logit contributions
 sorts-0.028
 Mill-0.027
 Joey-0.025
neath-0.025
 unst-0.025
Token,
Token ID11
Feature activation-9.69e-02

Pos logit contributions
 aids+0.068
 wig+0.067
 hair+0.063
 jokes+0.062
 song+0.060
Neg logit contributions
 Mill-0.067
 sorts-0.067
neath-0.063
 Joey-0.062
 scaven-0.062
Token the
Token ID262
Feature activation-5.14e-01

Pos logit contributions
 sorts+0.007
 Mill+0.007
 Joey+0.006
neath+0.006
 scaven+0.006
Neg logit contributions
 aids-0.007
 wig-0.006
 hair-0.006
 jokes-0.006
 song-0.006
Token handy
Token ID15728
Feature activation-1.24e+01

Pos logit contributions
 sorts+0.039
 Mill+0.039
 Joey+0.037
 scaven+0.036
 unst+0.036
Neg logit contributions
 aids-0.031
 wig-0.030
 hair-0.029
 jokes-0.028
ggie-0.027
Tokenman
Token ID805
Feature activation+4.12e-01

Pos logit contributions
 Mill+0.869
 sorts+0.863
 Joey+0.796
neath+0.772
 scaven+0.769
Neg logit contributions
 aids-0.822
 wig-0.799
 hair-0.771
 jokes-0.759
 cheeks-0.699
Token.
Token ID13
Feature activation+4.36e-01

Pos logit contributions
 aids+0.029
 wig+0.028
 hair+0.027
 jokes+0.026
 song+0.025
Neg logit contributions
 Mill-0.028
 sorts-0.028
 Joey-0.026
neath-0.026
 scaven-0.026
Token He
Token ID679
Feature activation+6.29e-01

Pos logit contributions
 aids+0.027
 wig+0.026
 hair+0.025
 jokes+0.025
 song+0.023
Neg logit contributions
 Mill-0.033
 sorts-0.033
 Joey-0.031
neath-0.031
 scaven-0.030
Token is
Token ID318
Feature activation-3.10e-01

Pos logit contributions
 aids+0.043
 wig+0.042
 hair+0.041
 jokes+0.040
 song+0.037
Neg logit contributions
 Mill-0.044
 sorts-0.044
 Joey-0.042
 unst-0.040
neath-0.040
Token fixing
Token ID18682
Feature activation-4.36e+00

Pos logit contributions
 Mill+0.022
 unst+0.022
 sorts+0.021
 Joey+0.021
 handy+0.021
Neg logit contributions
 aids-0.020
 wig-0.019
 cheeks-0.019
 jokes-0.019
 song-0.018
Token stood
Token ID6204
Feature activation+1.05e+00

Pos logit contributions
 aids+0.058
 wig+0.056
 hair+0.055
 jokes+0.053
 song+0.051
Neg logit contributions
 sorts-0.054
 Mill-0.054
 Joey-0.050
neath-0.049
 scaven-0.049
Token back
Token ID736
Feature activation+7.89e-01

Pos logit contributions
 aids+0.089
 wig+0.086
 hair+0.083
 jokes+0.082
 song+0.079
Neg logit contributions
 Mill-0.058
 sorts-0.057
 Joey-0.053
neath-0.052
 unst-0.051
Token and
Token ID290
Feature activation-1.88e-01

Pos logit contributions
 hair+0.050
 aids+0.048
 wig+0.046
 jokes+0.045
 song+0.043
Neg logit contributions
 sorts-0.058
 Mill-0.058
 Joey-0.055
neath-0.053
 unst-0.053
Token admired
Token ID29382
Feature activation-1.48e+00

Pos logit contributions
 sorts+0.014
 Mill+0.014
 Joey+0.013
 scaven+0.013
neath+0.013
Neg logit contributions
 wig-0.011
 hair-0.011
 aids-0.011
 jokes-0.010
 cheeks-0.010
Token their
Token ID511
Feature activation+8.62e-01

Pos logit contributions
 sorts+0.102
 Mill+0.101
 Joey+0.094
 scaven+0.094
 unst+0.094
Neg logit contributions
 aids-0.100
 hair-0.098
 wig-0.097
 jokes-0.095
 song-0.089
Token handy
Token ID15728
Feature activation-1.24e+01

Pos logit contributions
 aids+0.074
 wig+0.073
 hair+0.071
 jokes+0.070
 song+0.067
Neg logit contributions
 sorts-0.045
 Mill-0.045
 Joey-0.041
neath-0.040
 scaven-0.040
Token work
Token ID670
Feature activation-4.64e+00

Pos logit contributions
 sorts+0.859
 Mill+0.852
 Joey+0.789
 scaven+0.782
 unst+0.773
Neg logit contributions
 aids-0.836
 wig-0.817
 hair-0.782
 jokes-0.763
 Dancing-0.708
Token.
Token ID13
Feature activation+4.36e-01

Pos logit contributions
 Mill+0.341
 sorts+0.338
 Joey+0.321
neath+0.315
 scaven+0.311
Neg logit contributions
 aids-0.298
 wig-0.287
 hair-0.283
 jokes-0.273
 song-0.261
Token The
Token ID383
Feature activation+1.59e+00

Pos logit contributions
 aids+0.027
 hair+0.025
 wig+0.024
 jokes+0.024
 Dancing+0.022
Neg logit contributions
 Mill-0.033
 sorts-0.032
 unst-0.031
 scaven-0.031
 Joey-0.030
Token screw
Token ID9580
Feature activation-4.66e+00

Pos logit contributions
 aids+0.108
 wig+0.105
 hair+0.105
 jokes+0.101
 song+0.097
Neg logit contributions
 Mill-0.113
 sorts-0.110
 Joey-0.106
neath-0.102
 unst-0.100
Token was
Token ID373
Feature activation-2.14e-01

Pos logit contributions
 Mill+0.308
 sorts+0.308
 Joey+0.288
neath+0.280
 scaven+0.279
Neg logit contributions
 aids-0.332
 wig-0.324
 hair-0.316
 jokes-0.307
 song-0.294
Token it
Token ID340
Feature activation-1.26e+00

Pos logit contributions
 aids+0.161
 hair+0.156
 jokes+0.154
 wig+0.145
 song+0.143
Neg logit contributions
 sorts-0.182
aved-0.180
 aback-0.179
 scaven-0.179
 unst-0.178
Token's
Token ID338
Feature activation+2.18e+00

Pos logit contributions
 Mill+0.101
 sorts+0.097
 Joey+0.095
 unst+0.095
 scaven+0.094
Neg logit contributions
 aids-0.070
 jokes-0.067
 hair-0.066
 wig-0.063
 song-0.062
Token important
Token ID1593
Feature activation-1.79e+00

Pos logit contributions
 aids+0.137
 hair+0.132
 jokes+0.129
 wig+0.127
 song+0.120
Neg logit contributions
 sorts-0.161
 Mill-0.159
neath-0.154
 scaven-0.150
aved-0.149
Token to
Token ID284
Feature activation+1.03e+00

Pos logit contributions
 sorts+0.130
 Mill+0.130
neath+0.123
 Joey+0.122
 scaven+0.120
Neg logit contributions
 aids-0.116
 wig-0.112
 hair-0.111
 jokes-0.108
 song-0.102
Token keep
Token ID1394
Feature activation-2.07e+00

Pos logit contributions
 aids+0.059
 wig+0.057
 hair+0.057
 jokes+0.056
 song+0.052
Neg logit contributions
 sorts-0.083
 Mill-0.081
neath-0.078
 unst-0.078
 scaven-0.077
Token hed
Token ID16418
Feature activation-1.23e+01

Pos logit contributions
 sorts+0.146
 Mill+0.138
aved+0.137
neath+0.137
 scaven+0.135
Neg logit contributions
 hair-0.139
 aids-0.135
 jokes-0.130
 wig-0.124
 song-0.121
Tokenges
Token ID3212
Feature activation-4.30e-01

Pos logit contributions
 sorts+0.812
 Mill+0.785
 scaven+0.748
 Joey+0.724
neath+0.698
Neg logit contributions
 aids-0.853
 wig-0.834
 hair-0.800
agging-0.770
 Dancing-0.749
Token neat
Token ID15049
Feature activation-5.32e+00

Pos logit contributions
 sorts+0.033
 Mill+0.032
 scaven+0.032
neath+0.031
aved+0.031
Neg logit contributions
 aids-0.025
 hair-0.025
 jokes-0.024
 songs-0.022
 song-0.022
Token and
Token ID290
Feature activation-3.61e-01

Pos logit contributions
 Mill+0.396
 sorts+0.395
neath+0.388
 scaven+0.379
 Joey+0.375
Neg logit contributions
 hair-0.336
 aids-0.326
 jokes-0.310
 wig-0.304
 cheeks-0.296
Token tidy
Token ID43044
Feature activation-3.68e+00

Pos logit contributions
 Mill+0.025
neath+0.025
 sorts+0.025
 Joey+0.024
aved+0.023
Neg logit contributions
 hair-0.023
 jokes-0.023
 aids-0.022
 song-0.022
 wig-0.022
Token"
Token ID1
Feature activation-3.86e-01

Pos logit contributions
 sorts+0.241
 Mill+0.236
 scaven+0.234
neath+0.234
aved+0.222
Neg logit contributions
 hair-0.263
 aids-0.258
 jokes-0.247
 wig-0.241
 song-0.233
Token work
Token ID670
Feature activation-4.69e+00

Pos logit contributions
 hair+0.068
 wig+0.065
 jokes+0.065
 aids+0.063
 face+0.060
Neg logit contributions
ucer-0.088
 sorts-0.086
arp-0.085
rolley-0.085
pling-0.085
Token.
Token ID13
Feature activation+3.79e-01

Pos logit contributions
 Mill+0.368
 sorts+0.366
 Joey+0.348
neath+0.346
pling+0.340
Neg logit contributions
 hair-0.264
 aids-0.264
 wig-0.247
 jokes-0.246
 song-0.227
Token They
Token ID1119
Feature activation-2.90e-01

Pos logit contributions
 aids+0.022
 hair+0.022
 wig+0.021
 jokes+0.020
 cheeks+0.019
Neg logit contributions
 sorts-0.029
 Mill-0.029
 scaven-0.027
 unst-0.027
pling-0.027
Token trimmed
Token ID40325
Feature activation-1.29e-01

Pos logit contributions
 aback+0.022
 Mill+0.022
 unst+0.021
wood+0.021
 awaits+0.021
Neg logit contributions
 hair-0.015
 wig-0.014
 aids-0.014
 jokes-0.014
 cheeks-0.013
Token the
Token ID262
Feature activation-5.76e-01

Pos logit contributions
 sorts+0.010
 scaven+0.010
 Mill+0.009
aved+0.009
 unst+0.009
Neg logit contributions
 hair-0.008
 aids-0.007
 jokes-0.007
 cheeks-0.007
 wig-0.007
Token hed
Token ID16418
Feature activation-1.22e+01

