TOP ACTIVATIONS
MAX = 12.882

this power would come in handy . He was
was very happy because the handy man had helped her .
. The cart came in handy to carry all of the
a time there was a handy man who had a fancy
is that friends come in handy in times of need .
Maybe it will come in handy one day !"
<|endoftext|> Grand pa was a handy man and he had lots
. Then the handy man drove to the young
compassionate act would come in handy a few days later when
it 's important to keep hed ges neat and tidy "
stood back and admired their handy work . The screw was
stepped back to admire his handy work . "
. So the handy man went to the teach
they would knock on the handy man 's door .
work . They trimmed the hed ges and cut the grass
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
excitement growing . He quickly shed his clothes and plunged into
he went to the garden shed and found a stick .

MIN ACTIVATIONS
MIN = -10.785

a little girl named Jo anna . Jo anna lived in
, or in the sav anna with the lion , or
little fish . " W anna play with me ?" Bob
named Jo anna . Jo anna lived in a village near
friends . But no more jokes . And no more slides
. They do not need jokes . They need hugs .
. Every day , Jo anna would go to the mill
pictures and words . W anna try me out ?" Mike
together one day when Bre anna said , " Let 's
a little girl named Jo anna was walking through a field
were two friends , Bre anna and Mason . They were
you ?" Jo anna was so surprised that the
a little girl called Jo anna who lived in the countryside
the jungle , the sav anna , the desert and the
the dolls . They told jokes and stories . They hugged
One day , Jo anna dared to venture into the
" Yes , I like jokes !" Sally told a funny
One day , Jo anna saw a giant stone wall
a smart princess named Jo anna . She lived in a
really special inside ." Jo anna was very curious and couldn

INTERVAL 6.965 - 12.882
CONTAINS 0.261%

's mom my asked her if she wanted to help clean
scream . The box reaches the end of the
. They also want the box . " Let
bunny said hello and asked if the bird wanted to be
grass . She turned the box upside down and cut a

INTERVAL 1.049 - 6.965
CONTAINS 19.916%

should not climb the ladder without me . It is dangerous
find some . He wandered through the forest until he found
a wise old crab crawled up to them and said ,
'm glad we grew them together . Can we still be
smiled and said , " Don 't be scared , Anna

INTERVAL -4.868 - 1.049
CONTAINS 78.518%

was so happy and he bark ed with joy . He
sheep , and the dog . At first
bug ! Sarah was surprised to find a dead bug and
who had fallen down and hurt his knee , just like
The doctor then said Molly should be honest and not

INTERVAL -10.785 - -4.868
CONTAINS 1.305%

, " I miss you too , daddy . But don
go to a meeting . His mum told him ,
hospital , but it was too late . The water from
Me too ! I like to talk
clown liked to make people laugh . One day
Token this
Token ID428
Feature activation+1.34e+00

Pos logit contributions
 aids+0.134
 jokes+0.115
 song+0.115
 hair+0.112
ggie+0.112
Neg logit contributions
arp-0.127
 unst-0.123
 sorts-0.122
 Joey-0.121
aved-0.120
Token power
Token ID1176
Feature activation+2.50e+00

Pos logit contributions
 sorts+0.077
 Joey+0.077
arp+0.077
 unst+0.076
 Mill+0.075
Neg logit contributions
 aids-0.104
 jokes-0.090
 song-0.090
 wig-0.090
 hair-0.089
Token would
Token ID561
Feature activation+1.71e+00

Pos logit contributions
arp+0.157
 unst+0.150
 Joey+0.149
aved+0.147
 sorts+0.145
Neg logit contributions
 aids-0.187
 song-0.165
 jokes-0.163
 hair-0.160
 poems-0.156
Token come
Token ID1282
Feature activation+7.65e-01

Pos logit contributions
arp+0.137
 unst+0.129
aved+0.129
rolley+0.128
 sorts+0.127
Neg logit contributions
 aids-0.101
 song-0.089
 jokes-0.086
 hair-0.081
ggie-0.080
Token in
Token ID287
Feature activation-5.80e-01

Pos logit contributions
arp+0.050
 sorts+0.049
rolley+0.047
aved+0.047
erek+0.046
Neg logit contributions
 aids-0.055
 song-0.049
 hair-0.048
 jokes-0.047
 poems-0.045
Token handy
Token ID15728
Feature activation+1.28e+01

Pos logit contributions
 aids+0.033
 hair+0.029
 song+0.028
 jokes+0.028
 poems+0.026
Neg logit contributions
arp-0.049
aved-0.046
ucer-0.046
rolley-0.045
erek-0.044
Token.
Token ID13
Feature activation+5.29e-01

Pos logit contributions
arp+0.824
 unst+0.810
 Joey+0.806
 sorts+0.803
aved+0.787
Neg logit contributions
 aids-0.925
 song-0.794
 jokes-0.794
 hair-0.779
 wig-0.778
Token
Token ID220
Feature activation-3.47e-01

Pos logit contributions
arp+0.040
 unst+0.039
aved+0.038
 sorts+0.038
 extingu+0.037
Neg logit contributions
 aids-0.034
 jokes-0.027
 Dancing-0.027
 hair-0.027
 song-0.027
Token
Token ID198
Feature activation+7.85e-01

Pos logit contributions
 aids+0.021
 Dancing+0.017
ggie+0.016
 hair+0.016
 jokes+0.016
Neg logit contributions
arp-0.028
 sorts-0.027
 unst-0.026
aved-0.026
 extingu-0.026
TokenHe
Token ID1544
Feature activation+4.17e-01

Pos logit contributions
arp+0.057
 unst+0.056
aved+0.055
 extingu+0.054
 sorts+0.054
Neg logit contributions
 aids-0.052
ggie-0.043
 jokes-0.043
 song-0.043
 Dancing-0.043
Token was
Token ID373
Feature activation+7.89e-01

Pos logit contributions
arp+0.026
 unst+0.026
 Joey+0.025
 sorts+0.025
aved+0.025
Neg logit contributions
 aids-0.031
 song-0.027
 jokes-0.027
 hair-0.026
ggie-0.026
Token was
Token ID373
Feature activation+6.59e-01

Pos logit contributions
 aids+0.009
 jokes+0.008
 song+0.008
 poems+0.008
 Dancing+0.008
Neg logit contributions
arp-0.008
 sorts-0.008
 unst-0.008
 Joey-0.008
 Mill-0.008
Token very
Token ID845
Feature activation-6.09e-01

Pos logit contributions
 unst+0.037
 sorts+0.036
 Joey+0.035
 Mill+0.034
aved+0.032
Neg logit contributions
 aids-0.053
 cheeks-0.048
 wig-0.048
 jokes-0.048
 poems-0.048
Token happy
Token ID3772
Feature activation-8.69e-01

Pos logit contributions
 aids+0.044
 poems+0.038
 wig+0.037
 jokes+0.037
 cheeks+0.036
Neg logit contributions
 unst-0.041
 sorts-0.040
 Joey-0.040
 Mill-0.038
aved-0.037
Token because
Token ID780
Feature activation-2.60e+00

Pos logit contributions
 aids+0.067
 wig+0.056
ggie+0.056
 jokes+0.055
 song+0.055
Neg logit contributions
 Joey-0.053
 sorts-0.053
arp-0.051
 Mill-0.051
 unst-0.051
Token the
Token ID262
Feature activation+7.56e-01

Pos logit contributions
 aids+0.128
 song+0.111
 poems+0.109
 jokes+0.107
 hair+0.107
Neg logit contributions
arp-0.232
aved-0.229
 unst-0.222
 extingu-0.218
ucer-0.213
Token handy
Token ID15728
Feature activation+1.24e+01

Pos logit contributions
arp+0.059
aved+0.056
 Joey+0.056
 sorts+0.056
ucer+0.054
Neg logit contributions
 aids-0.046
 song-0.041
 hair-0.040
 jokes-0.040
 poems-0.039
Token man
Token ID582
Feature activation+1.45e+00

Pos logit contributions
arp+0.897
 unst+0.882
 Joey+0.877
 sorts+0.875
aved+0.860
Neg logit contributions
 aids-0.795
 jokes-0.669
 song-0.669
 hair-0.655
 wig-0.653
Token had
Token ID550
Feature activation-1.19e+00

Pos logit contributions
arp+0.093
 unst+0.091
 Joey+0.091
 sorts+0.090
aved+0.089
Neg logit contributions
 aids-0.105
 song-0.091
 jokes-0.090
 hair-0.089
ggie-0.089
Token helped
Token ID4193
Feature activation+3.37e+00

Pos logit contributions
 aids+0.087
 jokes+0.077
 song+0.076
 hair+0.076
 poems+0.075
Neg logit contributions
arp-0.080
aved-0.073
 unst-0.073
 Joey-0.073
 sorts-0.072
Token her
Token ID607
Feature activation-5.91e-01

Pos logit contributions
arp+0.200
aved+0.192
 unst+0.191
 sorts+0.191
 Joey+0.188
Neg logit contributions
 aids-0.266
 song-0.233
 jokes-0.233
 hair-0.229
ggie-0.228
Token.
Token ID13
Feature activation+1.68e-01

Pos logit contributions
 aids+0.046
 song+0.041
 jokes+0.040
 hair+0.040
ggie+0.039
Neg logit contributions
arp-0.036
 Joey-0.034
aved-0.034
 sorts-0.034
 unst-0.034
Token.
Token ID13
Feature activation+1.75e-01

Pos logit contributions
arp+0.112
 unst+0.111
 sorts+0.111
 Joey+0.110
aved+0.107
Neg logit contributions
 aids-0.135
 jokes-0.115
 song-0.115
 wig-0.114
ggie-0.113
Token The
Token ID383
Feature activation-1.30e+00

Pos logit contributions
arp+0.012
 Joey+0.012
 unst+0.012
 sorts+0.011
 Mill+0.011
Neg logit contributions
 aids-0.012
 song-0.011
 jokes-0.010
 wig-0.010
ggie-0.010
Token cart
Token ID6383
Feature activation+1.57e+00

Pos logit contributions
 aids+0.096
ggie+0.081
 song+0.080
 jokes+0.080
 wig+0.078
Neg logit contributions
 unst-0.085
arp-0.084
 Joey-0.083
 sorts-0.081
aved-0.080
Token came
Token ID1625
Feature activation-5.59e-01

Pos logit contributions
arp+0.099
 unst+0.096
 Joey+0.096
 sorts+0.095
aved+0.094
Neg logit contributions
 aids-0.115
 song-0.100
 jokes-0.100
 hair-0.098
ggie-0.098
Token in
Token ID287
Feature activation-1.25e+00

Pos logit contributions
 aids+0.042
 song+0.039
 hair+0.039
 jokes+0.038
ggie+0.037
Neg logit contributions
arp-0.034
 sorts-0.032
rolley-0.031
 Joey-0.030
 extingu-0.030
Token handy
Token ID15728
Feature activation+1.24e+01

Pos logit contributions
 aids+0.066
 song+0.064
 hair+0.063
 jokes+0.062
 songs+0.057
Neg logit contributions
arp-0.107
aved-0.103
ucer-0.102
pling-0.098
ylan-0.097
Token to
Token ID284
Feature activation-7.95e-01

Pos logit contributions
 sorts+0.705
 Joey+0.696
arp+0.695
 unst+0.694
wood+0.681
Neg logit contributions
 aids-0.967
 Dancing-0.839
 jokes-0.819
 wig-0.819
 poems-0.798
Token carry
Token ID3283
Feature activation+2.86e+00

Pos logit contributions
 aids+0.051
 song+0.048
 jokes+0.047
 hair+0.046
 wig+0.044
Neg logit contributions
arp-0.057
aved-0.055
ucer-0.054
rolley-0.054
erek-0.053
Token all
Token ID477
Feature activation+2.76e+00

Pos logit contributions
aved+0.239
ucer+0.239
 haven+0.237
stack+0.236
arp+0.234
Neg logit contributions
 hair-0.138
 aids-0.117
 jokes-0.110
 songs-0.107
 poems-0.101
Token of
Token ID286
Feature activation+4.64e-01

Pos logit contributions
aved+0.203
arp+0.199
 unst+0.194
 scaven+0.192
erek+0.191
Neg logit contributions
 aids-0.171
 song-0.150
 hair-0.150
 jokes-0.143
 poems-0.137
Token the
Token ID262
Feature activation+7.59e-01