Pos logit contributions
 sorts+0.038
 Mill+0.036
 Joey+0.035
neath+0.034
 aback+0.033
Neg logit contributions
 hair-0.045
 aids-0.041
 cheeks-0.040
 wig-0.040
 face-0.039
Tokenges
Token ID3212
Feature activation-3.24e-01

Pos logit contributions
 sorts+0.770
 Mill+0.765
 scaven+0.724
 Joey+0.706
 unst+0.695
Neg logit contributions
 aids-0.881
 wig-0.879
 hair-0.825
 Dancing-0.779
 jokes-0.776
Token and
Token ID290
Feature activation-2.51e-01

Pos logit contributions
 Mill+0.025
 sorts+0.025
pling+0.023
 scaven+0.023
 Joey+0.023
Neg logit contributions
 hair-0.019
 aids-0.019
 jokes-0.018
 song-0.016
 wig-0.016
Token cut
Token ID2005
Feature activation-7.58e-01

Pos logit contributions
 sorts+0.018
 Mill+0.018
neath+0.017
 Joey+0.016
 scaven+0.016
Neg logit contributions
 hair-0.016
 aids-0.016
 wig-0.016
 jokes-0.016
 cheeks-0.015
Token the
Token ID262
Feature activation-5.98e-01

Pos logit contributions
 sorts+0.055
 Mill+0.053
 scaven+0.052
 Joey+0.049
neath+0.049
Neg logit contributions
 hair-0.051
 aids-0.048
 jokes-0.045
 wig-0.044
 cheeks-0.042
Token grass
Token ID8701
Feature activation-1.44e+00

Pos logit contributions
 sorts+0.041
 Mill+0.039
 Joey+0.038
neath+0.037
 aback+0.036
Neg logit contributions
 hair-0.046
 cheeks-0.041
 face-0.040
 aids-0.039
 wig-0.039
Token spider
Token ID19230
Feature activation-1.13e+00

Pos logit contributions
 aids+0.100
 wig+0.097
 hair+0.091
 jokes+0.089
ggie+0.088
Neg logit contributions
 Mill-0.057
 sorts-0.057
 Joey-0.053
 scaven-0.053
 unst-0.052
Token lived
Token ID5615
Feature activation-3.37e+00

Pos logit contributions
 sorts+0.066
 Mill+0.066
 Joey+0.060
 scaven+0.059
 unst+0.058
Neg logit contributions
 aids-0.086
 wig-0.085
 hair-0.081
 jokes-0.080
 cheeks-0.076
Token in
Token ID287
Feature activation+4.63e-01

Pos logit contributions
 sorts+0.245
 Mill+0.245
 Joey+0.231
neath+0.228
 unst+0.225
Neg logit contributions
 aids-0.217
 wig-0.209
 hair-0.206
 jokes-0.199
 song-0.190
Token an
Token ID281
Feature activation-3.84e+00

Pos logit contributions
 aids+0.028
 hair+0.027
 wig+0.026
 jokes+0.025
 song+0.024
Neg logit contributions
 Mill-0.034
 unst-0.034
 sorts-0.034
pling-0.034
 scaven-0.033
Token old
Token ID1468
Feature activation-2.69e+00

Pos logit contributions
 Mill+0.271
 sorts+0.267
neath+0.257
 Joey+0.257
 unst+0.252
Neg logit contributions
 aids-0.258
 hair-0.245
 wig-0.243
 jokes-0.235
 song-0.223
Token shed
Token ID14999
Feature activation-1.09e+01

Pos logit contributions
 sorts+0.174
 Mill+0.173
 Joey+0.162
neath+0.160
 unst+0.158
Neg logit contributions
 aids-0.196
 wig-0.192
 hair-0.188
 jokes-0.182
 song-0.175
Token.
Token ID13
Feature activation-2.33e-01

Pos logit contributions
 sorts+0.818
 Mill+0.817
 Joey+0.773
neath+0.762
 scaven+0.753
Neg logit contributions
 aids-0.672
 wig-0.650
 hair-0.639
 jokes-0.610
 song-0.585
Token He
Token ID679
Feature activation+3.30e-02

Pos logit contributions
 Mill+0.018
 sorts+0.018
 Joey+0.017
neath+0.017
 scaven+0.017
Neg logit contributions
 aids-0.014
 wig-0.013
 hair-0.013
 jokes-0.013
 song-0.012
Token was
Token ID373
Feature activation-7.42e-01

Pos logit contributions
 aids+0.002
 wig+0.002
 hair+0.002
 jokes+0.002
 song+0.002
Neg logit contributions
 Mill-0.002
 sorts-0.002
 Joey-0.002
neath-0.002
 scaven-0.002
Token very
Token ID845
Feature activation+5.57e-01

Pos logit contributions
 sorts+0.055
 Mill+0.055
 Joey+0.052
neath+0.051
 scaven+0.051
Neg logit contributions
 aids-0.047
 wig-0.046
 hair-0.044
 jokes-0.043
 song-0.041
Token careful
Token ID8161
Feature activation-3.22e+00

Pos logit contributions
 aids+0.029
 hair+0.028
 wig+0.026
 jokes+0.026
 song+0.024
Neg logit contributions
 sorts-0.047
 Mill-0.046
neath-0.046
 scaven-0.044
 Joey-0.044
Token big
Token ID1263
Feature activation-2.46e+00

Pos logit contributions
 aids+0.039
 jokes+0.036
 wig+0.035
ggie+0.034
 song+0.033
Neg logit contributions
 Mill-0.036
 sorts-0.036
 unst-0.034
 Joey-0.033
 shed-0.033
Token red
Token ID2266
Feature activation+1.53e+00

Pos logit contributions
 Mill+0.156
 sorts+0.156
 Joey+0.145
neath+0.142
 scaven+0.141
Neg logit contributions
 aids-0.182
 wig-0.177
 hair-0.172
 jokes-0.168
 song-0.161
Token saw
Token ID2497
Feature activation-1.31e+00

Pos logit contributions
 aids+0.112
 wig+0.101
 jokes+0.099
ggie+0.098
 Dancing+0.096
Neg logit contributions
 sorts-0.093
 Mill-0.092
 Joey-0.089
neath-0.087
 scaven-0.083
Token near
Token ID1474
Feature activation-1.42e+00

Pos logit contributions
 sorts+0.089
 Mill+0.089
 Joey+0.083
neath+0.081
 scaven+0.080
Neg logit contributions
 aids-0.090
 wig-0.088
 hair-0.084
 jokes-0.082
 song-0.079
Token the
Token ID262
Feature activation-1.44e+00

Pos logit contributions
 Mill+0.096
 sorts+0.096
 unst+0.091
 scaven+0.091
 Joey+0.090
Neg logit contributions
 aids-0.099
 hair-0.094
 wig-0.094
 jokes-0.092
 song-0.087
Token shed
Token ID14999
Feature activation-1.09e+01

Pos logit contributions
 sorts+0.101
 Mill+0.100
 Joey+0.093
 unst+0.092
neath+0.092
Neg logit contributions
 aids-0.099
 wig-0.097
 hair-0.097
 jokes-0.092
 song-0.090
Token.
Token ID13
Feature activation-2.33e-01

Pos logit contributions
 sorts+0.837
 Mill+0.834
 Joey+0.785
neath+0.777
 scaven+0.773
Neg logit contributions
 aids-0.657
 wig-0.633
 hair-0.624
 jokes-0.595
 song-0.568
Token Lily
Token ID20037
Feature activation+6.35e-01

Pos logit contributions
 Mill+0.017
 sorts+0.017
 Joey+0.016
neath+0.015
 scaven+0.015
Neg logit contributions
 aids-0.015
 wig-0.015
 hair-0.014
 jokes-0.014
 song-0.014
Token wanted
Token ID2227
Feature activation-1.11e-01

Pos logit contributions
 aids+0.038
 hair+0.037
 wig+0.037
 jokes+0.035
 cheeks+0.033
Neg logit contributions
 Mill-0.049
 sorts-0.049
 Joey-0.046
 unst-0.046
neath-0.046
Token to
Token ID284
Feature activation+7.10e-01

Pos logit contributions
 sorts+0.009
 Mill+0.009
neath+0.008
 Joey+0.008
 unst+0.008
Neg logit contributions
 aids-0.007
 wig-0.006
 hair-0.006
 jokes-0.006
 song-0.006
Token touch
Token ID3638
Feature activation+2.38e+00

Pos logit contributions
 hair+0.045
 wig+0.045
 aids+0.045
 jokes+0.043
 song+0.040
Neg logit contributions
 sorts-0.051
 Mill-0.050
neath-0.048
 scaven-0.047
 Joey-0.047
Token the
Token ID262
Feature activation-6.70e-01

Pos logit contributions
 Mill+0.166
 sorts+0.166
 Joey+0.156
neath+0.153
 scaven+0.152
Neg logit contributions
 aids-0.172
 wig-0.167
 hair-0.163
 jokes-0.159
 song-0.151
Token picture
Token ID4286
Feature activation+3.29e+00

Pos logit contributions
 Mill+0.054
 sorts+0.054
 Joey+0.051
neath+0.050
 scaven+0.050
Neg logit contributions
 aids-0.039
 wig-0.038
 hair-0.036
 jokes-0.035
 song-0.033
Token of
Token ID286
Feature activation+2.22e-01

Pos logit contributions
 aids+0.222
 wig+0.217
 hair+0.209
 jokes+0.204
 song+0.193
Neg logit contributions
 Mill-0.230
 sorts-0.230
 Joey-0.215
neath-0.210
 scaven-0.209
Token the
Token ID262
Feature activation-6.82e-01

Pos logit contributions
 hair+0.014
 aids+0.014
 wig+0.013
 jokes+0.013
 song+0.012
Neg logit contributions
 sorts-0.017
 Mill-0.016
 scaven-0.015
 aback-0.015
aved-0.015
Token big
Token ID1263
Feature activation-7.83e-01

Pos logit contributions
 Mill+0.052
 sorts+0.052
 Joey+0.049
neath+0.048
 scaven+0.048
Neg logit contributions
 aids-0.043
 wig-0.041
 hair-0.040
 jokes-0.039
 song-0.037
Token pink
Token ID11398
Feature activation+5.00e+00

Pos logit contributions
 sorts+0.059
 Mill+0.059
 Joey+0.055
neath+0.054
 scaven+0.053
Neg logit contributions
 aids-0.050
 wig-0.048
 hair-0.046
 jokes-0.045
 song-0.043
Token elephant
Token ID20950
Feature activation+4.13e-01

Pos logit contributions
 aids+0.328
 wig+0.318
 hair+0.308
 jokes+0.300
 song+0.284
Neg logit contributions
 sorts-0.363
 Mill-0.363
 Joey-0.341
neath-0.334
 scaven-0.332
Token.
Token ID13
Feature activation+2.58e-01

Pos logit contributions
 aids+0.027
 wig+0.026
 hair+0.025
 jokes+0.024
 song+0.023
Neg logit contributions
 sorts-0.030
 Mill-0.030
 Joey-0.028
neath-0.028
 scaven-0.028
Token Tim
Token ID5045
Feature activation-4.87e+00

Pos logit contributions
 aids+0.019
 wig+0.018
 hair+0.018
 jokes+0.017
 song+0.017
Neg logit contributions
 sorts-0.017
 Mill-0.017
 Joey-0.015
neath-0.015
 scaven-0.015
Tokenmy
Token ID1820
Feature activation-1.57e+00

Pos logit contributions
 sorts+0.231
 Mill+0.230
 Joey+0.209
neath+0.201
 scaven+0.200
Neg logit contributions
 aids-0.444
 wig-0.433
 hair-0.423
 jokes-0.417
 song-0.401
Token said
Token ID531
Feature activation-1.72e-01

Pos logit contributions
 sorts+0.090
 Mill+0.088
 Joey+0.081
neath+0.079
 scaven+0.079
Neg logit contributions
 aids-0.127
 wig-0.124
 hair-0.119
 jokes-0.116
agging-0.113
Token shot
Token ID2823
Feature activation-1.26e+00

Pos logit contributions
 Mill+0.040
 sorts+0.039
arp+0.039
pling+0.038
rolley+0.037
Neg logit contributions
 jokes-0.026
 hair-0.025
 wig-0.025
 aids-0.023
 song-0.023
Token!
Token ID0
Feature activation-4.49e+00

Pos logit contributions
 Mill+0.086
 sorts+0.085
 scaven+0.078
 Joey+0.078
neath+0.077
Neg logit contributions
 aids-0.090
 hair-0.087
 wig-0.085
 jokes-0.085
 song-0.080
Token All
Token ID1439
Feature activation+2.23e+00

Pos logit contributions
 sorts+0.415
 Mill+0.405
 unst+0.386
pling+0.381
 scaven+0.381
Neg logit contributions
 aids-0.203
 hair-0.191
 jokes-0.177
 wig-0.175
 Dancing-0.163
Token of
Token ID286
Feature activation+5.51e-02

Pos logit contributions
 aids+0.167
 wig+0.161
 hair+0.159
 jokes+0.156
 song+0.149
Neg logit contributions
 Mill-0.141
 sorts-0.139
 Joey-0.130
 scaven-0.127
neath-0.127
Token a
Token ID257
Feature activation-6.82e-01

Pos logit contributions
 hair+0.003
 jokes+0.003
 aids+0.003
 wig+0.003
 song+0.003
Neg logit contributions
 sorts-0.004
 Mill-0.004
 unst-0.004
wood-0.004
aved-0.004
Token sudden
Token ID4802
Feature activation+4.86e+00

Pos logit contributions
 Mill+0.060
 sorts+0.060
 Joey+0.057
neath+0.056
 scaven+0.055
Neg logit contributions
 aids-0.034
 wig-0.033
 hair-0.032
 jokes-0.031
 song-0.029
Token,
Token ID11
Feature activation-4.43e-01

Pos logit contributions
 hair+0.241
 aids+0.233
 jokes+0.230
 wig+0.218
 clown+0.212
Neg logit contributions
 sorts-0.427
 Mill-0.415
rolley-0.392
wood-0.391
 unst-0.386
Token the
Token ID262
Feature activation-8.58e-01

Pos logit contributions
 sorts+0.038
 Mill+0.037
wood+0.036
aved+0.036
arp+0.035
Neg logit contributions
 hair-0.022
 jokes-0.022
 clown-0.021
 song-0.020
 aids-0.020
Token target
Token ID2496
Feature activation-3.38e+00

Pos logit contributions
 sorts+0.063
 Mill+0.061
 unst+0.060
 Joey+0.060
 scaven+0.059
Neg logit contributions
 aids-0.056
 wig-0.052
 hair-0.049
 jokes-0.048
 cheeks-0.045
Token burst
Token ID11173
Feature activation+3.27e-01

Pos logit contributions
 Mill+0.256
 sorts+0.251
 Joey+0.236
neath+0.226
 scaven+0.224
Neg logit contributions
 aids-0.215
 wig-0.209
 hair-0.204
 jokes-0.201
 song-0.191
Token with
Token ID351
Feature activation+5.86e-01

Pos logit contributions
 hair+0.020
 aids+0.019
 jokes+0.018
 face+0.018
 wig+0.017
Neg logit contributions
 sorts-0.025
 Mill-0.024
 awaited-0.023
neath-0.023
 awaits-0.022
Token and
Token ID290
Feature activation-2.89e-01

Pos logit contributions
 aids+0.390
 wig+0.375
 jokes+0.360
 hair+0.351
 song+0.332
Neg logit contributions
 Mill-0.339
 sorts-0.339
 unst-0.327
 scaven-0.317
neath-0.314
Token started
Token ID2067
Feature activation+2.19e+00

Pos logit contributions
 Mill+0.020
 sorts+0.020
 Joey+0.019
 unst+0.019
neath+0.019
Neg logit contributions
 aids-0.020
 wig-0.019
 jokes-0.018
 hair-0.018
 song-0.017
Token to
Token ID284
Feature activation+1.12e+00

Pos logit contributions
 aids+0.182
 wig+0.176
 jokes+0.167
agged+0.164
ggie+0.161
Neg logit contributions
 unst-0.120
 Mill-0.119
 sorts-0.111
 scaven-0.109
 Joey-0.107
Token cry
Token ID3960
Feature activation+1.15e+00

Pos logit contributions
 aids+0.058
 wig+0.056
 hair+0.054
 jokes+0.052
 song+0.049
Neg logit contributions
 sorts-0.096
 Mill-0.096
 Joey-0.091
neath-0.089
 scaven-0.089
Token.
Token ID13
Feature activation+3.64e-01

Pos logit contributions
 aids+0.084
 wig+0.083
 jokes+0.076
 hair+0.076
ggie+0.072
Neg logit contributions
 Mill-0.076
 sorts-0.072
 Joey-0.070
 unst-0.069
 scaven-0.066
Token Her
Token ID2332
Feature activation+5.82e+00

Pos logit contributions
 wig+0.027
 song+0.025
 aids+0.024
agging+0.024
 jokes+0.024
Neg logit contributions
 Mill-0.027
 Joey-0.024
 Bobby-0.022
 Suz-0.022
 Sus-0.021
Token friends
Token ID2460
Feature activation+2.01e+00

Pos logit contributions
 aids+0.386
 wig+0.316
agged+0.298
 jokes+0.297
uren+0.290
Neg logit contributions
 unst-0.397
 Mill-0.382
 scaven-0.380
 Joey-0.368
 bur-0.360
Token saw
Token ID2497
Feature activation+4.15e-02

Pos logit contributions
 aids+0.125
 wig+0.122
 hair+0.120
 jokes+0.116
 song+0.109
Neg logit contributions
 sorts-0.152
 Mill-0.150
 Joey-0.141
neath-0.139
 scaven-0.137
Token her
Token ID607
Feature activation+9.70e-01

Pos logit contributions
 aids+0.003
 wig+0.003
 hair+0.003
 jokes+0.003
 song+0.002
Neg logit contributions
 sorts-0.003
 Mill-0.003
 Joey-0.003
 scaven-0.003
neath-0.003
Token crying
Token ID13774
Feature activation+8.54e-01

Pos logit contributions
 aids+0.067
 wig+0.062
 jokes+0.056
agged+0.056
 Dancing+0.055
Neg logit contributions
 unst-0.064
 Mill-0.061
 sorts-0.061
 scaven-0.061
 Joey-0.059
Token and
Token ID290
Feature activation-2.18e-01

Pos logit contributions
 aids+0.075
 wig+0.072
ggie+0.068
 blond+0.065
 jokes+0.065
Neg logit contributions
 sorts-0.040
 Mill-0.040
 unst-0.039
 Joey-0.038
 aback-0.036
Token with
Token ID351
Feature activation+7.32e-01

Pos logit contributions
 unst+0.191
pling+0.190
 Mill+0.189
 Joey+0.188
 sorts+0.187
Neg logit contributions
 hair-0.156
 aids-0.153
 jokes-0.144
 wig-0.137
 song-0.135
Token food
Token ID2057
Feature activation-1.65e+00

Pos logit contributions
 hair+0.049
 aids+0.046
 jokes+0.045
 wig+0.043
 songs+0.041
Neg logit contributions
 sorts-0.050
 unst-0.050
neath-0.050
 scaven-0.050
 Mill-0.050
Token and
Token ID290
Feature activation-4.14e-01

Pos logit contributions
 sorts+0.134
 Mill+0.133
 unst+0.130
neath+0.129
 Joey+0.125
Neg logit contributions
 hair-0.089
 wig-0.085
 aids-0.085
 jokes-0.084
 song-0.076
Token drinks
Token ID11758
Feature activation+1.45e+00

Pos logit contributions
 sorts+0.029
 Mill+0.029
 Joey+0.027
neath+0.027
 unst+0.027
Neg logit contributions
 aids-0.028
 wig-0.027
 hair-0.027
 jokes-0.026
 song-0.025
Token.
Token ID13
Feature activation+2.13e-01

Pos logit contributions
 hair+0.083
 aids+0.083
 jokes+0.079
 wig+0.079
 song+0.073
Neg logit contributions
 sorts-0.113
 Mill-0.113
 scaven-0.108
 unst-0.107
neath-0.107
Token Her
Token ID2332
Feature activation+5.65e+00

Pos logit contributions
 aids+0.013
 wig+0.013
 hair+0.012
 jokes+0.012
 song+0.012
Neg logit contributions
 Mill-0.016
 sorts-0.016
 Joey-0.015
neath-0.015
 scaven-0.015
Token parents
Token ID3397
Feature activation-8.35e-01

Pos logit contributions
 aids+0.334
 wig+0.323
 hair+0.310
 jokes+0.301
 song+0.285
Neg logit contributions
 Mill-0.449
 sorts-0.448
 Joey-0.424
neath-0.413
 scaven-0.413
Token told
Token ID1297
Feature activation-3.28e-01

Pos logit contributions
 unst+0.057
 sorts+0.057
 Mill+0.056
 hed+0.055
wood+0.054
Neg logit contributions
 aids-0.052
 wig-0.052
 hair-0.051
 jokes-0.050
 clown-0.048
Token her
Token ID607
Feature activation+7.75e-01

Pos logit contributions
 Mill+0.024
 sorts+0.023
 Joey+0.022
neath+0.021
 unst+0.021
Neg logit contributions
 aids-0.022
 wig-0.022
 hair-0.020
 jokes-0.019
 song-0.019
Token that
Token ID326
Feature activation+2.10e+00

Pos logit contributions
 aids+0.054
 wig+0.054
 hair+0.051
 jokes+0.050
 song+0.048
Neg logit contributions
 Mill-0.053
 sorts-0.052
 Joey-0.049
 scaven-0.047
neath-0.047
Token it
Token ID340
Feature activation-1.37e+00