Pos logit contributions
aved+0.041
arp+0.041
rolley+0.041
ucer+0.040
erek+0.038
Neg logit contributions
 hair-0.022
 jokes-0.021
 aids-0.019
 yoga-0.019
 song-0.018
Token a
Token ID257
Feature activation+9.31e-01

Pos logit contributions
 Joey+0.190
 sorts+0.188
 unst+0.186
arp+0.182
 Mill+0.180
Neg logit contributions
 aids-0.321
 cheeks-0.277
 wig-0.272
 jokes-0.270
 song-0.269
Token time
Token ID640
Feature activation-4.34e+00

Pos logit contributions
 scaven+0.069
 sorts+0.067
 Joey+0.066
arp+0.066
 unst+0.065
Neg logit contributions
 aids-0.059
 wig-0.048
 cheeks-0.047
 jokes-0.046
 song-0.046
Token there
Token ID612
Feature activation+4.97e-01

Pos logit contributions
 aids+0.251
 hair+0.213
ggie+0.213
 song+0.212
 jokes+0.211
Neg logit contributions
arp-0.343
 sorts-0.332
 unst-0.325
rolley-0.325
aved-0.324
Token was
Token ID373
Feature activation+7.76e-01

Pos logit contributions
arp+0.039
 unst+0.037
 sorts+0.036
 extingu+0.036
wood+0.036
Neg logit contributions
 aids-0.028
ggie-0.026
 hair-0.025
 Dancing-0.025
 song-0.025
Token a
Token ID257
Feature activation+6.94e-01

Pos logit contributions
 Joey+0.047
arp+0.047
 unst+0.047
 sorts+0.047
aved+0.046
Neg logit contributions
 aids-0.059
 song-0.050
 jokes-0.050
 wig-0.050
ggie-0.049
Token handy
Token ID15728
Feature activation+1.23e+01

Pos logit contributions
arp+0.046
 Joey+0.045
 unst+0.044
 scaven+0.043
 Mill+0.043
Neg logit contributions
 aids-0.052
 jokes-0.042
 cheeks-0.040
 poems-0.040
 hair-0.039
Token man
Token ID582
Feature activation+1.49e+00

Pos logit contributions
arp+0.764
 Joey+0.749
 sorts+0.747
 Mill+0.740
 extingu+0.733
Neg logit contributions
 aids-0.927
 jokes-0.793
 Dancing-0.784
 hair-0.778
 wig-0.767
Token who
Token ID508
Feature activation-1.55e+00

Pos logit contributions
 sorts+0.085
 Joey+0.084
arp+0.081
 Mill+0.080
 extingu+0.077
Neg logit contributions
 aids-0.121
 jokes-0.105
 cheeks-0.104
 song-0.102
uren-0.101
Token had
Token ID550
Feature activation-1.26e+00

Pos logit contributions
 aids+0.093
ggie+0.082
 hair+0.080
 song+0.080
 jokes+0.077
Neg logit contributions
arp-0.117
 unst-0.114
 Joey-0.113
 hed-0.111
 Mill-0.109
Token a
Token ID257
Feature activation+5.39e-01

Pos logit contributions
 aids+0.103
 jokes+0.088
 song+0.088
 Dancing+0.087
 wig+0.087
Neg logit contributions
 unst-0.070
 Joey-0.070
arp-0.069
 sorts-0.069
 Mill-0.068
Token fancy
Token ID14996
Feature activation-1.59e+00

Pos logit contributions
arp+0.036
 unst+0.035
 Joey+0.035
 sorts+0.035
aved+0.034
Neg logit contributions
 aids-0.038
 jokes-0.032
 song-0.032
 hair-0.032
ggie-0.032
Token is
Token ID318
Feature activation+7.62e-01

Pos logit contributions
 aids+0.377
 jokes+0.314
 song+0.310
 Dancing+0.299
ggie+0.298
Neg logit contributions
arp-0.435
 unst-0.435
aved-0.431
 Joey-0.424
 afloat-0.416
Token that
Token ID326
Feature activation-1.77e+00

Pos logit contributions
arp+0.059
 unst+0.058
aved+0.057
 sorts+0.057
 Joey+0.056
Neg logit contributions
 aids-0.046
 jokes-0.039
 song-0.039
ggie-0.038
 hair-0.037
Token friends
Token ID2460
Feature activation-1.87e+00

Pos logit contributions
 aids+0.129
 jokes+0.120
 song+0.119
 poems+0.113
 hair+0.113
Neg logit contributions
arp-0.117
aved-0.115
rolley-0.109
 extingu-0.108
 unst-0.107
Token come
Token ID1282
Feature activation+3.62e-02

Pos logit contributions
 aids+0.143
 song+0.132
 jokes+0.132
 hair+0.130
 Dancing+0.126
Neg logit contributions
arp-0.110
 extingu-0.105
rolley-0.104
 hed-0.103
 Suz-0.103
Token in
Token ID287
Feature activation-1.33e+00

Pos logit contributions
 sorts+0.003
arp+0.003
aved+0.003
 hed+0.003
 Joey+0.003
Neg logit contributions
 aids-0.002
 hair-0.002
 song-0.002
ggie-0.002
 Dancing-0.002
Token handy
Token ID15728
Feature activation+1.23e+01

Pos logit contributions
 aids+0.082
 song+0.075
 hair+0.073
 poems+0.072
 jokes+0.072
Neg logit contributions
arp-0.103
aved-0.101
ucer-0.095
rolley-0.093
erek-0.093
Token in
Token ID287
Feature activation-1.30e+00

Pos logit contributions
arp+0.771
 unst+0.764
 Joey+0.759
 sorts+0.759
aved+0.738
Neg logit contributions
 aids-0.899
 song-0.770
 jokes-0.769
 wig-0.761
 hair-0.755
Token times
Token ID1661
Feature activation-1.05e+00

Pos logit contributions
 aids+0.094
 hair+0.083
 song+0.082
 jokes+0.081
 poems+0.078
Neg logit contributions
arp-0.085
aved-0.083
erek-0.080
ucer-0.079
 Joey-0.079
Token of
Token ID286
Feature activation+3.75e-01

Pos logit contributions
 aids+0.057
 hair+0.049
 jokes+0.047
 song+0.047
 Dancing+0.046
Neg logit contributions
arp-0.086
 extingu-0.084
aved-0.081
 unst-0.080
 sorts-0.079
Token need
Token ID761
Feature activation+3.41e+00

Pos logit contributions
arp+0.026
aved+0.025
erek+0.024
rolley+0.024
ucer+0.024
Neg logit contributions
 aids-0.027
 jokes-0.024
 song-0.024
 hair-0.024
 poems-0.023
Token.
Token ID13
Feature activation+1.73e-01

Pos logit contributions
arp+0.258
aved+0.244
erek+0.241
rolley+0.236
ucer+0.236
Neg logit contributions
 aids-0.218
 jokes-0.196
 hair-0.193
 song-0.192
 poems-0.185
Token Maybe
Token ID6674
Feature activation+3.49e+00

Pos logit contributions
 aids+0.073
 song+0.062
 jokes+0.061
 hair+0.060
 wig+0.060
Neg logit contributions
arp-0.078
 unst-0.076
 Joey-0.076
 sorts-0.076
aved-0.075
Token it
Token ID340
Feature activation+1.48e+00

Pos logit contributions
arp+0.233
aved+0.228
 sorts+0.225
 unst+0.225
 Joey+0.219
Neg logit contributions
 aids-0.245
 song-0.216
 jokes-0.215
 hair-0.214
 wig-0.211
Token will
Token ID481
Feature activation+5.76e+00

Pos logit contributions
arp+0.095
 Joey+0.094
 Mill+0.090
 sorts+0.089
 unst+0.088
Neg logit contributions
 aids-0.107
 hair-0.093
 jokes-0.093
 song-0.092
ggie-0.090
Token come
Token ID1282
Feature activation+9.91e-02

Pos logit contributions
arp+0.480
rolley+0.465
erek+0.444
 sorts+0.441
aved+0.440
Neg logit contributions
 aids-0.323
 song-0.293
 jokes-0.277
 hair-0.269
ggie-0.253
Token in
Token ID287
Feature activation-1.32e+00

Pos logit contributions
 sorts+0.007
arp+0.007
erek+0.007
ylan+0.007
 hed+0.007
Neg logit contributions
 aids-0.006
 song-0.006
 hair-0.006
 songs-0.005
 poems-0.005
Token handy
Token ID15728
Feature activation+1.23e+01

Pos logit contributions
 aids+0.076
 song+0.074
 hair+0.071
 poems+0.070
 yoga+0.067
Neg logit contributions
aved-0.103
arp-0.100
erek-0.098
ucer-0.096
ylan-0.093
Token one
Token ID530
Feature activation-2.85e+00

Pos logit contributions
arp+0.568
 sorts+0.561
 unst+0.560
 Joey+0.557
 Mill+0.534
Neg logit contributions
 aids-1.096
 jokes-0.964
 Dancing-0.958
 song-0.955
 wig-0.953
Token day
Token ID1110
Feature activation-1.27e+00

Pos logit contributions
 aids+0.215
 song+0.190
 jokes+0.187
 hair+0.185
ggie+0.183
Neg logit contributions
arp-0.173
 unst-0.171
 Joey-0.170
aved-0.168
 sorts-0.167
Token!"
Token ID2474
Feature activation+3.67e+00

Pos logit contributions
 aids+0.096
 song+0.088
 hair+0.086
 jokes+0.085
 poems+0.084
Neg logit contributions
arp-0.075
 unst-0.074
aved-0.073
 sorts-0.070
 Joey-0.070
Token
Token ID220
Feature activation-6.85e-01

Pos logit contributions
arp+0.232
 unst+0.229
 Joey+0.229
 sorts+0.226
 Mill+0.223
Neg logit contributions
 aids-0.272
 jokes-0.233
 song-0.233
ggie-0.229
 wig-0.229
Token
Token ID198
Feature activation+4.14e-01

Pos logit contributions
 aids+0.034
ggie+0.028
 Dancing+0.028
 Her+0.027
 hair+0.027
Neg logit contributions
arp-0.059
 sorts-0.058
 extingu-0.057
aved-0.057
 unst-0.056
Token<|endoftext|>
Token ID50256
Feature activation-2.88e-01

Pos logit contributions
 aids+0.004
 Dancing+0.003
 Her+0.003
 hair+0.003
uren+0.003
Neg logit contributions
arp-0.006
aved-0.006
 unst-0.006
 afloat-0.006
 deeper-0.006
TokenGrand
Token ID23581
Feature activation+8.63e-01

Pos logit contributions
 aids+0.022
 Dancing+0.021
 hair+0.020
 song+0.019
ggie+0.019
Neg logit contributions
 unst-0.017
arp-0.016
 extingu-0.015
 sorts-0.015
aved-0.015
Tokenpa
Token ID8957
Feature activation+8.25e-01

Pos logit contributions
arp+0.046
 Joey+0.045
 sorts+0.045
 unst+0.045
 Mill+0.044
Neg logit contributions
 aids-0.072
 song-0.063
 jokes-0.063
ggie-0.062
 hair-0.062
Token was
Token ID373
Feature activation+3.34e-01

Pos logit contributions
arp+0.066
 unst+0.064
aved+0.061
 afloat+0.061
ucer+0.060
Neg logit contributions
 aids-0.046
 jokes-0.042
 hair-0.042
 wig-0.039
ggie-0.038
Token a
Token ID257
Feature activation+4.37e-01

Pos logit contributions
 Joey+0.020
 unst+0.020
 Mill+0.020
 sorts+0.019
neath+0.019
Neg logit contributions
 aids-0.025
 jokes-0.023
 cheeks-0.022
 song-0.022
 wig-0.022
Token handy
Token ID15728
Feature activation+1.21e+01

Pos logit contributions
 Joey+0.028
 Mill+0.027
 sorts+0.027
 unst+0.027
arp+0.027
Neg logit contributions
 aids-0.033
 jokes-0.028
 poems-0.027
ggie-0.027
 wig-0.026
Token man
Token ID582
Feature activation+1.20e+00

Pos logit contributions
arp+0.755
 Joey+0.753
 sorts+0.751
 Mill+0.738
 extingu+0.723
Neg logit contributions
 aids-0.895
 jokes-0.769
 Dancing-0.758
 hair-0.756
 wig-0.751
Token and
Token ID290
Feature activation+2.41e-01

Pos logit contributions
 Joey+0.070
 sorts+0.070
 Mill+0.068
arp+0.068
 unst+0.066
Neg logit contributions
 aids-0.093
 jokes-0.081
 song-0.079
 wig-0.079
 poems-0.079
Token he
Token ID339
Feature activation-5.54e-01

Pos logit contributions
arp+0.017
 unst+0.017
 Joey+0.016
aved+0.016
 sorts+0.016
Neg logit contributions
 aids-0.016
 jokes-0.014
 song-0.014
 hair-0.013
 wig-0.013
Token had
Token ID550
Feature activation-1.46e+00

Pos logit contributions
 aids+0.040
 song+0.035
 jokes+0.035
 hair+0.034
ggie+0.034
Neg logit contributions
arp-0.036
 unst-0.035
 Joey-0.035
 sorts-0.034
aved-0.034
Token lots
Token ID6041
Feature activation+5.66e+00

Pos logit contributions
 aids+0.111
 song+0.096
 jokes+0.095
 wig+0.094
ggie+0.093
Neg logit contributions
 Joey-0.087
 sorts-0.087
 unst-0.087
arp-0.087
 Mill-0.085
Token.
Token ID13
Feature activation-1.63e-01

Pos logit contributions
 aids+0.014
 song+0.012
 hair+0.012
ggie+0.012
 jokes+0.011
Neg logit contributions
arp-0.017
 Joey-0.017
 sorts-0.017
aved-0.017
 unst-0.017
Token
Token ID198
Feature activation+3.40e-01

Pos logit contributions
 aids+0.010
 jokes+0.008
 hair+0.008
 song+0.008
 Dancing+0.008
Neg logit contributions
arp-0.013
 unst-0.012
aved-0.012
 sorts-0.012
 Joey-0.012
Token
Token ID198
Feature activation+3.50e-01

Pos logit contributions
arp+0.024
 unst+0.024
 sorts+0.023
aved+0.023
 Joey+0.023
Neg logit contributions
 aids-0.023
 song-0.019
ggie-0.019
 jokes-0.019
 Dancing-0.019
TokenThen
Token ID6423
Feature activation-2.69e+00

Pos logit contributions
arp+0.022
 sorts+0.022
 unst+0.022
 Joey+0.022
aved+0.021
Neg logit contributions
 aids-0.025
 hair-0.022
 jokes-0.022
 cheeks-0.022
 wig-0.022
Token the
Token ID262
Feature activation+5.58e-01

Pos logit contributions
 aids+0.179
 jokes+0.155
 hair+0.155
 song+0.155
ggie+0.151
Neg logit contributions
arp-0.193
 unst-0.185
 sorts-0.184
aved-0.183
 Joey-0.179
Token handy
Token ID15728
Feature activation+1.21e+01

Pos logit contributions
arp+0.037
 unst+0.037
 Joey+0.037
 sorts+0.037
aved+0.036
Neg logit contributions
 aids-0.039
 jokes-0.034
 song-0.033
 wig-0.033
 hair-0.033
Token man
Token ID582
Feature activation+1.22e+00

Pos logit contributions
arp+0.838
 unst+0.820
 Joey+0.815
 sorts+0.814
 Mill+0.801
Neg logit contributions
 aids-0.818
 jokes-0.698
 song-0.684
 wig-0.683
 hair-0.682
Token drove
Token ID10357
Feature activation+1.09e+00

Pos logit contributions
arp+0.087
 sorts+0.084
 unst+0.083
 Joey+0.083
 hed+0.083
Neg logit contributions
 aids-0.080
 song-0.069
ggie-0.069
 jokes-0.068
 hair-0.067
Token to
Token ID284
Feature activation-1.07e+00

Pos logit contributions
arp+0.060
 sorts+0.057
aved+0.056
 unst+0.056
 Joey+0.056
Neg logit contributions
 aids-0.090
 song-0.080
 hair-0.080
 jokes-0.079
ggie-0.078
Token the
Token ID262
Feature activation+5.75e-01

Pos logit contributions
 aids+0.057
 jokes+0.050
 hair+0.050
 song+0.050
 haircut+0.049
Neg logit contributions
arp-0.095
aved-0.093
ucer-0.085
pling-0.084
rol-0.083
Token young
Token ID1862
Feature activation+1.51e+00

Pos logit contributions
 Joey+0.038
aved+0.038
 sorts+0.037
arp+0.037
 Suz+0.036
Neg logit contributions
 aids-0.040
 song-0.037
 hair-0.037
 jokes-0.035
 poems-0.034
Token compassionate
Token ID32533
Feature activation-6.33e-01

Pos logit contributions
 aids+0.188
 wig+0.154
ggie+0.152
 song+0.151
 jokes+0.149
Neg logit contributions
 Joey-0.213
arp-0.211
 unst-0.209
 sorts-0.208
 Mill-0.204
Token act
Token ID719
Feature activation-3.17e-01

Pos logit contributions
 aids+0.040
 song+0.034
 jokes+0.034
 hair+0.033
ggie+0.033
Neg logit contributions
arp-0.047
 unst-0.046
 Joey-0.046
 sorts-0.046
aved-0.045
Token would
Token ID561
Feature activation+9.77e-01

Pos logit contributions
 aids+0.023
 song+0.020
 jokes+0.019
 hair+0.019
ggie+0.019
Neg logit contributions
arp-0.021
 Joey-0.020
 sorts-0.020
 unst-0.020
 hed-0.019
Token come
Token ID1282
Feature activation-4.99e-02

Pos logit contributions
arp+0.075
 unst+0.071
aved+0.070
 sorts+0.069
rolley+0.069
Neg logit contributions
 aids-0.061
 song-0.054
 jokes-0.053
 hair-0.051
ggie-0.050
Token in
Token ID287
Feature activation-1.40e+00

Pos logit contributions
 aids+0.003
 song+0.003
 hair+0.003
 jokes+0.003
 Dancing+0.003
Neg logit contributions
arp-0.004
 sorts-0.004
 hed-0.003
aved-0.003
rolley-0.003
Token handy
Token ID15728
Feature activation+1.21e+01

Pos logit contributions
 aids+0.086
 song+0.076
 hair+0.075
 jokes+0.074
 poems+0.073
Neg logit contributions
arp-0.110
aved-0.106
ucer-0.102
erek-0.100
 unst-0.099
Token a
Token ID257
Feature activation+5.71e-01

Pos logit contributions
arp+0.716
 sorts+0.715
 unst+0.715
 Joey+0.712
 Mill+0.699
Neg logit contributions
 aids-0.916
 Dancing-0.789
 jokes-0.786
 wig-0.782
 song-0.769
Token few
Token ID1178
Feature activation-1.91e+00

Pos logit contributions
arp+0.036
aved+0.036
 unst+0.034
 Joey+0.034
neath+0.034
Neg logit contributions
 aids-0.042
 song-0.039
 jokes-0.036
 wig-0.036
 hair-0.036
Token days
Token ID1528
Feature activation-1.04e+00

Pos logit contributions
 aids+0.126
 wig+0.106
 Dancing+0.106
ggie+0.105
 song+0.105
Neg logit contributions
 sorts-0.133
arp-0.133
 unst-0.132
 Joey-0.130
aved-0.127
Token later
Token ID1568
Feature activation+1.13e+00

Pos logit contributions
 aids+0.065
 hair+0.056
 song+0.056
 jokes+0.055
ggie+0.054
Neg logit contributions
arp-0.076
 unst-0.072
 Joey-0.072
 sorts-0.072
aved-0.071
Token when
Token ID618
Feature activation-4.56e-01

Pos logit contributions
arp+0.078
 unst+0.076
 sorts+0.075
 Joey+0.075
aved+0.074
Neg logit contributions
 aids-0.078
 song-0.067
 jokes-0.066
 hair-0.066
ggie-0.065
Token it
Token ID340
Feature activation+1.47e+00

Pos logit contributions
 aids+0.190
 jokes+0.168
 song+0.166
 hair+0.163
 poems+0.163
Neg logit contributions
aved-0.195
arp-0.190
 unst-0.189
 extingu-0.186
 afloat-0.178
Token's
Token ID338
Feature activation-3.07e+00

Pos logit contributions
arp+0.117
 unst+0.112
aved+0.111
 Joey+0.110
 extingu+0.108
Neg logit contributions
 aids-0.087
 jokes-0.075
 song-0.074
 hair-0.071
ggie-0.070
Token important
Token ID1593
Feature activation+1.32e+00

Pos logit contributions
 aids+0.206
 jokes+0.179
 song+0.177
 hair+0.175
ggie+0.172
Neg logit contributions
arp-0.224
aved-0.212
 unst-0.209
 sorts-0.205
 Joey-0.204
Token to
Token ID284
Feature activation-9.90e-01

Pos logit contributions
arp+0.092
 unst+0.090
 Joey+0.089
 sorts+0.088
aved+0.088
Neg logit contributions
 aids-0.090
 song-0.077
 jokes-0.077
 hair-0.076
ggie-0.075
Token keep
Token ID1394
Feature activation+2.30e+00

Pos logit contributions
 aids+0.062
 jokes+0.054
 song+0.053
 hair+0.052
ggie+0.051
Neg logit contributions
arp-0.075
 unst-0.074
aved-0.072
 sorts-0.072
rolley-0.070
Token hed
Token ID16418
Feature activation+1.20e+01

Pos logit contributions
arp+0.152
aved+0.148
 extingu+0.143
erek+0.141
 sorts+0.141
Neg logit contributions
 aids-0.167
 hair-0.152
 jokes-0.149
 poems-0.147
 song-0.147
Tokenges
Token ID3212
Feature activation+9.11e-01

Pos logit contributions
 sorts+0.717
arp+0.690
 Joey+0.684
 unst+0.684
 hed+0.682
Neg logit contributions
 aids-0.875
 Dancing-0.768
ggie-0.740
 wig-0.739
 song-0.733
Token neat
Token ID15049
Feature activation+5.56e+00

Pos logit contributions
aved+0.065
erek+0.064
arp+0.064
 unst+0.063
 extingu+0.062
Neg logit contributions
 aids-0.059
 poems-0.052
 hair-0.051
 song-0.051
 jokes-0.051
Token and
Token ID290
Feature activation+4.60e-01

Pos logit contributions
arp+0.387
aved+0.382
 unst+0.378
neath+0.376
 Joey+0.374
Neg logit contributions
 aids-0.369
 hair-0.337
 jokes-0.325
 song-0.324
 poems-0.322
Token tidy
Token ID43044
Feature activation+3.86e+00

Pos logit contributions
arp+0.031
aved+0.030
 extingu+0.029
neath+0.029
rolley+0.029
Neg logit contributions
 aids-0.031
 song-0.029
 jokes-0.029
 hair-0.028
 poems-0.027
Token"
Token ID1
Feature activation+5.26e-01

Pos logit contributions
aved+0.234
arp+0.233
 unst+0.224
neath+0.223
 sorts+0.220
Neg logit contributions
 aids-0.293
 hair-0.270
 jokes-0.263
 song-0.261
 poems-0.258
Token stood
Token ID6204
Feature activation-1.43e+00

Pos logit contributions
 aids+0.066
 song+0.057
 jokes+0.057
 hair+0.056
 wig+0.056
Neg logit contributions
arp-0.054
 Joey-0.053
 unst-0.053
 sorts-0.053
aved-0.052
Token back
Token ID736
Feature activation-6.98e-01

Pos logit contributions
 aids+0.124
 song+0.109
 jokes+0.109
ggie+0.107
 wig+0.107
Neg logit contributions
arp-0.073
 unst-0.071
 Joey-0.071
 sorts-0.070
aved-0.069
Token and
Token ID290
Feature activation+4.96e-01

Pos logit contributions
 aids+0.048
 hair+0.043
 song+0.042
 jokes+0.041
 cheeks+0.040
Neg logit contributions
arp-0.048
 unst-0.045
 Joey-0.045
 sorts-0.045
aved-0.045
Token admired
Token ID29382
Feature activation+1.26e+00

Pos logit contributions
arp+0.037
 unst+0.035
 sorts+0.035
 Joey+0.034
aved+0.034
Neg logit contributions
 aids-0.031
 hair-0.027
 song-0.027
 jokes-0.027
 wig-0.026
Token their
Token ID511
Feature activation+1.49e-01

Pos logit contributions
arp+0.081
 unst+0.078
 sorts+0.076
aved+0.076
 Joey+0.076
Neg logit contributions
 aids-0.093
 jokes-0.082
 hair-0.081
 song-0.081
 poems-0.079
Token handy
Token ID15728
Feature activation+1.20e+01