Pos logit contributions
 aids+0.139
 jokes+0.135
 hair+0.134
 wig+0.128
 song+0.125
Neg logit contributions
 sorts-0.146
aved-0.144
 unst-0.143
 aback-0.141
neath-0.140
Token Lily
Token ID20037
Feature activation+1.00e+00

Pos logit contributions
 sorts+0.029
 Mill+0.029
 Joey+0.027
 scaven+0.027
neath+0.027
Neg logit contributions
 aids-0.025
 wig-0.025
 hair-0.024
 jokes-0.023
 song-0.022
Token are
Token ID389
Feature activation-3.35e+00

Pos logit contributions
 hair+0.048
 wig+0.042
 jokes+0.042
 clown+0.041
 aids+0.038
Neg logit contributions
 Mill-0.093
 sorts-0.086
wood-0.086
 unst-0.085
pling-0.085
Token twins
Token ID20345
Feature activation+1.33e+00

Pos logit contributions
 sorts+0.230
 Mill+0.228
 Joey+0.216
 unst+0.212
 scaven+0.211
Neg logit contributions
 aids-0.237
 wig-0.229
 jokes-0.210
 hair-0.208
 song-0.206
Token who
Token ID508
Feature activation+1.80e+00

Pos logit contributions
 aids+0.102
 wig+0.097
 jokes+0.093
 hair+0.091
ggie+0.088
Neg logit contributions
 Mill-0.079
 sorts-0.079
 Joey-0.074
 scaven-0.072
neath-0.071
Token love
Token ID1842
Feature activation-4.64e+00

Pos logit contributions
 aids+0.117
 wig+0.115
 hair+0.114
 jokes+0.111
 song+0.103
Neg logit contributions
 Mill-0.131
 sorts-0.126
 Joey-0.122
neath-0.120
 unst-0.120
Token music
Token ID2647
Feature activation+5.17e+00

Pos logit contributions
 Mill+0.314
 sorts+0.313
 Joey+0.298
 scaven+0.282
neath+0.278
Neg logit contributions
 aids-0.334
 wig-0.323
 hair-0.302
 jokes-0.296
ggie-0.291
Token.
Token ID13
Feature activation+1.92e-01

Pos logit contributions
 aids+0.382
 wig+0.371
 hair+0.342
 jokes+0.334
 cheeks+0.329
Neg logit contributions
 sorts-0.334
 Mill-0.318
 Joey-0.295
 unst-0.287
 scaven-0.285
Token They
Token ID1119
Feature activation-4.76e-01

Pos logit contributions
 wig+0.015
 aids+0.015
ggie+0.014
ggy+0.014
 song+0.014
Neg logit contributions
 sorts-0.012
 Mill-0.012
 Joey-0.011
neath-0.010
 Sus-0.010
Token have
Token ID423
Feature activation+2.13e+00

Pos logit contributions
 Mill+0.030
 sorts+0.029
 Joey+0.028
neath+0.027
 scaven+0.027
Neg logit contributions
 aids-0.035
 wig-0.035
 hair-0.034
 jokes-0.034
 song-0.032
Token a
Token ID257
Feature activation-6.11e-01

Pos logit contributions
 aids+0.180
 wig+0.170
 cheeks+0.159
 jokes+0.158
agging+0.153
Neg logit contributions
 sorts-0.117
 Mill-0.116
 Joey-0.107
 scaven-0.100
neath-0.100
Token big
Token ID1263
Feature activation-8.69e-01

Pos logit contributions
 sorts+0.040
 Mill+0.039
 scaven+0.036
 Joey+0.036
neath+0.035
Neg logit contributions
 aids-0.046
 wig-0.043
 hair-0.041
 jokes-0.041
 cheeks-0.040
Token it
Token ID340
Feature activation-2.96e+00

Pos logit contributions
 Mill+0.080
 sorts+0.079
 Joey+0.076
neath+0.073
 scaven+0.072
Neg logit contributions
 wig-0.058
 hair-0.057
 aids-0.056
 jokes-0.052
 song-0.050
Token up
Token ID510
Feature activation-4.15e+00

Pos logit contributions
 Mill+0.201
 sorts+0.200
 Joey+0.185
neath+0.184
 scaven+0.183
Neg logit contributions
 aids-0.205
 wig-0.199
 hair-0.197
 jokes-0.191
 song-0.183
Token and
Token ID290
Feature activation-1.58e+00

Pos logit contributions
 Mill+0.296
 sorts+0.295
 Joey+0.276
neath+0.272
 scaven+0.271
Neg logit contributions
 aids-0.275
 wig-0.266
 hair-0.262
 jokes-0.253
 song-0.241
Token down
Token ID866
Feature activation-1.26e+00

Pos logit contributions
 sorts+0.108
 Mill+0.107
 Joey+0.100
 scaven+0.099
neath+0.098
Neg logit contributions
 aids-0.109
 wig-0.106
 hair-0.104
 jokes-0.101
 song-0.096
Token.
Token ID13
Feature activation-4.86e-01

Pos logit contributions
 Mill+0.092
 sorts+0.092
 Joey+0.086
neath+0.085
 scaven+0.085
Neg logit contributions
 aids-0.081
 hair-0.077
 wig-0.077
 jokes-0.074
 song-0.070
Token Zip
Token ID38636
Feature activation+2.42e+00

Pos logit contributions
 Mill+0.035
 sorts+0.034
 Joey+0.033
neath+0.032
 scaven+0.031
Neg logit contributions
 aids-0.032
 wig-0.032
 hair-0.030
 jokes-0.030
 song-0.029
Token,
Token ID11
Feature activation-7.71e-01

Pos logit contributions
 aids+0.159
 wig+0.155
 hair+0.151
 jokes+0.147
 song+0.139
Neg logit contributions
 Mill-0.173
 sorts-0.172
 Joey-0.162
neath-0.159
 unst-0.157
Token zip
Token ID19974
Feature activation-1.50e-01

Pos logit contributions
 Mill+0.054
 sorts+0.054
 Joey+0.051
neath+0.050
 scaven+0.050
Neg logit contributions
 aids-0.052
 wig-0.050
 hair-0.049
 jokes-0.047
 song-0.045
Token,
Token ID11
Feature activation-6.30e-01

Pos logit contributions
 Mill+0.010
 sorts+0.010
 Joey+0.009
 scaven+0.009
neath+0.009
Neg logit contributions
 aids-0.011
 hair-0.011
 wig-0.011
 jokes-0.010
 song-0.010
Token zip
Token ID19974
Feature activation-4.22e-02

Pos logit contributions
 sorts+0.044
 Mill+0.044
 Joey+0.041
neath+0.040
 scaven+0.040
Neg logit contributions
 aids-0.043
 wig-0.042
 hair-0.041
 jokes-0.040
 song-0.038
Token!"
Token ID2474
Feature activation-3.33e+00

Pos logit contributions
 sorts+0.003
 Mill+0.003
 Joey+0.003
 scaven+0.003
neath+0.003
Neg logit contributions
 hair-0.003
 aids-0.003
 wig-0.003
 jokes-0.003
 song-0.002
Tokengy
Token ID1360
Feature activation-2.35e-01

Pos logit contributions
 sorts+0.292
 Mill+0.288
 Joey+0.264
neath+0.263
 scaven+0.259
Neg logit contributions
 aids-0.451
 wig-0.442
 hair-0.433
 jokes-0.423
 song-0.408
Token smiled
Token ID13541
Feature activation+1.38e+00

Pos logit contributions
 Mill+0.017
 sorts+0.016
 Joey+0.016
 scaven+0.015
neath+0.015
Neg logit contributions
 aids-0.016
 wig-0.015
 hair-0.015
 jokes-0.014
 song-0.014
Token and
Token ID290
Feature activation-1.90e-01

Pos logit contributions
 aids+0.100
 wig+0.097
 hair+0.092
 jokes+0.090
ggie+0.085
Neg logit contributions
 Mill-0.093
 sorts-0.092
 Joey-0.088
 unst-0.084
neath-0.083
Token said
Token ID531
Feature activation+1.53e-02

Pos logit contributions
 Mill+0.014
 sorts+0.014
 Joey+0.013
 scaven+0.012
 unst+0.012
Neg logit contributions
 aids-0.013
 wig-0.012
 hair-0.012
 jokes-0.011
 song-0.011
Token,
Token ID11
Feature activation-1.02e-01

Pos logit contributions
 aids+0.001
 wig+0.001
 hair+0.001
 jokes+0.001
 cheeks+0.001
Neg logit contributions
 Mill-0.001
 Joey-0.001
 sorts-0.001
 unst-0.001
 aback-0.001
Token "
Token ID366
Feature activation+5.01e-01

Pos logit contributions
 Mill+0.008
 Joey+0.007
 sorts+0.007
 Bobby+0.007
 unst+0.007
Neg logit contributions
 aids-0.007
 wig-0.007
 hair-0.006
 jokes-0.006
ggie-0.006
TokenMe
Token ID5308
Feature activation+1.25e+00

Pos logit contributions
 aids+0.039
 wig+0.037
 hair+0.037
 jokes+0.036
 cheeks+0.034
Neg logit contributions
 sorts-0.031
 Mill-0.031
 Joey-0.029
neath-0.028
 unst-0.027
Token too
Token ID1165
Feature activation+5.84e+00

Pos logit contributions
 aids+0.061
 wig+0.059
 hair+0.056
 jokes+0.054
 song+0.049
Neg logit contributions
 Mill-0.113
 sorts-0.112
 Joey-0.107
neath-0.104
 unst-0.104
Token,
Token ID11
Feature activation-1.03e-01

Pos logit contributions
 aids+0.422
 hair+0.415
 jokes+0.409
 wig+0.406
 song+0.398
Neg logit contributions
 sorts-0.363
neath-0.353
 Mill-0.349
 unst-0.339
 scaven-0.326
Token W
Token ID370
Feature activation-1.74e+00

Pos logit contributions
 sorts+0.007
aved+0.006
neath+0.006
ucer+0.006
rolley+0.006
Neg logit contributions
 jokes-0.007
 song-0.007
 hair-0.007
 aids-0.007
 songs-0.007
Tokenigg
Token ID6950
Feature activation-4.54e+00

Pos logit contributions
 sorts+0.106
 Mill+0.102
neath+0.097
 Joey+0.092
 aback+0.091
Neg logit contributions
 aids-0.136
 hair-0.131
 wig-0.129
 jokes-0.127
agging-0.122
TokenTim
Token ID14967
Feature activation-2.84e+00

Pos logit contributions
 Mill+0.041
 sorts+0.041
 Joey+0.039
 scaven+0.038
neath+0.037
Neg logit contributions
 wig-0.018
 aids-0.018
 hair-0.016
His-0.016
 jokes-0.015
Token and
Token ID290
Feature activation-5.02e-01