Pos logit contributions
arp+0.007
 unst+0.007
 sorts+0.007
 Joey+0.007
aved+0.006
Neg logit contributions
 aids-0.014
 song-0.012
 jokes-0.012
ggie-0.012
 wig-0.012
Token work
Token ID670
Feature activation+4.47e+00

Pos logit contributions
arp+0.747
 sorts+0.744
 unst+0.741
 Joey+0.720
wood+0.719
Neg logit contributions
 aids-0.862
 Dancing-0.742
 wig-0.732
 jokes-0.732
 hair-0.717
Token.
Token ID13
Feature activation+3.05e-03

Pos logit contributions
arp+0.290
 unst+0.285
 Joey+0.284
 sorts+0.283
aved+0.278
Neg logit contributions
 aids-0.319
 song-0.274
 jokes-0.274
 hair-0.269
 wig-0.268
Token The
Token ID383
Feature activation-1.44e+00

Pos logit contributions
arp+0.000
 unst+0.000
aved+0.000
 Joey+0.000
 sorts+0.000
Neg logit contributions
 aids-0.000
 hair-0.000
 jokes-0.000
 Dancing-0.000
 song-0.000
Token screw
Token ID9580
Feature activation+5.02e+00

Pos logit contributions
 aids+0.107
 song+0.094
 jokes+0.093
 hair+0.093
 poems+0.091
Neg logit contributions
arp-0.091
 Joey-0.090
 unst-0.089
 sorts-0.088
aved-0.088
Token was
Token ID373
Feature activation+3.81e-01

Pos logit contributions
arp+0.307
 unst+0.301
 Joey+0.300
 sorts+0.298
aved+0.292
Neg logit contributions
 aids-0.378
 song-0.328
 jokes-0.327
 hair-0.322
ggie-0.321
Token stepped
Token ID10764
Feature activation+3.02e-01

Pos logit contributions
 aids+0.004
 song+0.003
 jokes+0.003
 hair+0.003
ggie+0.003
Neg logit contributions
arp-0.004
 unst-0.004
 Joey-0.004
 sorts-0.004
aved-0.004
Token back
Token ID736
Feature activation-7.28e-01

Pos logit contributions
 sorts+0.020
arp+0.019
 Mill+0.018
 Joey+0.018
 hed+0.018
Neg logit contributions
 aids-0.020
 hair-0.020
 wig-0.019
 song-0.018
 Dancing-0.018
Token to
Token ID284
Feature activation-1.15e+00

Pos logit contributions
 aids+0.044
 hair+0.042
 song+0.039
 jokes+0.038
 wig+0.038
Neg logit contributions
arp-0.054
 unst-0.051
aved-0.051
 sorts-0.050
 Joey-0.050
Token admire
Token ID21099
Feature activation+1.62e+00

Pos logit contributions
 aids+0.078
 jokes+0.070
 song+0.070
 hair+0.068
 wig+0.066
Neg logit contributions
arp-0.084
aved-0.079
 unst-0.078
ucer-0.075
rolley-0.075
Token his
Token ID465
Feature activation-1.62e+00

Pos logit contributions
arp+0.099
 unst+0.097
 sorts+0.095
aved+0.095
 Joey+0.094
Neg logit contributions
 aids-0.123
 jokes-0.108
 song-0.107
 hair-0.106
ggie-0.105
Token handy
Token ID15728
Feature activation+1.20e+01

Pos logit contributions
 aids+0.131
 Dancing+0.111
 wig+0.110
ggie+0.109
 jokes+0.108
Neg logit contributions
 unst-0.090
 sorts-0.090
arp-0.088
 Joey-0.087
 Mill-0.085
Token work
Token ID670
Feature activation+4.41e+00

Pos logit contributions
 sorts+0.773
arp+0.769
 unst+0.755
 Mill+0.749
 Joey+0.749
Neg logit contributions
 aids-0.834
 Dancing-0.717
 jokes-0.708
 wig-0.688
 hair-0.682
Token.
Token ID13
Feature activation-1.60e-01

Pos logit contributions
arp+0.286
 unst+0.281
 Joey+0.280
 sorts+0.279
aved+0.274
Neg logit contributions
 aids-0.316
 song-0.271
 jokes-0.271
 hair-0.266
 wig-0.265
Token
Token ID198
Feature activation+3.42e-01

Pos logit contributions
 aids+0.010
 Dancing+0.008
 jokes+0.008
 hair+0.008
 song+0.008
Neg logit contributions
arp-0.012
 unst-0.012
aved-0.011
 sorts-0.011
 Joey-0.011
Token
Token ID198
Feature activation+3.29e-01

Pos logit contributions
arp+0.027
 unst+0.027
 extingu+0.026
aved+0.026
 sorts+0.026
Neg logit contributions
 aids-0.020
ggie-0.017
 Dancing-0.017
 song-0.016
 jokes-0.016
Token"
Token ID1
Feature activation+3.85e-01

Pos logit contributions
arp+0.024
 unst+0.023
 Joey+0.023
 sorts+0.023
aved+0.023
Neg logit contributions
 aids-0.022
 song-0.018
 jokes-0.018
ggie-0.018
 wig-0.018
Token.
Token ID13
Feature activation-4.36e-01

Pos logit contributions
 aids+0.083
 song+0.071
 jokes+0.071
 hair+0.070
 wig+0.070
Neg logit contributions
arp-0.067
 unst-0.065
 Joey-0.065
 sorts-0.065
aved-0.063
Token
Token ID198
Feature activation+9.27e-02

Pos logit contributions
 aids+0.030
 song+0.025
 jokes+0.025
 hair+0.025
 wig+0.024
Neg logit contributions
arp-0.030
 unst-0.030
 sorts-0.029
aved-0.029
 Joey-0.029
Token
Token ID198
Feature activation+1.04e-01

Pos logit contributions
arp+0.007
 unst+0.007
aved+0.007
 sorts+0.007
 Joey+0.007
Neg logit contributions
 aids-0.006
ggie-0.005
 song-0.005
 jokes-0.005
 Dancing-0.005
TokenSo
Token ID2396
Feature activation+1.74e+00

Pos logit contributions
arp+0.007
 unst+0.007
 sorts+0.007
 Joey+0.007
aved+0.007
Neg logit contributions
 aids-0.007
 jokes-0.006
 song-0.006
 hair-0.006
 wig-0.006
Token the
Token ID262
Feature activation+4.11e-01

Pos logit contributions
arp+0.114
 unst+0.111
 sorts+0.110
aved+0.109
 Joey+0.109
Neg logit contributions
 aids-0.125
 song-0.108
 jokes-0.108
 hair-0.107
ggie-0.106
Token handy
Token ID15728
Feature activation+1.19e+01

Pos logit contributions
arp+0.030
 unst+0.030
 Joey+0.030
 sorts+0.030
aved+0.029
Neg logit contributions
 aids-0.026
 song-0.022
 jokes-0.022
 hair-0.022
ggie-0.022
Token man
Token ID582
Feature activation+1.03e+00

Pos logit contributions
arp+0.788
 sorts+0.766
 unst+0.766
 Joey+0.766
 Mill+0.757
Neg logit contributions
 aids-0.837
 jokes-0.718
 Dancing-0.707
 hair-0.703
 wig-0.702
Token went
Token ID1816
Feature activation+9.32e-01

Pos logit contributions
arp+0.069
 unst+0.067
 Joey+0.067
 hed+0.067
 sorts+0.066
Neg logit contributions
 aids-0.070
ggie-0.061
 song-0.061
 hair-0.060
 jokes-0.060
Token to
Token ID284
Feature activation-1.27e+00

Pos logit contributions
arp+0.064
 Joey+0.062
 unst+0.062
 sorts+0.062
aved+0.061
Neg logit contributions
 aids-0.064
 song-0.055
 jokes-0.054
 hair-0.054
 wig-0.053
Token the
Token ID262
Feature activation+4.29e-01

Pos logit contributions
 aids+0.069
 jokes+0.060
 hair+0.059
 haircut+0.059
 song+0.059
Neg logit contributions
arp-0.113
aved-0.108
ucer-0.100
rol-0.098
rolley-0.097
Token teach
Token ID4545
Feature activation-2.32e+00

Pos logit contributions
arp+0.026
 Joey+0.026
aved+0.026
 sorts+0.026
 unst+0.025
Neg logit contributions
 aids-0.032
 song-0.029
 hair-0.029
 jokes-0.028
ggie-0.027
Token they
Token ID484
Feature activation-6.24e-01

Pos logit contributions
arp+0.008
 unst+0.008
aved+0.008
 sorts+0.008
 Joey+0.008
Neg logit contributions
 aids-0.009
 jokes-0.008
 song-0.008
 hair-0.008
 poems-0.008
Token would
Token ID561
Feature activation+9.13e-01

Pos logit contributions
 aids+0.043
 jokes+0.038
 song+0.038
 hair+0.037
 poems+0.037
Neg logit contributions
arp-0.042
 unst-0.041
 Joey-0.040
 sorts-0.040
 hed-0.039
Token knock
Token ID10643
Feature activation-3.98e+00

Pos logit contributions
arp+0.066
 unst+0.064
 Joey+0.061
 sorts+0.061
aved+0.061
Neg logit contributions
 aids-0.062
 song-0.054
 jokes-0.054
 hair-0.052
ggie-0.050
Token on
Token ID319
Feature activation-3.24e+00

Pos logit contributions
 aids+0.262
 hair+0.248
 jokes+0.235
 poems+0.230
 song+0.229
Neg logit contributions
arp-0.270
 sorts-0.263
aved-0.261
 hed-0.258
 unst-0.257
Token the
Token ID262
Feature activation+4.89e-01

Pos logit contributions
 aids+0.200
 hair+0.183
 jokes+0.175
 poems+0.169
 song+0.160
Neg logit contributions
aved-0.246
arp-0.241
 unst-0.239
ucer-0.236
 sorts-0.228
Token handy
Token ID15728
Feature activation+1.19e+01

Pos logit contributions
arp+0.028
 unst+0.028
 Joey+0.027
 sorts+0.027
aved+0.027
Neg logit contributions
 aids-0.039
 song-0.034
 jokes-0.034
ggie-0.033
 wig-0.033
Token man
Token ID582
Feature activation+1.13e+00

Pos logit contributions
arp+0.717
 sorts+0.688
 unst+0.688
wood+0.684
 extingu+0.681
Neg logit contributions
 aids-0.900
 jokes-0.793
 Dancing-0.787
ggie-0.775
 wig-0.775
Token's
Token ID338
Feature activation-3.25e+00

Pos logit contributions
arp+0.089
 unst+0.089
 Joey+0.088
 sorts+0.088
aved+0.086
Neg logit contributions
 aids-0.065
 song-0.054
 jokes-0.053
ggie-0.052
 wig-0.052
Token door
Token ID3420
Feature activation+2.85e+00

Pos logit contributions
 aids+0.267
ggie+0.239
 song+0.235
 jokes+0.234
 Dancing+0.232
Neg logit contributions
arp-0.174
 unst-0.173
 Joey-0.168
 sorts-0.166
 Mill-0.164
Token.
Token ID13
Feature activation-2.00e-01

Pos logit contributions
arp+0.203
 Joey+0.198
 unst+0.197
aved+0.195
 sorts+0.194
Neg logit contributions
 aids-0.187
 song-0.160
 jokes-0.157
 hair-0.157
 poems-0.153
Token
Token ID198
Feature activation+2.26e-01

Pos logit contributions
 aids+0.013
 song+0.011
 jokes+0.011
 wig+0.011
ggie+0.011
Neg logit contributions
 Joey-0.015
arp-0.014
 sorts-0.014
 unst-0.014
 Mill-0.014
Token work
Token ID670
Feature activation+4.40e+00

Pos logit contributions
 aids+0.070
 jokes+0.066
 hair+0.066
 song+0.063
 blond+0.062
Neg logit contributions
arp-0.093
ucer-0.088
rolley-0.086
aved-0.082
erek-0.079
Token.
Token ID13
Feature activation-2.49e-01

Pos logit contributions
arp+0.338
aved+0.310
 Joey+0.310
 sorts+0.306
 unst+0.305
Neg logit contributions
 aids-0.274
 hair-0.239
 jokes-0.236
 song-0.232
 poems-0.230
Token They
Token ID1119
Feature activation+5.37e-01

Pos logit contributions
 aids+0.016
 hair+0.013
 jokes+0.013
 Dancing+0.013
 cheeks+0.012
Neg logit contributions
arp-0.019
 unst-0.018
aved-0.018
 sorts-0.018
ucer-0.017
Token trimmed
Token ID40325
Feature activation-3.03e-01

Pos logit contributions
arp+0.043
 unst+0.040
wood+0.039
 extingu+0.038
ucer+0.038
Neg logit contributions
 aids-0.028
 hair-0.027
 jokes-0.025
 cheeks-0.025
 curly-0.024
Token the
Token ID262
Feature activation+2.80e-01

Pos logit contributions
 aids+0.018
 hair+0.018
 jokes+0.017
 cheeks+0.017
 song+0.016
Neg logit contributions
arp-0.022
aved-0.021
 scaven-0.021
 unst-0.021
 sorts-0.021
Token hed
Token ID16418
Feature activation+1.19e+01

Pos logit contributions
 sorts+0.016
 Joey+0.016
arp+0.015
aved+0.015
 unst+0.015
Neg logit contributions
 hair-0.022
 aids-0.021
 cheeks-0.020
 song-0.020
 jokes-0.019
Tokenges
Token ID3212
Feature activation+8.01e-01

Pos logit contributions
 unst+0.681
arp+0.672
 sorts+0.667
 Joey+0.658
 scaven+0.650
Neg logit contributions
 aids-0.899
 Dancing-0.801
 wig-0.787
ggie-0.762
 hair-0.753
Token and
Token ID290
Feature activation+1.16e-01

Pos logit contributions
arp+0.058
ucer+0.056
 unst+0.056
aved+0.056
erek+0.055
Neg logit contributions
 aids-0.050
 hair-0.045
 jokes-0.045
 song-0.043
 poems-0.042
Token cut
Token ID2005
Feature activation+1.18e+00

Pos logit contributions
arp+0.008
aved+0.007
 unst+0.007
rolley+0.007
 Joey+0.007
Neg logit contributions
 aids-0.008
 jokes-0.007
 hair-0.007
 song-0.007
 cheeks-0.007
Token the
Token ID262
Feature activation+3.32e-01

Pos logit contributions
arp+0.079
 sorts+0.077
aved+0.076
rolley+0.075
 scaven+0.075
Neg logit contributions
 aids-0.080
 hair-0.076
 jokes-0.071
 cheeks-0.067
 song-0.067
Token grass
Token ID8701
Feature activation+1.27e+00

Pos logit contributions
 sorts+0.020
 Joey+0.020
arp+0.019
erek+0.019
neath+0.019
Neg logit contributions
 hair-0.025
 aids-0.024
 cheeks-0.023
 song-0.023
 jokes-0.022
Token for
Token ID329
Feature activation+3.04e+00

Pos logit contributions
 aids+0.238
 song+0.220
 jokes+0.210
 hair+0.208
ggie+0.207
Neg logit contributions
arp-0.211
aved-0.210
 unst-0.204
 Joey-0.202
erek-0.200
Token my
Token ID616
Feature activation-1.51e+00

Pos logit contributions
arp+0.176
 unst+0.171
 sorts+0.170
 Joey+0.169
aved+0.167
Neg logit contributions
 aids-0.241
 song-0.211
 jokes-0.211
 hair-0.208
ggie-0.207
Token son
Token ID3367
Feature activation+2.23e+00

Pos logit contributions
 aids+0.103
 song+0.088
 jokes+0.087
 hair+0.086
ggie+0.085
Neg logit contributions
arp-0.104
 unst-0.102
 Joey-0.102
 sorts-0.101
aved-0.100
Token."
Token ID526
Feature activation+8.10e-01

Pos logit contributions
arp+0.133
 unst+0.131
 Joey+0.130
 sorts+0.130
aved+0.127
Neg logit contributions
 aids-0.171
 song-0.149
 jokes-0.148
 hair-0.146
 wig-0.146
Token The
Token ID383
Feature activation-1.73e+00

Pos logit contributions
arp+0.057
 Joey+0.057
 unst+0.057
 sorts+0.056
 Mill+0.056
Neg logit contributions
 aids-0.053
 song-0.045
 jokes-0.045
ggie-0.044
 wig-0.044
Token handy
Token ID15728
Feature activation+1.18e+01

Pos logit contributions
 aids+0.112
 jokes+0.093
 song+0.093
 wig+0.091
ggie+0.091
Neg logit contributions
arp-0.127
 unst-0.125
 Joey-0.124
 sorts-0.124
 Mill-0.121
Token man
Token ID582
Feature activation+9.65e-01

Pos logit contributions
arp+0.746
 Joey+0.729
 sorts+0.723
 Mill+0.722
 unst+0.720
Neg logit contributions
 aids-0.858
 jokes-0.743
 Dancing-0.740
 hair-0.729
 wig-0.729
Token said
Token ID531
Feature activation+8.21e-02

Pos logit contributions
 Joey+0.056
 sorts+0.055
 Mill+0.054
 unst+0.054
arp+0.054
Neg logit contributions
 aids-0.074
 Dancing-0.066
 poems-0.064
 wig-0.064
 song-0.064
Token he
Token ID339
Feature activation-7.91e-01

Pos logit contributions
 Joey+0.004
 unst+0.004
 Mill+0.004
 Bobby+0.004
 Suz+0.004
Neg logit contributions
 aids-0.007
 Dancing-0.006
 wig-0.006
 poems-0.006
 song-0.006
Token could
Token ID714
Feature activation+1.37e+00

Pos logit contributions
 aids+0.060
 jokes+0.052
 song+0.052
ggie+0.052
 hair+0.051
Neg logit contributions
arp-0.049
 unst-0.047
 Joey-0.047
 sorts-0.047
aved-0.045
Token help
Token ID1037
Feature activation+3.18e+00

Pos logit contributions
arp+0.091
 sorts+0.087
 hed+0.086
 Joey+0.085
aved+0.085
Neg logit contributions
 aids-0.096
 hair-0.086
 song-0.085
ggie-0.084
 jokes-0.084
Token of
Token ID286
Feature activation-5.91e-02

Pos logit contributions
arp+0.226
 extingu+0.225
aved+0.217
 sorts+0.211
 hed+0.211
Neg logit contributions
 aids-0.197
 song-0.169
ggie-0.167
 jokes-0.166
 cheeks-0.165
Token salt
Token ID8268
Feature activation+4.03e+00

Pos logit contributions
 hair+0.004
 aids+0.004
 jokes+0.004
 wig+0.004
 poems+0.004
Neg logit contributions
aved-0.004
 unst-0.004
 Mill-0.003
neath-0.003
arp-0.003
Token could
Token ID714
Feature activation+1.37e+00

Pos logit contributions
arp+0.245
aved+0.237
 sorts+0.230
 unst+0.230
rolley+0.224
Neg logit contributions
 aids-0.303
 jokes-0.278
 hair-0.272
 song-0.271
 poems-0.268
Token come
Token ID1282
Feature activation-2.94e-01

Pos logit contributions
 sorts+0.107
arp+0.104
rolley+0.103
aved+0.102
erek+0.102
Neg logit contributions
 aids-0.078
 song-0.069
 hair-0.068
ggie-0.067
 jokes-0.067
Token in
Token ID287
Feature activation-1.67e+00

Pos logit contributions
 aids+0.018
 song+0.018
 hair+0.017
ggie+0.016
 songs+0.015
Neg logit contributions
 sorts-0.020
erek-0.019
 hed-0.019
aved-0.018
ylan-0.018
Token handy
Token ID15728
Feature activation+1.18e+01

Pos logit contributions
 aids+0.095
 song+0.090
 hair+0.089
 poems+0.083
 yoga+0.082
Neg logit contributions
aved-0.127
ucer-0.119
erek-0.118
arp-0.117
vell-0.110
Token,"
Token ID553
Feature activation+2.59e+00

Pos logit contributions
arp+0.612
 unst+0.595
 Joey+0.589
 sorts+0.586
aved+0.581
Neg logit contributions
 aids-1.010
 song-0.897
 jokes-0.891
ggie-0.881
 hair-0.881
Token so
Token ID523
Feature activation-1.32e+00

Pos logit contributions
 Joey+0.171
arp+0.171
 unst+0.168
 sorts+0.166
 Mill+0.166
Neg logit contributions
 aids-0.185
 song-0.157
 jokes-0.156
 wig-0.154
ggie-0.153
Token he
Token ID339
Feature activation-7.54e-01

Pos logit contributions
 aids+0.089
 song+0.076
 jokes+0.076
 hair+0.074
 wig+0.074
Neg logit contributions
arp-0.091
 unst-0.090
 Joey-0.089
 sorts-0.089
aved-0.087
Token scoop
Token ID23529
Feature activation+1.10e+00

Pos logit contributions
 aids+0.058
 Dancing+0.051
 song+0.049
 jokes+0.048
 poems+0.048
Neg logit contributions
 Joey-0.046
 unst-0.046
arp-0.045
 Mill-0.044
 scaven-0.044
Tokened
Token ID276
Feature activation+5.87e-01

Pos logit contributions
 sorts+0.087
 hed+0.084
 scaven+0.084
 haven+0.084
 shed+0.083
Neg logit contributions
 aids-0.055
 hair-0.055
ggie-0.049
 jokes-0.046
 cheeks-0.045
Token Mr
Token ID1770
Feature activation+5.44e+00

Pos logit contributions
 aids+0.033
 jokes+0.029
 hair+0.029
 song+0.028
 poems+0.028
Neg logit contributions
arp-0.034
 Joey-0.033
 unst-0.033
 sorts-0.033
aved-0.033
Token.
Token ID13
Feature activation-7.88e-01

Pos logit contributions
arp+0.366
 unst+0.356
 Joey+0.355
 sorts+0.352
aved+0.348
Neg logit contributions
 aids-0.385
 song-0.326
 jokes-0.326
 wig-0.320
 hair-0.319
Token Lee
Token ID5741
Feature activation-1.42e+00

Pos logit contributions
 aids+0.060
 jokes+0.052
 song+0.052
 hair+0.051
 wig+0.051
Neg logit contributions
arp-0.048
 unst-0.047
 sorts-0.047
aved-0.047
 Joey-0.046
Token,
Token ID11
Feature activation-1.18e-01

Pos logit contributions
 aids+0.104
 song+0.091
ggie+0.089
 wig+0.088
 jokes+0.088
Neg logit contributions
 unst-0.087
 Joey-0.084
 sorts-0.084
aved-0.084
arp-0.083
Token the
Token ID262
Feature activation+1.89e-01

Pos logit contributions
 aids+0.008
 jokes+0.007
 song+0.007
 hair+0.007
 wig+0.007
Neg logit contributions
arp-0.008
 unst-0.008
 sorts-0.008
 Joey-0.008
aved-0.008
Token handy
Token ID15728
Feature activation+1.17e+01

Pos logit contributions
arp+0.013
 unst+0.013
 sorts+0.013
 Joey+0.013
aved+0.013
Neg logit contributions
 aids-0.013
 jokes-0.011
ggie-0.010
 song-0.010
 hair-0.010
Tokenman
Token ID805
Feature activation-8.08e-01

Pos logit contributions
arp+0.737
 extingu+0.714
 sorts+0.711
 Joey+0.701
 unst+0.700
Neg logit contributions
 aids-0.850
 jokes-0.736
 Dancing-0.728
 wig-0.716
 poems-0.715
Token.
Token ID13
Feature activation-7.73e-01

Pos logit contributions
 aids+0.060
 song+0.052
 jokes+0.051
 poems+0.050
ggie+0.050
Neg logit contributions
 unst-0.050
 Joey-0.050
arp-0.050
 sorts-0.049
aved-0.048
Token He
Token ID679
Feature activation-4.73e-01

Pos logit contributions
 aids+0.053
 song+0.045
 jokes+0.045
ggie+0.044
 hair+0.044
Neg logit contributions
arp-0.053
 unst-0.052
 Joey-0.052
 sorts-0.052
aved-0.051
Token is
Token ID318
Feature activation+2.00e-01

Pos logit contributions
 aids+0.034
 jokes+0.029
 song+0.029
 hair+0.029
 wig+0.029
Neg logit contributions
arp-0.031
 unst-0.030
 Joey-0.030
 sorts-0.030
aved-0.029
Token fixing
Token ID18682
Feature activation+4.06e+00