Pos logit contributions
 Mill+0.208
 sorts+0.206
 Joey+0.195
neath+0.190
 scaven+0.188
Neg logit contributions
 aids-0.185
 wig-0.181
 hair-0.176
 jokes-0.171
 song-0.161
Token Jen
Token ID13364
Feature activation+8.03e-01

Pos logit contributions
 Mill+0.031
 sorts+0.031
 Joey+0.029
 unst+0.028
 scaven+0.028
Neg logit contributions
 aids-0.039
 wig-0.038
 hair-0.036
 jokes-0.036
 song-0.035
Token are
Token ID389
Feature activation-3.45e+00

Pos logit contributions
 wig+0.052
 aids+0.052
 hair+0.052
 jokes+0.050
 song+0.047
Neg logit contributions
 Mill-0.059
 sorts-0.058
 Joey-0.054
neath-0.052
pling-0.051
Token sad
Token ID6507
Feature activation+3.70e+00

Pos logit contributions
 unst+0.216
 afloat+0.194
 sorts+0.192
 Mill+0.191
 deeper+0.190
Neg logit contributions
 aids-0.261
 wig-0.247
 cheeks-0.222
 jokes-0.220
 haircut-0.219
Token and
Token ID290
Feature activation-5.23e-01

Pos logit contributions
 aids+0.290
 wig+0.280
 hair+0.256
ggie+0.254
 jokes+0.250
Neg logit contributions
 sorts-0.225
 Mill-0.223
 Joey-0.212
 scaven-0.206
 unst-0.202
Token angry
Token ID7954
Feature activation+2.96e+00

Pos logit contributions
 sorts+0.040
 unst+0.039
 Mill+0.039
 Joey+0.038
 scaven+0.037
Neg logit contributions
 aids-0.032
 wig-0.031
 hair-0.028
ggie-0.028
 jokes-0.027
Token.
Token ID13
Feature activation+8.21e-02

Pos logit contributions
 aids+0.254
 wig+0.254
ggie+0.228
 haircut+0.227
 blond+0.225
Neg logit contributions
 sorts-0.150
 Mill-0.139
 Joey-0.138
 hed-0.137
 unst-0.130
Token They
Token ID1119
Feature activation-5.75e-01

Pos logit contributions
 aids+0.006
 wig+0.006
 hair+0.006
 jokes+0.005
 song+0.005
Neg logit contributions
 Mill-0.005
 sorts-0.005
 Joey-0.005
neath-0.005
 scaven-0.005
Token do
Token ID466
Feature activation+3.25e+00

Pos logit contributions
 Mill+0.043
 sorts+0.043
 Joey+0.040
neath+0.039
 scaven+0.039
Neg logit contributions
 aids-0.036
 wig-0.035
 hair-0.034
 jokes-0.034
 song-0.032
Token not
Token ID407
Feature activation+2.18e+00

Pos logit contributions
 wig+0.222
 blond+0.219
 cheeks+0.218
 aids+0.214
 hair+0.210
Neg logit contributions
 unst-0.208
 sorts-0.203
 least-0.200
neath-0.194
 retrieve-0.192
Token outing
Token ID32922
Feature activation-9.04e-01

Pos logit contributions
 sorts+0.167
 Mill+0.166
 Joey+0.154
 scaven+0.150
neath+0.146
Neg logit contributions
 aids-0.239
 wig-0.235
 hair-0.228
 jokes-0.219
 cheeks-0.212
Token to
Token ID284
Feature activation+1.00e+00

Pos logit contributions
 sorts+0.063
 Mill+0.063
 Joey+0.059
neath+0.058
 scaven+0.058
Neg logit contributions
 aids-0.062
 wig-0.060
 hair-0.058
 jokes-0.057
 song-0.054
Token the
Token ID262
Feature activation-7.20e-01

Pos logit contributions
 aids+0.061
 wig+0.061
 hair+0.060
 jokes+0.060
 song+0.055
Neg logit contributions
 sorts-0.073
 Mill-0.073
pling-0.070
aved-0.069
 scaven-0.069
Token opera
Token ID27296
Feature activation+3.79e+00

Pos logit contributions
 Mill+0.046
 sorts+0.046
 Joey+0.043
neath+0.042
 unst+0.042
Neg logit contributions
 aids-0.053
 wig-0.052
 hair-0.050
 jokes-0.050
 song-0.048
Token that
Token ID326
Feature activation+2.14e+00

Pos logit contributions
 aids+0.272
 wig+0.261
 hair+0.250
 jokes+0.246
 cheeks+0.240
Neg logit contributions
 sorts-0.260
 Mill-0.253
 Joey-0.229
 scaven-0.227
neath-0.221
Token evening
Token ID6180
Feature activation+3.37e-01

Pos logit contributions
 aids+0.118
 jokes+0.117
 hair+0.113
 wig+0.113
 song+0.111
Neg logit contributions
 aback-0.165
 Mill-0.162
neath-0.158
pling-0.157
arp-0.155
Token.
Token ID13
Feature activation+2.04e-01

Pos logit contributions
 aids+0.023
 wig+0.023
 hair+0.022
 jokes+0.021
 cheeks+0.020
Neg logit contributions
 sorts-0.024
 Mill-0.023
 Joey-0.022
 scaven-0.021
neath-0.021
Token Tom
Token ID4186
Feature activation-2.85e-01

Pos logit contributions
 aids+0.015
 wig+0.015
 song+0.014
 hair+0.013
 cheeks+0.013
Neg logit contributions
 sorts-0.014
 Joey-0.013
neath-0.012
 Mill-0.012
 scaven-0.012
Token was
Token ID373
Feature activation-4.38e-01

Pos logit contributions
 Mill+0.022
 sorts+0.022
 unst+0.022
neath+0.021
 hed+0.021
Neg logit contributions
 hair-0.015
 wig-0.015
 aids-0.015
 jokes-0.014
 clown-0.014
Token very
Token ID845
Feature activation+7.99e-01

Pos logit contributions
 sorts+0.028
 Mill+0.028
 Joey+0.026
 unst+0.025
 scaven+0.024
Neg logit contributions
 aids-0.034
 wig-0.033
 jokes-0.031
 cheeks-0.031
 hair-0.030
Token excited
Token ID6568
Feature activation-1.02e+00

Pos logit contributions
 aids+0.056
 wig+0.054
 hair+0.051
 jokes+0.051
 cheeks+0.049
Neg logit contributions
 sorts-0.056
 Mill-0.056
 Joey-0.054
 unst-0.051
 scaven-0.050
Token oy
Token ID35104
Feature activation-4.69e+00

Pos logit contributions
 Mill+0.117
 sorts+0.117
 Joey+0.111
 scaven+0.109
neath+0.106
Neg logit contributions
 aids-0.103
 wig-0.098
 hair-0.094
 jokes-0.092
 cheeks-0.086
Tokenster
Token ID1706
Feature activation-1.08e+00

Pos logit contributions
 Mill+0.344
 sorts+0.343
neath+0.322
 Joey+0.318
 unst+0.313
Neg logit contributions
 wig-0.306
 aids-0.297
 hair-0.290
 jokes-0.281
 song-0.267
Token.
Token ID13
Feature activation+8.46e-03

Pos logit contributions
 sorts+0.072
 Mill+0.069
 Joey+0.065
 scaven+0.063
pling+0.062
Neg logit contributions
 aids-0.081
 wig-0.075
 jokes-0.073
 hair-0.072
 cheeks-0.070
Token He
Token ID679
Feature activation+2.13e-01

Pos logit contributions
 aids+0.001
 wig+0.001
 hair+0.000
 jokes+0.000
 song+0.000
Neg logit contributions
 sorts-0.001
 Mill-0.001
 Joey-0.001
neath-0.001
 scaven-0.001
Token lived
Token ID5615
Feature activation-2.06e+00

Pos logit contributions
 aids+0.016
 wig+0.016
 hair+0.015
 jokes+0.015
 song+0.014
Neg logit contributions
 sorts-0.014
 Mill-0.013
 scaven-0.013
 Joey-0.012
neath-0.012
Token on
Token ID319
Feature activation+2.79e+00

Pos logit contributions
 Mill+0.161
 sorts+0.158
 Joey+0.150
neath+0.147
 scaven+0.144
Neg logit contributions
 wig-0.122
 aids-0.121
 hair-0.119
 jokes-0.113
 song-0.109
Token the
Token ID262
Feature activation-9.65e-01

Pos logit contributions
 aids+0.184
 wig+0.179
 hair+0.178
 jokes+0.171
 song+0.161
Neg logit contributions
 sorts-0.200
 Mill-0.199
 Joey-0.185
 unst-0.184
neath-0.182
Token beach
Token ID10481
Feature activation-2.55e+00

Pos logit contributions
 Mill+0.051
 sorts+0.051
 Joey+0.046
neath+0.045
 unst+0.045
Neg logit contributions
 aids-0.082
 wig-0.081
 hair-0.079
 jokes-0.077
 song-0.075
Token and
Token ID290
Feature activation-6.34e-01

Pos logit contributions
 sorts+0.184
 Mill+0.179
 Joey+0.170
 scaven+0.167
neath+0.164
Neg logit contributions
 aids-0.172
 wig-0.165
 hair-0.158
 jokes-0.155
 song-0.146
Token every
Token ID790
Feature activation+4.60e-01

Pos logit contributions
 sorts+0.047
 Mill+0.047
 Joey+0.044
neath+0.043
 scaven+0.043
Neg logit contributions
 aids-0.041
 wig-0.040
 hair-0.038
 jokes-0.037
 song-0.035
Token day
Token ID1110
Feature activation+7.33e-01

Pos logit contributions
 aids+0.040
 wig+0.038
 hair+0.037
 jokes+0.036
 cheeks+0.035
Neg logit contributions
 sorts-0.026
 Joey-0.025
 Mill-0.024
 scaven-0.023
neath-0.022
Token.
Token ID13
Feature activation+1.70e-01

Pos logit contributions
 hair+0.019
 aids+0.019
 wig+0.017
 jokes+0.017
 song+0.016
Neg logit contributions
 sorts-0.040
 Mill-0.039
neath-0.039
 aback-0.038
 scaven-0.037
Token Lily
Token ID20037
Feature activation+9.62e-01

Pos logit contributions
 aids+0.011
 wig+0.011
 hair+0.011
 jokes+0.010
 song+0.010
Neg logit contributions
 Mill-0.012
 sorts-0.012
 Joey-0.012
neath-0.011
 scaven-0.011
Token wanted
Token ID2227
Feature activation+1.49e-01

Pos logit contributions
 aids+0.060
 wig+0.058
 hair+0.057
 jokes+0.055
 song+0.052
Neg logit contributions
 Mill-0.072
 sorts-0.072
 Joey-0.068
neath-0.067
 unst-0.066
Token to
Token ID284
Feature activation+9.12e-01

Pos logit contributions
 hair+0.008
 aids+0.008
 wig+0.008
 jokes+0.008
 song+0.007
Neg logit contributions
 sorts-0.012
 Mill-0.012
neath-0.011
 Joey-0.011
 unst-0.011
Token use
Token ID779
Feature activation-1.89e+00

Pos logit contributions
 aids+0.060
 wig+0.059
 hair+0.058
 jokes+0.056
 song+0.053
Neg logit contributions
 Mill-0.065
 sorts-0.065
 Joey-0.061
neath-0.060
 scaven-0.059
Token it
Token ID340
Feature activation-1.40e+00

Pos logit contributions
 sorts+0.133
 Mill+0.130
 scaven+0.126
rolley+0.126
wood+0.124
Neg logit contributions
 hair-0.129
 aids-0.121
 wig-0.115
 jokes-0.114
 cheeks-0.104
Token as
Token ID355
Feature activation+3.17e+00

Pos logit contributions
 sorts+0.115
 Mill+0.111
neath+0.109
rolley+0.107
 Joey+0.104
Neg logit contributions
 hair-0.074
 jokes-0.069
 aids-0.069
 wig-0.068
 song-0.064
Token a
Token ID257
Feature activation-6.55e-01

Pos logit contributions
 hair+0.180
 jokes+0.173
 aids+0.172
 wig+0.166
ggie+0.166
Neg logit contributions
 sorts-0.251
 Mill-0.240
 aback-0.238
neath-0.234
 unst-0.232
Token sword
Token ID8429
Feature activation+2.10e-01

Pos logit contributions
 Mill+0.044
 sorts+0.044
 Joey+0.042
 scaven+0.041
neath+0.041
Neg logit contributions
 aids-0.046
 wig-0.044
 hair-0.043
 jokes-0.042
 song-0.040
Token,
Token ID11
Feature activation-4.08e-01

Pos logit contributions
 aids+0.014
 wig+0.013
 hair+0.013
 jokes+0.013
 song+0.012
Neg logit contributions
 sorts-0.015
 Mill-0.015
 Joey-0.014
neath-0.014
 scaven-0.014
Token but
Token ID475
Feature activation+2.12e-01

Pos logit contributions
 sorts+0.029
 Mill+0.029
 Joey+0.027
neath+0.027
 scaven+0.027
Neg logit contributions
 aids-0.027
 wig-0.026
 hair-0.026
 jokes-0.025
 song-0.024
Token shiny
Token ID22441
Feature activation-2.28e+00

Pos logit contributions
 sorts+0.079
 Mill+0.079
 Joey+0.075
neath+0.074
 scaven+0.073
Neg logit contributions
 aids-0.069
 hair-0.067
 wig-0.067
 jokes-0.064
 song-0.061
Token and
Token ID290
Feature activation-7.80e-01

Pos logit contributions
 Mill+0.190
 sorts+0.187
 Joey+0.179
neath+0.177
 scaven+0.175
Neg logit contributions
 hair-0.130
 wig-0.122
 aids-0.118
 jokes-0.115
 song-0.109
Token hard
Token ID1327
Feature activation-3.02e+00

Pos logit contributions
 Mill+0.060
 sorts+0.060
 scaven+0.058
neath+0.058
 Joey+0.057
Neg logit contributions
 hair-0.044
 aids-0.044
 wig-0.044
 jokes-0.042
 song-0.041
Token.
Token ID13
Feature activation-5.31e-02

Pos logit contributions
 Mill+0.229
 sorts+0.229
 Joey+0.217
neath+0.214
 unst+0.211
Neg logit contributions
 aids-0.183
 hair-0.179
 wig-0.178
 jokes-0.170
 song-0.160
Token They
Token ID1119
Feature activation-6.57e-01

Pos logit contributions
 Mill+0.004
 sorts+0.004
 Joey+0.004
neath+0.004
 scaven+0.004
Neg logit contributions
 aids-0.003
 wig-0.003
 hair-0.003
 jokes-0.003
 song-0.003
Token want
Token ID765
Feature activation-1.36e+00

Pos logit contributions
 Mill+0.043
 sorts+0.043
 Joey+0.040
 scaven+0.039
 unst+0.039
Neg logit contributions
 aids-0.047
 hair-0.046
 wig-0.046
 jokes-0.044
 cheeks-0.042
Token to
Token ID284
Feature activation+8.40e-01

Pos logit contributions
 sorts+0.101
 Mill+0.101
 Joey+0.095
neath+0.093
 scaven+0.092
Neg logit contributions
 aids-0.088
 wig-0.085
 hair-0.083
 jokes-0.081
 song-0.076
Token climb
Token ID12080
Feature activation-1.37e+00

Pos logit contributions
 aids+0.063
 wig+0.059
 jokes+0.057
 hair+0.056
 cheeks+0.054
Neg logit contributions
 Mill-0.055
 sorts-0.055
 Joey-0.051
neath-0.049
 unst-0.049
Token on
Token ID319
Feature activation+2.94e+00

Pos logit contributions
 sorts+0.103
 Mill+0.098
 scaven+0.094
pling+0.092
 aback+0.091
Neg logit contributions
 hair-0.089
 wig-0.082
 aids-0.080
 jokes-0.078
 clown-0.075
Token it
Token ID340
Feature activation-1.38e+00

Pos logit contributions
 hair+0.186
 aids+0.163
 wig+0.163
 jokes+0.162
 song+0.151
Neg logit contributions
 sorts-0.228
 Mill-0.218
pling-0.212
 aback-0.210
 Joey-0.209
Token.
Token ID13
Feature activation+1.77e-01

Pos logit contributions
 Mill+0.115
 sorts+0.113
 Joey+0.110
neath+0.108
 scaven+0.107
Neg logit contributions
 hair-0.071
 aids-0.071
 wig-0.069
 jokes-0.067
 song-0.065
Token said
Token ID531
Feature activation-3.20e-01

Pos logit contributions
 Mill+0.070
 sorts+0.070
 Joey+0.066
neath+0.065
 scaven+0.064
Neg logit contributions
 aids-0.058
 wig-0.057
 hair-0.056
 jokes-0.054
 song-0.051
Token to
Token ID284
Feature activation+8.56e-01

Pos logit contributions
 Mill+0.017
 Joey+0.016
 Bobby+0.014
 unst+0.014
 if+0.013
Neg logit contributions
 aids-0.027
 wig-0.027
ggie-0.024
 hair-0.024
 song-0.024
Token Rose
Token ID8049
Feature activation+1.37e+00

Pos logit contributions
 aids+0.064
 wig+0.060
 hair+0.057
ggie+0.055
 song+0.055
Neg logit contributions
 Mill-0.055
 Joey-0.052
 sorts-0.052
neath-0.051
 scaven-0.049
Token,
Token ID11
Feature activation-4.51e-01

Pos logit contributions
 aids+0.091
 wig+0.088
 hair+0.086
 jokes+0.084
 song+0.079
Neg logit contributions
 sorts-0.098
 Mill-0.098
 Joey-0.092
neath-0.090
 scaven-0.089
Token "
Token ID366
Feature activation+1.52e-01

Pos logit contributions
 Mill+0.030
 Joey+0.027
 unst+0.026
neath+0.026
 sorts+0.026
Neg logit contributions
 aids-0.034
 wig-0.031
 jokes-0.030
ggie-0.030
 hair-0.030
TokenI
Token ID40
Feature activation-1.16e+00

Pos logit contributions
 aids+0.013
 wig+0.013
 jokes+0.013
 hair+0.013
 cheeks+0.012
Neg logit contributions
 sorts-0.008
 Mill-0.007
neath-0.007
'll-0.007
 aback-0.007
Token'm
Token ID1101
Feature activation-8.26e-01

Pos logit contributions
 Mill+0.076
neath+0.076
 sorts+0.074
 Joey+0.072
 scaven+0.072
Neg logit contributions
 wig-0.082
 hair-0.081
 jokes-0.079
 aids-0.078
 song-0.075
Token sorry
Token ID7926
Feature activation+2.60e+00

Pos logit contributions
 Mill+0.075
 sorts+0.072
 Joey+0.071
 unst+0.068
neath+0.067
Neg logit contributions
 aids-0.042
 wig-0.041
 hair-0.038
 jokes-0.037
 cheeks-0.036
Token I
Token ID314
Feature activation+3.90e-01

Pos logit contributions
 aids+0.207
 wig+0.198
 hair+0.186
 jokes+0.180
ggie+0.176
Neg logit contributions
 Mill-0.159
 sorts-0.150
 Joey-0.148
 unst-0.139
 scaven-0.138
Token lost
Token ID2626
Feature activation-4.73e+00

Pos logit contributions
 aids+0.024
 wig+0.024
 hair+0.023
 jokes+0.023
 song+0.021
Neg logit contributions
 Mill-0.030
 sorts-0.030
 Joey-0.028
neath-0.028
 scaven-0.027
Token you
Token ID345
Feature activation-1.06e+00

Pos logit contributions
 Mill+0.339
 sorts+0.335
 Joey+0.318
 unst+0.307
neath+0.306
Neg logit contributions
 aids-0.314
 wig-0.303
 hair-0.290
 jokes-0.286
 song-0.271
Token on
Token ID319
Feature activation+3.22e+00

Pos logit contributions
 Mill+0.079
 sorts+0.079
 Joey+0.074
 scaven+0.072
neath+0.072
Neg logit contributions
 aids-0.088
 wig-0.085
 hair-0.083
 jokes-0.081
 song-0.077
Token many
Token ID867
Feature activation-4.25e+00

Pos logit contributions
 aids+0.217
 wig+0.212
 hair+0.211
 jokes+0.204
 song+0.192
Neg logit contributions
 Mill-0.227
 sorts-0.225
 Joey-0.213
neath-0.208
 unst-0.207
Token adventures
Token ID17545
Feature activation-2.32e-01

Pos logit contributions
 sorts+0.241
 Mill+0.209
 scaven+0.209
 hed+0.188
 Joey+0.186
Neg logit contributions
 aids-0.374
 wig-0.359
 cheeks-0.335
 hair-0.332
 jokes-0.327
Token and
Token ID290
Feature activation-1.97e-01

Pos logit contributions
 sorts+0.017
 Mill+0.017
 Joey+0.016
neath+0.015
 scaven+0.015
Neg logit contributions
 aids-0.016
 wig-0.015
 hair-0.015
 jokes-0.014
 song-0.014
Token met
Token ID1138
Feature activation+1.41e+00

Pos logit contributions
 sorts+0.013
 Mill+0.013
 Joey+0.012
 scaven+0.012
neath+0.011
Neg logit contributions
 aids-0.015
 wig-0.014
 hair-0.014
 jokes-0.013
 song-0.013
Token lots
Token ID6041
Feature activation-5.87e+00

Pos logit contributions
 aids+0.100
 wig+0.097
 hair+0.094
 jokes+0.092
 song+0.088
Neg logit contributions
 sorts-0.094
 Mill-0.094
 Joey-0.088
neath-0.086
 scaven-0.085
Token of
Token ID286
Feature activation+3.65e-01