Pos logit contributions
 unst+0.014
 Joey+0.013
 handy+0.013
 Mill+0.013
 deeper+0.013
Neg logit contributions
 aids-0.014
 cheeks-0.012
 song-0.012
 jokes-0.012
uren-0.012
Token excitement
Token ID14067
Feature activation-2.52e-01

Pos logit contributions
 aids+0.087
 poems+0.071
uren+0.070
 wig+0.070
ggie+0.069
Neg logit contributions
 Joey-0.095
 unst-0.092
arp-0.091
 afloat-0.089
aved-0.088
Token growing
Token ID3957
Feature activation+3.32e+00

Pos logit contributions
 aids+0.019
 jokes+0.016
 song+0.016
 wig+0.016
ggie+0.016
Neg logit contributions
arp-0.015
 unst-0.015
 Joey-0.015
 sorts-0.015
aved-0.015
Token.
Token ID13
Feature activation+1.51e-01

Pos logit contributions
arp+0.214
 sorts+0.207
 Joey+0.206
 Mill+0.206
 unst+0.202
Neg logit contributions
 aids-0.238
 song-0.211
 hair-0.206
 jokes-0.206
ggie-0.202
Token He
Token ID679
Feature activation+2.68e-01

Pos logit contributions
 Joey+0.011
arp+0.010
 unst+0.010
 sorts+0.010
 Mill+0.010
Neg logit contributions
 aids-0.010
 song-0.009
 jokes-0.009
 wig-0.009
 poems-0.009
Token quickly
Token ID2952
Feature activation+5.39e+00

Pos logit contributions
arp+0.017
 Joey+0.017
 unst+0.016
 sorts+0.016
aved+0.016
Neg logit contributions
 aids-0.020
 song-0.017
 jokes-0.017
 wig-0.017
 hair-0.017
Token shed
Token ID14999
Feature activation+1.09e+01

Pos logit contributions
arp+0.357
 unst+0.350
 Joey+0.348
 sorts+0.347
aved+0.340
Neg logit contributions
 aids-0.379
 song-0.326
 jokes-0.326
 hair-0.320
ggie-0.318
Token his
Token ID465
Feature activation-1.29e+00

Pos logit contributions
 sorts+0.755
arp+0.749
 Joey+0.715
aved+0.698
 Mill+0.697
Neg logit contributions
 aids-0.727
 hair-0.652
ggie-0.630
 cheeks-0.625
 song-0.618
Token clothes
Token ID8242
Feature activation-5.90e-01

Pos logit contributions
 aids+0.081
 song+0.065
 Dancing+0.065
ggie+0.065
 jokes+0.065
Neg logit contributions
arp-0.096
 Joey-0.096
 unst-0.095
 sorts-0.092
 Mill-0.091
Token and
Token ID290
Feature activation+5.23e-01

Pos logit contributions
 hair+0.030
 aids+0.030
 cheeks+0.029
 song+0.027
 wig+0.026
Neg logit contributions
 sorts-0.048
arp-0.047
 Joey-0.044
 hed-0.044
 Mill-0.044
Token plunged
Token ID31460
Feature activation+3.08e+00

Pos logit contributions
arp+0.041
aved+0.039
 sorts+0.038
 unst+0.038
neath+0.037
Neg logit contributions
 aids-0.030
 hair-0.029
 cheeks-0.028
 jokes-0.027
 wig-0.027
Token into
Token ID656
Feature activation+3.57e-01

Pos logit contributions
 sorts+0.236
arp+0.234
rolley+0.228
ucer+0.216
pling+0.214
Neg logit contributions
 hair-0.175
 aids-0.149
 curly-0.149
 blond-0.143
 cheeks-0.139
Token he
Token ID339
Feature activation-3.77e-01

Pos logit contributions
 aids+0.078
 Dancing+0.069
 wig+0.068
 poems+0.067
 song+0.066
Neg logit contributions
 Joey-0.051
 Mill-0.048
 Bobby-0.045
 sorts-0.045
 unst-0.044
Token went
Token ID1816
Feature activation+1.30e+00

Pos logit contributions
 aids+0.030
 Dancing+0.025
 song+0.025
 jokes+0.025
 hair+0.025
Neg logit contributions
 Joey-0.023
 unst-0.022
arp-0.022
aved-0.022
 sorts-0.021
Token to
Token ID284
Feature activation-8.07e-01

Pos logit contributions
arp+0.079
 sorts+0.076
aved+0.074
 Joey+0.074
 unst+0.074
Neg logit contributions
 aids-0.098
 hair-0.087
 jokes-0.087
 song-0.086
 wig-0.086
Token the
Token ID262
Feature activation+7.44e-01

Pos logit contributions
 aids+0.053
 jokes+0.047
 song+0.045
 hair+0.045
 haircut+0.044
Neg logit contributions
arp-0.063
aved-0.058
ucer-0.056
rolley-0.056
pling-0.053
Token garden
Token ID11376
Feature activation+3.10e+00

Pos logit contributions
arp+0.048
 unst+0.047
 Joey+0.047
 sorts+0.047
 hed+0.046
Neg logit contributions
 aids-0.054
 jokes-0.044
 cheeks-0.044
 poems-0.044
 Dancing-0.044
Token shed
Token ID14999
Feature activation+1.09e+01

Pos logit contributions
arp+0.250
aved+0.242
 unst+0.240
 Joey+0.236
neath+0.234
Neg logit contributions
 aids-0.173
 song-0.149
 hair-0.148
 jokes-0.146
 poems-0.139
Token and
Token ID290
Feature activation+4.92e-01

Pos logit contributions
arp+0.886
aved+0.850
 Joey+0.839
 sorts+0.828
neath+0.826
Neg logit contributions
 aids-0.582
 hair-0.506
 song-0.495
 jokes-0.472
 cheeks-0.466
Token found
Token ID1043
Feature activation+4.59e+00

Pos logit contributions
arp+0.040
aved+0.035
 sorts+0.034
rolley+0.034
 unst+0.034
Neg logit contributions
 aids-0.027
 hair-0.025
 cheeks-0.023
 wig-0.023
 song-0.023
Token a
Token ID257
Feature activation+6.27e-01

Pos logit contributions
arp+0.454
rying+0.433
aved+0.428
 haven+0.423
keeping+0.421
Neg logit contributions
 hair-0.135
 aids-0.135
 jokes-0.118
 His-0.115
ggie-0.111
Token stick
Token ID4859
Feature activation+1.82e+00

Pos logit contributions
arp+0.042
aved+0.041
neath+0.040
 Joey+0.039
 unst+0.039
Neg logit contributions
 aids-0.043
 song-0.041
 wig-0.040
 hair-0.039
ggie-0.039
Token.
Token ID13
Feature activation+1.82e-01

Pos logit contributions
arp+0.132
 Joey+0.127
 sorts+0.127
 unst+0.126
 Mill+0.126
Neg logit contributions
 aids-0.116
 song-0.100
 hair-0.099
 jokes-0.098
ggie-0.097
Token a
Token ID257
Feature activation+2.40e-01

Pos logit contributions
arp+0.014
 unst+0.014
 Joey+0.014
 sorts+0.014
aved+0.013
Neg logit contributions
 aids-0.015
 jokes-0.013
 song-0.013
 hair-0.013
ggie-0.013
Token little
Token ID1310
Feature activation-1.32e+00

Pos logit contributions
arp+0.016
 Joey+0.016
 unst+0.016
 Mill+0.015
 sorts+0.015
Neg logit contributions
 aids-0.017
 jokes-0.014
 cheeks-0.014
 poems-0.014
 hair-0.014
Token girl
Token ID2576
Feature activation+1.73e-01

Pos logit contributions
 aids+0.081
 song+0.075
 hair+0.073
 wig+0.072
 jokes+0.071
Neg logit contributions
 unst-0.096
aved-0.093
arp-0.093
 sorts-0.093
 Joey-0.091
Token named
Token ID3706
Feature activation-1.55e+00

Pos logit contributions
arp+0.010
 sorts+0.010
 Mill+0.010
 Joey+0.009
 Suz+0.009
Neg logit contributions
 aids-0.014
 jokes-0.012
 cheeks-0.012
 poems-0.012
uren-0.012
Token Jo
Token ID5302
Feature activation+1.66e+00

Pos logit contributions
 aids+0.112
 jokes+0.095
 wig+0.094
 song+0.093
ggie+0.093
Neg logit contributions
 Mill-0.103
 unst-0.101
 Joey-0.100
arp-0.099
 sorts-0.098
Tokenanna
Token ID7697
Feature activation-1.08e+01

Pos logit contributions
arp+0.093
 Mill+0.092
 sorts+0.090
 Joey+0.089
aved+0.087
Neg logit contributions
 aids-0.137
 jokes-0.122
 poems-0.116
 wig-0.115
 Dancing-0.113
Token.
Token ID13
Feature activation-4.08e-01

Pos logit contributions
 aids+0.771
 jokes+0.657
 song+0.648
 wig+0.640
 poems+0.639
Neg logit contributions
arp-0.712
 unst-0.702
 Joey-0.695
 sorts-0.692
aved-0.687
Token Jo
Token ID5302
Feature activation+1.69e+00

Pos logit contributions
 aids+0.027
 song+0.023
 jokes+0.023
 hair+0.023
 Dancing+0.023
Neg logit contributions
arp-0.028
 unst-0.028
 Joey-0.028
 sorts-0.027
aved-0.027
Tokenanna
Token ID7697
Feature activation-1.08e+01

Pos logit contributions
arp+0.146
 sorts+0.143
 Mill+0.143
 Joey+0.142
aved+0.140
Neg logit contributions
 aids-0.087
 jokes-0.071
 wig-0.069
 poems-0.067
 song-0.066
Token lived
Token ID5615
Feature activation+1.67e+00

Pos logit contributions
 aids+0.746
 hair+0.652
 song+0.650
 jokes+0.640
ggie+0.636
Neg logit contributions
arp-0.713
 unst-0.703
 Joey-0.694
 sorts-0.684
aved-0.668
Token in
Token ID287
Feature activation-1.66e+00

Pos logit contributions
arp+0.113
 Joey+0.110
 unst+0.110
 sorts+0.109
aved+0.107
Neg logit contributions
 aids-0.115
 song-0.100
 jokes-0.099
 hair-0.099
ggie-0.097
Token,
Token ID11
Feature activation+1.16e-01

Pos logit contributions
 aids+0.315
 song+0.264
 jokes+0.264
 wig+0.264
 Dancing+0.262
Neg logit contributions
arp-0.267
 sorts-0.263
 unst-0.260
 Joey-0.260
aved-0.256
Token or
Token ID393
Feature activation-1.38e+00

Pos logit contributions
 Joey+0.007
 unst+0.007
arp+0.007
 sorts+0.007
 Mill+0.007
Neg logit contributions
 aids-0.009
ggie-0.007
 song-0.007
 jokes-0.007
 wig-0.007
Token in
Token ID287
Feature activation-1.65e+00

Pos logit contributions
 aids+0.115
ggie+0.102
 wig+0.099
uren+0.099
 song+0.098
Neg logit contributions
 Joey-0.073
 sorts-0.070
 Mill-0.070
 unst-0.070
 deeper-0.068
Token the
Token ID262
Feature activation+3.79e-01

Pos logit contributions
 aids+0.119
 hair+0.104
 song+0.103
 jokes+0.103
 poems+0.101
Neg logit contributions
arp-0.112
 unst-0.108
 Joey-0.108
aved-0.107
 Mill-0.104
Token sav
Token ID6799
Feature activation+3.64e+00

Pos logit contributions
arp+0.023
 unst+0.022
 Joey+0.022
 sorts+0.022
aved+0.022
Neg logit contributions
 aids-0.029
 song-0.025
 jokes-0.025
 hair-0.025
 wig-0.025
Tokenanna
Token ID7697
Feature activation-1.08e+01

Pos logit contributions
arp+0.222
 unst+0.219
rying+0.207
ylan+0.206
aved+0.206
Neg logit contributions
 aids-0.281
 song-0.250
 jokes-0.249
ggie-0.242
 Dancing-0.239
Token with
Token ID351
Feature activation-9.15e-01

Pos logit contributions
 aids+0.777
 jokes+0.663
 song+0.658
ggie+0.656
 wig+0.655
Neg logit contributions
arp-0.690
 unst-0.684
 Joey-0.678
 sorts-0.672
aved-0.666
Token the
Token ID262
Feature activation+4.09e-01

Pos logit contributions
 aids+0.069
 song+0.059
 jokes+0.059
 hair+0.058
 wig+0.058
Neg logit contributions
arp-0.057
 unst-0.056
 Joey-0.055
 sorts-0.055
aved-0.054
Token lion
Token ID18744
Feature activation-2.55e+00

Pos logit contributions
arp+0.028
 unst+0.027
 Joey+0.027
 sorts+0.027
aved+0.026
Neg logit contributions
 aids-0.028
ggie-0.023
 jokes-0.023
 song-0.023
 wig-0.023
Token,
Token ID11
Feature activation+1.92e-01

Pos logit contributions
 aids+0.190
 wig+0.162
ggie+0.161
 Dancing+0.160
uren+0.159
Neg logit contributions
 Joey-0.150
arp-0.150
 sorts-0.149
 Mill-0.146
 unst-0.145
Token or
Token ID393
Feature activation-1.32e+00

Pos logit contributions
 Joey+0.012
 unst+0.012
 sorts+0.012
arp+0.012
 Mill+0.011
Neg logit contributions
 aids-0.014
ggie-0.012
 song-0.012
 jokes-0.012
 wig-0.012
Token little
Token ID1310
Feature activation-1.48e+00

Pos logit contributions
 Joey+0.002
arp+0.002
 unst+0.002
 sorts+0.002
 deeper+0.002
Neg logit contributions
 aids-0.003
ggie-0.003
 hair-0.003
 poems-0.003
uren-0.003
Token fish
Token ID5916
Feature activation-4.89e-01

Pos logit contributions
 aids+0.123
 song+0.107
 jokes+0.107
ggie+0.106
 hair+0.106
Neg logit contributions
arp-0.080
 Joey-0.079
 unst-0.078
 sorts-0.078
aved-0.076
Token.
Token ID13
Feature activation-3.93e-01

Pos logit contributions
 aids+0.040
 poems+0.034
uren+0.034
 wig+0.034
 hair+0.033
Neg logit contributions
 Joey-0.029
 sorts-0.028
arp-0.028
 unst-0.027
aved-0.027
Token "
Token ID366
Feature activation-7.46e-01

Pos logit contributions
 aids+0.030
 song+0.025
 poems+0.025
 wig+0.025
ggie+0.025
Neg logit contributions
 Joey-0.028
 Mill-0.026
 Bobby-0.024
 unst-0.024
 Suz-0.024
TokenW
Token ID54
Feature activation-1.42e-01

Pos logit contributions
 aids+0.064
 cheeks+0.057
 hair+0.056
 poems+0.056
 jokes+0.055
Neg logit contributions
arp-0.039
 Joey-0.038
 sorts-0.037
 unst-0.037
aved-0.036
Tokenanna
Token ID7697
Feature activation-1.08e+01

Pos logit contributions
 aids+0.008
 jokes+0.007
ggie+0.007
 song+0.007
 hair+0.007
Neg logit contributions
arp-0.011
 unst-0.011
neath-0.011
 extingu-0.011
aved-0.011
Token play
Token ID711
Feature activation-2.58e+00

Pos logit contributions
 aids+0.729
 jokes+0.666
 song+0.662
 hair+0.659
 Dancing+0.639
Neg logit contributions
arp-0.726
 extingu-0.680
 unst-0.675
rolley-0.672
neath-0.671
Token with
Token ID351
Feature activation-1.04e+00

Pos logit contributions
 aids+0.167
 jokes+0.153
 song+0.152
ggie+0.144
 poems+0.143
Neg logit contributions
arp-0.185
 Mill-0.179
 unst-0.179
aved-0.179
 extingu-0.177
Token me
Token ID502
Feature activation-2.24e+00

Pos logit contributions
 aids+0.054
 jokes+0.052
 song+0.046
 hair+0.046
 poems+0.044
Neg logit contributions
arp-0.089
aved-0.088
rolley-0.087
 extingu-0.086
ucer-0.086
Token?"
Token ID1701
Feature activation-2.83e+00

Pos logit contributions
 aids+0.188
 song+0.169
 jokes+0.168
 hair+0.166
ggie+0.165
Neg logit contributions
arp-0.119
 unst-0.115
 Joey-0.114
 sorts-0.112
aved-0.112
Token Bob
Token ID5811
Feature activation+1.78e+00

Pos logit contributions
 aids+0.274
 poems+0.240
 wig+0.235
 song+0.234
ggie+0.228
Neg logit contributions
 Joey-0.150
 Mill-0.133
 Bobby-0.123
 Suz-0.120
 Wil-0.119
Token named
Token ID3706
Feature activation-1.55e+00

Pos logit contributions
arp+0.010
 sorts+0.010
 Mill+0.010
 Joey+0.009
 Suz+0.009
Neg logit contributions
 aids-0.014
 jokes-0.012
 cheeks-0.012
 poems-0.012
uren-0.012
Token Jo
Token ID5302
Feature activation+1.66e+00

Pos logit contributions
 aids+0.112
 jokes+0.095
 wig+0.094
 song+0.093
ggie+0.093
Neg logit contributions
 Mill-0.103
 unst-0.101
 Joey-0.100
arp-0.099
 sorts-0.098
Tokenanna
Token ID7697
Feature activation-1.08e+01

Pos logit contributions
arp+0.093
 Mill+0.092
 sorts+0.090
 Joey+0.089
aved+0.087
Neg logit contributions
 aids-0.137
 jokes-0.122
 poems-0.116
 wig-0.115
 Dancing-0.113
Token.
Token ID13
Feature activation-4.08e-01

Pos logit contributions
 aids+0.771
 jokes+0.657
 song+0.648
 wig+0.640
 poems+0.639
Neg logit contributions
arp-0.712
 unst-0.702
 Joey-0.695
 sorts-0.692
aved-0.687
Token Jo
Token ID5302
Feature activation+1.69e+00

Pos logit contributions
 aids+0.027
 song+0.023
 jokes+0.023
 hair+0.023
 Dancing+0.023
Neg logit contributions
arp-0.028
 unst-0.028
 Joey-0.028
 sorts-0.027
aved-0.027
Tokenanna
Token ID7697
Feature activation-1.08e+01

Pos logit contributions
arp+0.146
 sorts+0.143
 Mill+0.143
 Joey+0.142
aved+0.140
Neg logit contributions
 aids-0.087
 jokes-0.071
 wig-0.069
 poems-0.067
 song-0.066
Token lived
Token ID5615
Feature activation+1.67e+00

Pos logit contributions
 aids+0.746
 hair+0.652
 song+0.650
 jokes+0.640
ggie+0.636
Neg logit contributions
arp-0.713
 unst-0.703
 Joey-0.694
 sorts-0.684
aved-0.668
Token in
Token ID287
Feature activation-1.66e+00

Pos logit contributions
arp+0.113
 Joey+0.110
 unst+0.110
 sorts+0.109
aved+0.107
Neg logit contributions
 aids-0.115
 song-0.100
 jokes-0.099
 hair-0.099
ggie-0.097
Token a
Token ID257
Feature activation+2.36e-01

Pos logit contributions
 aids+0.118
 song+0.102
 jokes+0.101
 hair+0.100
ggie+0.099
Neg logit contributions
arp-0.110
 unst-0.108
 Joey-0.107
 sorts-0.106
aved-0.105
Token village
Token ID7404
Feature activation+2.52e+00

Pos logit contributions
arp+0.016
 unst+0.015
 Joey+0.015
 sorts+0.015
aved+0.015
Neg logit contributions
 aids-0.017
 song-0.014
 jokes-0.014
 hair-0.014
 wig-0.014
Token near
Token ID1474
Feature activation+8.26e-01

Pos logit contributions
 sorts+0.160
arp+0.158
 Joey+0.153
 unst+0.152
 Mill+0.150
Neg logit contributions
 aids-0.188
 jokes-0.162
 wig-0.158
 poems-0.157
 song-0.156
Token friends
Token ID2460
Feature activation-2.59e+00

Pos logit contributions
 aids+0.360
 cheeks+0.309
uren+0.303
 Dancing+0.290
ggie+0.287
Neg logit contributions
 unst-0.279
 sorts-0.262
 Joey-0.259
arp-0.249
 deeper-0.246
Token.
Token ID13
Feature activation-9.30e-01

Pos logit contributions
 aids+0.215
 cheeks+0.183
uren+0.183
 wig+0.180
 jokes+0.180
Neg logit contributions
arp-0.141
 unst-0.140
 sorts-0.136
 Joey-0.132
aved-0.128
Token But
Token ID887
Feature activation-1.71e+00

Pos logit contributions
 aids+0.074
 poems+0.065
ggie+0.065
 wig+0.064
 song+0.063
Neg logit contributions
 Joey-0.053
 unst-0.051
arp-0.051
 Mill-0.050
 sorts-0.049
Token no
Token ID645
Feature activation+9.39e-01

Pos logit contributions
 aids+0.123
 song+0.104
 jokes+0.104
ggie+0.103
 hair+0.103
Neg logit contributions
arp-0.111
 unst-0.110
 Joey-0.110
 sorts-0.108
 Mill-0.106
Token more
Token ID517
Feature activation-3.02e+00

Pos logit contributions
 sorts+0.055
 hed+0.053
 Joey+0.053
 deeper+0.053
 unst+0.050
Neg logit contributions
 aids-0.076
uren-0.064
ggie-0.062
agged-0.060
 blond-0.060
Token jokes
Token ID14532
Feature activation-1.07e+01

Pos logit contributions
 aids+0.217
uren+0.194
ggie+0.185
 wig+0.178
 cheeks+0.174
Neg logit contributions
 hed-0.188
 Joey-0.183
 sorts-0.182
 unst-0.171
 deeper-0.170
Token.
Token ID13
Feature activation-9.04e-01

Pos logit contributions
 aids+0.902
 song+0.794
 jokes+0.793
 hair+0.782
ggie+0.779
Neg logit contributions
arp-0.562
 unst-0.549
 Joey-0.546
 sorts-0.543
aved-0.531
Token And
Token ID843
Feature activation+1.74e+00

Pos logit contributions
 aids+0.073
ggie+0.071
 wig+0.068
 poems+0.068
 haircut+0.067
Neg logit contributions
 Joey-0.046
arp-0.043
 Mill-0.042
 extingu-0.042
 unst-0.042
Token no
Token ID645
Feature activation+9.59e-01

Pos logit contributions
 Joey+0.093
 unst+0.091
 sorts+0.088
 Mill+0.088
 hed+0.085
Neg logit contributions
 aids-0.145
ggie-0.124
 wig-0.124
 song-0.122
 poems-0.121
Token more
Token ID517
Feature activation-2.98e+00

Pos logit contributions
 sorts+0.056
 deeper+0.054
 hed+0.053
 Joey+0.052
 unst+0.051
Neg logit contributions
 aids-0.076
uren-0.067
ggie-0.064
 Dancing-0.061
 blond-0.061
Token slides
Token ID19392
Feature activation-3.83e+00

Pos logit contributions
 aids+0.189
uren+0.171
ggie+0.166
 wig+0.160
 blond+0.153
Neg logit contributions
 Joey-0.201
 hed-0.199
 sorts-0.198
 unst-0.187
 deeper-0.184
Token.
Token ID13
Feature activation-8.76e-01

Pos logit contributions
 aids+0.134
ggie+0.119
uren+0.117
 blond+0.115
 wig+0.114
Neg logit contributions
 Joey-0.076
 sorts-0.073
 Mill-0.072
 hed-0.070
arp-0.070
Token They
Token ID1119
Feature activation-1.83e-02

Pos logit contributions
 aids+0.080
ggie+0.075
 wig+0.074
 song+0.072
 poems+0.070
Neg logit contributions
 Joey-0.039
 Mill-0.038
 hed-0.036
 sorts-0.035
arp-0.034
Token do
Token ID466
Feature activation-2.93e+00

Pos logit contributions
 aids+0.001
 jokes+0.001
 hair+0.001
 song+0.001
 wig+0.001
Neg logit contributions
arp-0.001
 Joey-0.001
 Mill-0.001
 unst-0.001
rolley-0.001
Token not
Token ID407
Feature activation-3.05e+00

Pos logit contributions
 aids+0.197
 blond+0.194
 cheeks+0.188
 blonde+0.181
 wig+0.175
Neg logit contributions
 sorts-0.183
 unst-0.179
 ourselves-0.177
 if-0.171
'll-0.171
Token need
Token ID761
Feature activation+2.78e+00