Pos logit contributions
 sorts+0.361
 Mill+0.343
 Joey+0.320
 scaven+0.312
 unst+0.298
Neg logit contributions
 aids-0.464
 wig-0.456
 hair-0.434
 jokes-0.414
 cheeks-0.412
Token friends
Token ID2460
Feature activation+2.05e+00

Pos logit contributions
 aids+0.023
 wig+0.022
 hair+0.021
 jokes+0.020
 cheeks+0.020
Neg logit contributions
 sorts-0.028
 Mill-0.027
 Joey-0.026
 scaven-0.025
neath-0.025
Token.
Token ID13
Feature activation+4.01e-01

Pos logit contributions
 aids+0.150
 wig+0.142
 hair+0.136
 jokes+0.132
 cheeks+0.130
Neg logit contributions
 sorts-0.140
 Mill-0.138
 Joey-0.130
 scaven-0.124
neath-0.123
Token
Token ID198
Feature activation-1.50e-01

Pos logit contributions
 wig+0.033
 aids+0.032
 hair+0.031
 jokes+0.030
 cheeks+0.030
Neg logit contributions
 sorts-0.024
 Mill-0.023
 Joey-0.021
neath-0.020
wood-0.019
Token
Token ID198
Feature activation-1.56e-01

Pos logit contributions
 sorts+0.010
 Mill+0.009
 Joey+0.009
neath+0.009
 scaven+0.009
Neg logit contributions
 aids-0.011
 wig-0.011
 hair-0.011
 jokes-0.010
 cheeks-0.010
Token is
Token ID318
Feature activation-5.77e-01

Pos logit contributions
 Mill+0.049
 sorts+0.047
 scaven+0.046
 unst+0.046
neath+0.045
Neg logit contributions
 aids-0.045
 hair-0.043
 jokes-0.043
 wig-0.042
 song-0.040
Token a
Token ID257
Feature activation-6.21e-01

Pos logit contributions
 Mill+0.039
 sorts+0.039
 Joey+0.036
neath+0.036
 scaven+0.035
Neg logit contributions
 aids-0.041
 wig-0.040
 hair-0.039
 jokes-0.038
 song-0.036
Token good
Token ID922
Feature activation-2.45e+00

Pos logit contributions
 Mill+0.047
neath+0.047
 sorts+0.047
 Joey+0.045
aved+0.045
Neg logit contributions
 wig-0.037
 hair-0.037
 aids-0.036
 song-0.036
 jokes-0.035
Token thing
Token ID1517
Feature activation+2.30e+00

Pos logit contributions
neath+0.187
 Mill+0.184
 unst+0.178
aved+0.175
 sorts+0.175
Neg logit contributions
 hair-0.156
 song-0.148
 wig-0.148
 jokes-0.147
 aids-0.143
Token,
Token ID11
Feature activation-3.93e-01

Pos logit contributions
 aids+0.171
 wig+0.166
 hair+0.161
 jokes+0.155
 cheeks+0.149
Neg logit contributions
 Mill-0.147
 sorts-0.146
 Joey-0.136
 scaven-0.130
neath-0.128
Token don
Token ID836
Feature activation-4.66e+00

Pos logit contributions
 Mill+0.026
 sorts+0.026
 Joey+0.025
 unst+0.024
 scaven+0.023
Neg logit contributions
 aids-0.028
 wig-0.027
 hair-0.026
 jokes-0.025
 cheeks-0.024
Token't
Token ID470
Feature activation+1.77e+00

Pos logit contributions
 Mill+0.382
 sorts+0.382
 Joey+0.362
neath+0.356
 scaven+0.354
Neg logit contributions
 aids-0.259
 wig-0.251
 hair-0.242
 jokes-0.234
 song-0.219
Token you
Token ID345
Feature activation-9.82e-01

Pos logit contributions
 aids+0.126
 wig+0.122
 hair+0.115
 jokes+0.110
agged+0.108
Neg logit contributions
 Mill-0.118
 sorts-0.117
 Joey-0.112
 scaven-0.105
 unst-0.104
Token think
Token ID892
Feature activation-1.38e+00

Pos logit contributions
 sorts+0.060
 Mill+0.059
 Joey+0.055
 scaven+0.053
neath+0.053
Neg logit contributions
 aids-0.076
 wig-0.074
 hair-0.071
 jokes-0.070
 song-0.067
Token?"
Token ID1701
Feature activation+3.32e+00

Pos logit contributions
 Mill+0.078
 sorts+0.076
 Joey+0.075
neath+0.068
 scaven+0.066
Neg logit contributions
 wig-0.111
 aids-0.105
 hair-0.101
 cheeks-0.098
agged-0.095
Token
Token ID198
Feature activation-4.28e-01

Pos logit contributions
 aids+0.289
 wig+0.277
agging+0.271
ggie+0.264
 song+0.263
Neg logit contributions
 Mill-0.188
 Joey-0.186
 sorts-0.158
 Bobby-0.156
 Suz-0.154
Token use
Token ID779
Feature activation-1.87e+00

Pos logit contributions
 Mill+0.065
rolley+0.060
 extingu+0.059
 sorts+0.059
 Joey+0.059
Neg logit contributions
 jokes-0.062
 hair-0.061
 aids-0.060
 song-0.059
 tricks-0.058
Token your
Token ID534
Feature activation-3.68e-01

Pos logit contributions
 Mill+0.139
 sorts+0.137
aved+0.135
arp+0.131
pling+0.131
Neg logit contributions
 hair-0.119
 aids-0.114
 jokes-0.113
 wig-0.104
 song-0.101
Token brain
Token ID3632
Feature activation+2.35e+00

Pos logit contributions
 Mill+0.032
 sorts+0.032
 Joey+0.030
neath+0.030
 scaven+0.029
Neg logit contributions
 aids-0.019
 wig-0.018
 hair-0.018
 jokes-0.017
 song-0.016
Token,
Token ID11
Feature activation-3.88e-01

Pos logit contributions
 hair+0.142
 aids+0.142
 wig+0.134
 jokes+0.134
 song+0.128
Neg logit contributions
 Mill-0.179
 sorts-0.170
 Joey-0.169
neath-0.169
 scaven-0.161
Token even
Token ID772
Feature activation-3.61e+00

Pos logit contributions
 Mill+0.029
 sorts+0.029
aved+0.028
neath+0.028
ucer+0.027
Neg logit contributions
 hair-0.023
 aids-0.023
 jokes-0.023
 wig-0.022
 song-0.021
Token if
Token ID611
Feature activation-7.95e+00

Pos logit contributions
 Mill+0.158
 sorts+0.154
 Joey+0.140
neath+0.139
 scaven+0.133
Neg logit contributions
 aids-0.336
 wig-0.332
 hair-0.330
 jokes-0.324
 song-0.313
Token you
Token ID345
Feature activation-9.78e-01

Pos logit contributions
 sorts+0.527
 Mill+0.514
neath+0.480
 unst+0.478
 Joey+0.471
Neg logit contributions
 aids-0.569
 wig-0.551
 hair-0.549
 jokes-0.546
 song-0.510
Token cannot
Token ID2314
Feature activation+1.67e-01

Pos logit contributions
 Mill+0.067
 sorts+0.063
 Joey+0.060
rolley+0.058
neath+0.058
Neg logit contributions
 aids-0.066
 jokes-0.066
 hair-0.066
 wig-0.063
 song-0.061
Token use
Token ID779
Feature activation-1.91e+00

Pos logit contributions
 aids+0.011
 wig+0.011
 hair+0.011
 jokes+0.010
 song+0.010
Neg logit contributions
 sorts-0.012
 Mill-0.012
 Joey-0.011
neath-0.011
 scaven-0.011
Token your
Token ID534
Feature activation-4.09e-01

Pos logit contributions
 Mill+0.138
 sorts+0.138
 Joey+0.128
aved+0.128
 scaven+0.127
Neg logit contributions
 hair-0.124
 aids-0.123
 jokes-0.118
 wig-0.116
 song-0.107
Token eyes
Token ID2951
Feature activation+6.35e+00

Pos logit contributions
 sorts+0.035
 Mill+0.034
 Joey+0.033
 scaven+0.033
 unst+0.032
Neg logit contributions
 aids-0.021
 wig-0.021
 hair-0.019
 jokes-0.019
ggie-0.018
Token.
Token ID13
Feature activation+2.52e-01

Pos logit contributions
 aids+0.197
 wig+0.191
 hair+0.180
 jokes+0.174
 cheeks+0.172
Neg logit contributions
 sorts-0.183
 Mill-0.174
 scaven-0.164
 Joey-0.163
 unst-0.162
Token They
Token ID1119
Feature activation-3.90e-01

Pos logit contributions
 wig+0.023
ggy+0.022
ggie+0.022
agging+0.021
 aids+0.021
Neg logit contributions
 Mill-0.014
 Joey-0.013
 sorts-0.013
 Suz-0.012
neath-0.011
Token had
Token ID550
Feature activation+1.15e+00

Pos logit contributions
 sorts+0.026
 Mill+0.026
 Joey+0.025
 scaven+0.024
neath+0.024
Neg logit contributions
 aids-0.028
 wig-0.027
 hair-0.026
 jokes-0.026
 song-0.025
Token a
Token ID257
Feature activation-4.97e-01

Pos logit contributions
 aids+0.096
 wig+0.094
 cheeks+0.087
 jokes+0.087
 song+0.084
Neg logit contributions
 sorts-0.063
 Mill-0.063
 scaven-0.055
 Joey-0.054
 unst-0.053
Token big
Token ID1263
Feature activation-7.30e-01

Pos logit contributions
 sorts+0.029
 Mill+0.029
 scaven+0.028
 unst+0.025
 Joey+0.025
Neg logit contributions
 aids-0.040
 wig-0.037
 jokes-0.037
agged-0.035
 cheeks-0.035
Token box
Token ID3091
Feature activation-7.40e+00

Pos logit contributions
 sorts+0.050
 Mill+0.048
 scaven+0.045
 Joey+0.044
 unst+0.044
Neg logit contributions
 aids-0.052
 wig-0.049
 jokes-0.047
ggie-0.045
 hair-0.045
Token of
Token ID286
Feature activation+2.81e-01

Pos logit contributions
 sorts+0.461
 Mill+0.456
 Joey+0.415
 scaven+0.406
neath+0.404
Neg logit contributions
 aids-0.572
 wig-0.553
 jokes-0.534
 hair-0.525
 cheeks-0.498
Token trains
Token ID13404
Feature activation+2.85e+00

Pos logit contributions
 aids+0.017
 hair+0.016
 wig+0.016
 jokes+0.016
 song+0.015
Neg logit contributions
 Mill-0.022
 sorts-0.021
 Joey-0.021
neath-0.021
 scaven-0.020
Token and
Token ID290
Feature activation-2.66e-01

Pos logit contributions
 aids+0.189
 wig+0.183
 hair+0.178
 jokes+0.173
 song+0.164
Neg logit contributions
 Mill-0.205
 sorts-0.205
 Joey-0.193
neath-0.188
 scaven-0.187
Token tracks
Token ID8339
Feature activation-6.72e-01

Pos logit contributions
 sorts+0.019
 Mill+0.018
 Joey+0.017
 scaven+0.017
neath+0.016
Neg logit contributions
 aids-0.018
 wig-0.018
 hair-0.017
 jokes-0.016
 song-0.016
Token that
Token ID326
Feature activation+2.28e+00

Pos logit contributions
 sorts+0.046
 Mill+0.046
 Joey+0.043
neath+0.043
 scaven+0.042
Neg logit contributions
 aids-0.046
 wig-0.045
 hair-0.043
 jokes-0.042
 song-0.040
Token out
Token ID503
Feature activation-4.33e+00

Pos logit contributions
 aids+0.204
 wig+0.198
 hair+0.193
 jokes+0.189
 song+0.179
Neg logit contributions
 Mill-0.211
 sorts-0.210
 Joey-0.197
neath-0.194
 scaven-0.192
Token loud
Token ID7812
Feature activation+3.81e+00

Pos logit contributions
 sorts+0.286
 Mill+0.284
 Joey+0.262
neath+0.255
 unst+0.254
Neg logit contributions
 wig-0.318
 aids-0.317
 hair-0.298
 jokes-0.287
 cheeks-0.278
Token,
Token ID11
Feature activation-2.81e-01

Pos logit contributions
 aids+0.272
 wig+0.270
 hair+0.246
 jokes+0.238
ggie+0.237
Neg logit contributions
 sorts-0.251
 Mill-0.247
 Joey-0.231
 scaven-0.226
neath-0.220
Token which
Token ID543
Feature activation+2.32e+00

Pos logit contributions
 Mill+0.020
 sorts+0.020
 Joey+0.019
neath+0.018
 scaven+0.018
Neg logit contributions
 aids-0.019
 wig-0.018
 hair-0.018
 jokes-0.017
 song-0.016
Token disturbed
Token ID24069
Feature activation+1.69e+00

Pos logit contributions
 aids+0.141
 jokes+0.133
 hair+0.131
 song+0.130
 wig+0.129
Neg logit contributions
 unst-0.164
 scaven-0.162
 Mill-0.162
 sorts-0.156
 Joey-0.156
Token Mill
Token ID9212
Feature activation-8.95e+00

Pos logit contributions
 aids+0.118
 hair+0.112
 jokes+0.112
 song+0.105
 wig+0.105
Neg logit contributions
 scaven-0.109
 sorts-0.108
 unst-0.105
neath-0.104
pling-0.102
Tokenie
Token ID494
Feature activation+2.21e+00

Pos logit contributions
 sorts+0.622
 unst+0.608
 Mill+0.604
 scaven+0.590
neath+0.583
Neg logit contributions
 aids-0.560
 hair-0.546
 wig-0.540
 jokes-0.540
 song-0.521
Token.
Token ID13
Feature activation+2.38e-01

Pos logit contributions
 aids+0.144
 wig+0.141
 hair+0.135
 jokes+0.131
 song+0.124
Neg logit contributions
 sorts-0.161
 Mill-0.160
 Joey-0.150
 scaven-0.147
neath-0.146
Token
Token ID198
Feature activation-3.26e-01

Pos logit contributions
 aids+0.013
 hair+0.012
 Her+0.012
 His+0.011
 cheeks+0.011
Neg logit contributions
 scaven-0.019
 sorts-0.019
 unst-0.018
ucer-0.018
pling-0.017
Token
Token ID198
Feature activation-3.39e-01

Pos logit contributions
 sorts+0.028
 unst+0.028
 scaven+0.027
wood+0.027
neath+0.026
Neg logit contributions
 aids-0.015
Her-0.014
 hair-0.014
His-0.013
 wig-0.013
TokenMill
Token ID22603
Feature activation-6.86e+00

Pos logit contributions
 sorts+0.021
 scaven+0.020
 unst+0.019
 Joey+0.019
 Mill+0.019
Neg logit contributions
 aids-0.025
Her-0.023
 hair-0.023
 song-0.023
 wig-0.022
Token were
Token ID547
Feature activation-3.35e+00

Pos logit contributions
 sorts+0.010
 Mill+0.010
 Joey+0.009
neath+0.009
 scaven+0.009
Neg logit contributions
 aids-0.009
 wig-0.009
 hair-0.009
 jokes-0.008
 cheeks-0.008
Token happy
Token ID3772
Feature activation+1.22e+00

Pos logit contributions
 unst+0.197
 Mill+0.188
 sorts+0.178
 aback+0.176
 scaven+0.175
Neg logit contributions
 aids-0.249
 wig-0.247
 jokes-0.230
 cheeks-0.226
 song-0.219
Token.
Token ID13
Feature activation+3.41e-01

Pos logit contributions
 aids+0.093
 wig+0.089
 hair+0.084
ggie+0.082
 jokes+0.080
Neg logit contributions
 Mill-0.076
 sorts-0.075
 Joey-0.072
 scaven-0.068
 unst-0.067
Token They
Token ID1119
Feature activation-3.19e-01

Pos logit contributions
 aids+0.024
 wig+0.024
 hair+0.023
 jokes+0.022
 song+0.021
Neg logit contributions
 Mill-0.023
 sorts-0.023
 Joey-0.022
neath-0.021
 scaven-0.021
Token had
Token ID550
Feature activation+1.19e+00

Pos logit contributions
 sorts+0.029
 Mill+0.029
wood+0.028
 Joey+0.027
neath+0.027
Neg logit contributions
 wig-0.016
 hair-0.015
 jokes-0.014
 aids-0.014
 clown-0.013
Token saved
Token ID7448
Feature activation-7.21e+00

Pos logit contributions
 aids+0.088
 wig+0.086
 hair+0.082
 jokes+0.081
 song+0.078
Neg logit contributions
 Mill-0.077
 sorts-0.077
 Joey-0.072
 unst-0.071
 scaven-0.070
Token their
Token ID511
Feature activation+7.65e-01

Pos logit contributions
 sorts+0.599
aved+0.587
neath+0.583
pling+0.573
 Mill+0.571
Neg logit contributions
 hair-0.423
 aids-0.382
 jokes-0.382
 wig-0.359
 song-0.343
Token truck
Token ID7779
Feature activation-2.25e-01

Pos logit contributions
 aids+0.047
 wig+0.046
 hair+0.046
 jokes+0.045
 song+0.042
Neg logit contributions
 Mill-0.058
 sorts-0.058
 Joey-0.055
neath-0.054
 scaven-0.052
Token and
Token ID290
Feature activation-2.97e-01

Pos logit contributions
 Mill+0.020
 sorts+0.019
neath+0.019
 Joey+0.019
 scaven+0.018
Neg logit contributions
 aids-0.011
 hair-0.011
 wig-0.011
 jokes-0.011
 song-0.010
Token their
Token ID511
Feature activation+7.59e-01

Pos logit contributions
 sorts+0.022
 Mill+0.022
neath+0.021
 Joey+0.021
 scaven+0.021
Neg logit contributions
 hair-0.018
 aids-0.018
 wig-0.018
 jokes-0.018
 song-0.017
Token rocks
Token ID12586
Feature activation-3.45e+00

Pos logit contributions
 aids+0.042
 wig+0.041
 hair+0.041
 jokes+0.040
 song+0.037
Neg logit contributions
 Mill-0.062
 sorts-0.062
 Joey-0.059
neath-0.059
 aback-0.057
Token help
Token ID1037
Feature activation-2.99e+00

Pos logit contributions
 aids+0.087
 wig+0.085
 hair+0.083
 jokes+0.079
 cheeks+0.077
Neg logit contributions
 Mill-0.078
 sorts-0.077
 Joey-0.073
 unst-0.068
neath-0.068
Token.
Token ID13
Feature activation+4.29e-01

Pos logit contributions
 sorts+0.189
 Mill+0.188
 Joey+0.175
neath+0.172
 scaven+0.171
Neg logit contributions
 aids-0.224
 wig-0.218
 hair-0.212
 jokes-0.208
 song-0.198
Token Is
Token ID1148
Feature activation+1.90e+00

Pos logit contributions
 aids+0.029
 wig+0.028
 hair+0.028
 jokes+0.027
 song+0.026
Neg logit contributions
 sorts-0.030
 Mill-0.029
 Joey-0.028
neath-0.027
 scaven-0.027
Token it
Token ID340
Feature activation-1.11e+00

Pos logit contributions
 aids+0.137
 wig+0.134
 hair+0.130
 jokes+0.126
 song+0.121
Neg logit contributions
 Mill-0.125
 sorts-0.124
 Joey-0.116
neath-0.113
 scaven-0.112
Token OK
Token ID7477
Feature activation-1.12e+00

Pos logit contributions
 sorts+0.076
 Mill+0.075
 Joey+0.070
neath+0.069
 scaven+0.069
Neg logit contributions
 aids-0.076
 wig-0.073
 hair-0.072
 jokes-0.071
 song-0.068
Token if
Token ID611
Feature activation-7.66e+00

Pos logit contributions
 Mill+0.070
 sorts+0.066
 Joey+0.064
'll+0.059
 unst+0.057
Neg logit contributions
 aids-0.089
 wig-0.088
 hair-0.084
 jokes-0.081
 cheeks-0.080
Token I
Token ID314
Feature activation+7.61e-01

Pos logit contributions
 sorts+0.476
 Mill+0.473
 Joey+0.440
neath+0.433
 scaven+0.430
Neg logit contributions
 aids-0.578
 wig-0.563
 hair-0.549
 jokes-0.539
 song-0.515
Token talk
Token ID1561
Feature activation+3.37e+00

Pos logit contributions
 aids+0.050
 jokes+0.050
 hair+0.050
 wig+0.049
 face+0.047
Neg logit contributions
 Mill-0.048
 sorts-0.048
 hed-0.046
neath-0.045
 scaven-0.044
Token to
Token ID284
Feature activation+1.20e+00

Pos logit contributions
 aids+0.247
 wig+0.246
 hair+0.232
 cheeks+0.227
 jokes+0.224
Neg logit contributions
 sorts-0.214
 Mill-0.213
 Joey-0.196
'll-0.191
neath-0.186
Token you
Token ID345
Feature activation-6.71e-01

Pos logit contributions
 wig+0.090
 aids+0.089
 hair+0.085
 jokes+0.082
 cheeks+0.080
Neg logit contributions
 Mill-0.078
 sorts-0.073
 Joey-0.071
neath-0.066
 scaven-0.064
Token?"
Token ID1701
Feature activation+3.63e+00

Pos logit contributions
 Mill+0.042
 sorts+0.041
 Joey+0.039
neath+0.037
 scaven+0.037
Neg logit contributions
 aids-0.050
 wig-0.050
 hair-0.048
 jokes-0.046
 cheeks-0.045