Pos logit contributions
 aids+0.262
 poems+0.233
ggie+0.232
uren+0.228
 wig+0.223
Neg logit contributions
 Joey-0.150
 sorts-0.144
aved-0.143
 unst-0.140
 Mill-0.136
Token jokes
Token ID14532
Feature activation-1.07e+01

Pos logit contributions
 Joey+0.168
 unst+0.163
 sorts+0.163
 Mill+0.162
arp+0.158
Neg logit contributions
 aids-0.211
ggie-0.179
uren-0.178
 song-0.178
 wig-0.178
Token.
Token ID13
Feature activation-9.06e-01

Pos logit contributions
 aids+0.862
uren+0.737
 wig+0.728
 cheeks+0.724
ggie+0.723
Neg logit contributions
 unst-0.589
 sorts-0.560
arp-0.560
aved-0.560
 Joey-0.557
Token They
Token ID1119
Feature activation-5.45e-02

Pos logit contributions
 aids+0.082
 wig+0.077
ggie+0.077
 song+0.075
 poems+0.073
Neg logit contributions
 Joey-0.039
 Mill-0.037
 hed-0.037
arp-0.035
 sorts-0.035
Token need
Token ID761
Feature activation+2.74e+00

Pos logit contributions
 aids+0.005
 song+0.004
 jokes+0.004
ggie+0.004
 hair+0.004
Neg logit contributions
arp-0.003
 unst-0.003
 Joey-0.003
 sorts-0.003
aved-0.003
Token hugs
Token ID40657
Feature activation-4.00e-01

Pos logit contributions
 Joey+0.166
 sorts+0.164
 unst+0.164
arp+0.163
 Mill+0.160
Neg logit contributions
 aids-0.203
ggie-0.173
 wig-0.171
 song-0.171
uren-0.170
Token.
Token ID13
Feature activation-9.60e-01

Pos logit contributions
 aids+0.032
ggie+0.028
 wig+0.027
uren+0.027
 blond+0.027
Neg logit contributions
arp-0.022
 unst-0.022
 Joey-0.022
 sorts-0.021
 Mill-0.021
Token.
Token ID13
Feature activation-3.64e-01

Pos logit contributions
arp+0.432
 sorts+0.423
 unst+0.413
 Joey+0.411
aved+0.405
Neg logit contributions
 aids-0.501
 jokes-0.434
 wig-0.423
 song-0.422
 poems-0.421
Token Every
Token ID3887
Feature activation-2.00e+00

Pos logit contributions
 aids+0.025
 jokes+0.021
 song+0.021
 wig+0.021
ggie+0.021
Neg logit contributions
arp-0.025
 sorts-0.024
 Joey-0.024
 unst-0.024
 Mill-0.024
Token day
Token ID1110
Feature activation-1.63e+00

Pos logit contributions
 aids+0.161
 wig+0.143
 cheeks+0.142
 jokes+0.142
 hair+0.140
Neg logit contributions
 sorts-0.118
arp-0.113
 Joey-0.112
 Mill-0.108
aved-0.106
Token,
Token ID11
Feature activation+5.87e-02

Pos logit contributions
 aids+0.128
 jokes+0.110
 song+0.109
 poems+0.108
 wig+0.108
Neg logit contributions
 Joey-0.097
 Mill-0.096
arp-0.096
 sorts-0.096
 unst-0.095
Token Jo
Token ID5302
Feature activation+1.73e+00

Pos logit contributions
arp+0.004
 unst+0.004
 Joey+0.004
 sorts+0.004
aved+0.004
Neg logit contributions
 aids-0.004
 song-0.003
 jokes-0.003
 hair-0.003
ggie-0.003
Tokenanna
Token ID7697
Feature activation-1.07e+01

Pos logit contributions
arp+0.170
 Mill+0.166
 sorts+0.163
 Joey+0.163
aved+0.162
Neg logit contributions
 aids-0.072
 jokes-0.057
 wig-0.054
 poems-0.052
 hair-0.049
Token would
Token ID561
Feature activation+8.23e-01

Pos logit contributions
 aids+0.705
 hair+0.631
 song+0.615
 jokes+0.604
ggie+0.588
Neg logit contributions
arp-0.727
 unst-0.720
 Joey-0.718
 sorts-0.703
 hed-0.703
Token go
Token ID467
Feature activation-5.47e-01

Pos logit contributions
arp+0.060
 unst+0.058
 Joey+0.057
aved+0.056
ucer+0.056
Neg logit contributions
 aids-0.054
 song-0.047
 jokes-0.046
 hair-0.045
ggie-0.044
Token to
Token ID284
Feature activation-1.23e+00

Pos logit contributions
 hair+0.026
 song+0.026
 aids+0.025
 wig+0.023
 songs+0.023
Neg logit contributions
arp-0.043
 Joey-0.041
rolley-0.040
 sorts-0.040
 extingu-0.040
Token the
Token ID262
Feature activation+2.19e-01

Pos logit contributions
 hair+0.056
 aids+0.053
 haircut+0.053
 song+0.053
 yoga+0.052
Neg logit contributions
arp-0.114
aved-0.110
ucer-0.108
pling-0.104
rol-0.103
Token mill
Token ID3939
Feature activation+6.83e+00

Pos logit contributions
 Joey+0.012
aved+0.011
 Mill+0.011
 aback+0.011
 Suz+0.011
Neg logit contributions
 aids-0.017
 song-0.016
 hair-0.016
 jokes-0.015
 clown-0.015
Token pictures
Token ID5986
Feature activation-3.79e+00

Pos logit contributions
arp+0.024
 unst+0.023
aved+0.023
 Joey+0.023
 extingu+0.023
Neg logit contributions
 aids-0.027
 jokes-0.024
 song-0.024
 poems-0.023
 hair-0.023
Token and
Token ID290
Feature activation+3.76e-01

Pos logit contributions
 aids+0.269
 song+0.235
 jokes+0.234
 hair+0.229
 poems+0.228
Neg logit contributions
arp-0.251
 unst-0.246
 Joey-0.242
aved-0.240
 sorts-0.236
Token words
Token ID2456
Feature activation-4.25e+00

Pos logit contributions
arp+0.026
 unst+0.025
 Joey+0.025
aved+0.025
 sorts+0.024
Neg logit contributions
 aids-0.026
 jokes-0.023
 song-0.023
 hair-0.022
 poems-0.022
Token.
Token ID13
Feature activation+1.59e-02

Pos logit contributions
 aids+0.330
 song+0.287
 jokes+0.287
 hair+0.282
 wig+0.282
Neg logit contributions
arp-0.248
 unst-0.243
 Joey-0.242
 sorts-0.241
aved-0.236
Token W
Token ID370
Feature activation+1.90e+00

Pos logit contributions
arp+0.001
 unst+0.001
 sorts+0.001
 Joey+0.001
aved+0.001
Neg logit contributions
 aids-0.001
 jokes-0.001
 song-0.001
 hair-0.001
 Dancing-0.001
Tokenanna
Token ID7697
Feature activation-1.07e+01

Pos logit contributions
 Joey+0.127
 unst+0.127
arp+0.126
 sorts+0.126
 Mill+0.125
Neg logit contributions
 aids-0.132
 jokes-0.112
ggie-0.110
 hair-0.110
 song-0.109
Token try
Token ID1949
Feature activation-1.45e+00

Pos logit contributions
 aids+0.888
 jokes+0.788
 song+0.787
 hair+0.786
 wig+0.761
Neg logit contributions
arp-0.571
 unst-0.555
 Joey-0.540
 sorts-0.529
 hed-0.521
Token me
Token ID502
Feature activation-1.94e+00

Pos logit contributions
 aids+0.111
 wig+0.096
ggie+0.095
 cheeks+0.095
 song+0.095
Neg logit contributions
 Joey-0.083
 sorts-0.083
arp-0.082
 unst-0.082
 Mill-0.081
Token out
Token ID503
Feature activation+4.04e+00

Pos logit contributions
 aids+0.147
 song+0.128
 jokes+0.128
 hair+0.127
ggie+0.125
Neg logit contributions
arp-0.118
 unst-0.115
 Joey-0.114
 sorts-0.114
aved-0.112
Token?"
Token ID1701
Feature activation-2.47e+00

Pos logit contributions
arp+0.222
 unst+0.218
 Joey+0.216
 sorts+0.215
aved+0.211
Neg logit contributions
 aids-0.329
 song-0.288
 jokes-0.287
 hair-0.283
ggie-0.282
Token Mike
Token ID4995
Feature activation+3.70e+00

Pos logit contributions
 aids+0.187
 song+0.163
 jokes+0.161
 poems+0.160
 wig+0.158
Neg logit contributions
 Joey-0.153
arp-0.152
 sorts-0.150
 unst-0.149
 Mill-0.148
Token together
Token ID1978
Feature activation+3.05e+00

Pos logit contributions
 aids+0.161
 jokes+0.145
 song+0.145
 hair+0.142
ggie+0.141
Neg logit contributions
arp-0.115
 unst-0.111
 Joey-0.111
 sorts-0.110
aved-0.108
Token one
Token ID530
Feature activation-3.23e+00

Pos logit contributions
 sorts+0.168
 Joey+0.165
 unst+0.163
arp+0.160
aved+0.159
Neg logit contributions
 aids-0.252
 wig-0.213
 cheeks-0.210
 jokes-0.210
 song-0.209
Token day
Token ID1110
Feature activation-1.58e+00

Pos logit contributions
 aids+0.265
 cheeks+0.229
 jokes+0.222
 blond+0.220
 wig+0.220
Neg logit contributions
 sorts-0.195
arp-0.187
 unst-0.179
 Joey-0.177
 deeper-0.168
Token when
Token ID618
Feature activation-6.09e-01

Pos logit contributions
 aids+0.116
 song+0.099
 jokes+0.098
 wig+0.097
ggie+0.097
Neg logit contributions
arp-0.101
 Joey-0.100
 unst-0.100
 sorts-0.099
 Mill-0.097
Token Bre
Token ID3719
Feature activation+8.80e-01

Pos logit contributions
 aids+0.053
 song+0.045
 cheeks+0.043
 jokes+0.043
 wig+0.043
Neg logit contributions
 Joey-0.034
 Mill-0.032
 sorts-0.031
arp-0.031
 Suz-0.030
Tokenanna
Token ID7697
Feature activation-1.07e+01

Pos logit contributions
arp+0.073
 Joey+0.072
 sorts+0.071
aved+0.070
 Mill+0.070
Neg logit contributions
 aids-0.047
 song-0.038
 jokes-0.038
 hair-0.038
 wig-0.037
Token said
Token ID531
Feature activation+2.04e-01

Pos logit contributions
 aids+0.637
 hair+0.576
 jokes+0.543
 cheeks+0.533
 wig+0.524
Neg logit contributions
arp-0.802
 sorts-0.763
 unst-0.762
 hed-0.755
 extingu-0.740
Token,
Token ID11
Feature activation+3.34e-01

Pos logit contributions
 Joey+0.012
 Mill+0.011
 unst+0.010
 Bobby+0.010
 Suz+0.010
Neg logit contributions
 aids-0.016
 song-0.014
 wig-0.014
 cheeks-0.014
 poems-0.014
Token "
Token ID366
Feature activation-4.73e-01

Pos logit contributions
 Joey+0.025
 Mill+0.024
 Bobby+0.023
 unst+0.023
 Suz+0.022
Neg logit contributions
 aids-0.022
ggie-0.018
 song-0.018
 wig-0.018
 hair-0.018
TokenLet
Token ID5756
Feature activation+2.73e+00

Pos logit contributions
 aids+0.042
 jokes+0.037
 cheeks+0.036
 song+0.036
 hair+0.036
Neg logit contributions
arp-0.024
 sorts-0.023
 Joey-0.023
aved-0.023
 unst-0.022
Token's
Token ID338
Feature activation-3.19e+00

Pos logit contributions
 Joey+0.208
 unst+0.206
arp+0.204
 Mill+0.202
 sorts+0.201
Neg logit contributions
 aids-0.163
 wig-0.138
 cheeks-0.132
 Dancing-0.131
 song-0.131
Token a
Token ID257
Feature activation+1.86e-01

Pos logit contributions
 aids+0.001
ggie+0.001
 song+0.001
 hair+0.001
 jokes+0.001
Neg logit contributions
arp-0.001
 unst-0.001
 sorts-0.001
aved-0.001
 Joey-0.001
Token little
Token ID1310
Feature activation-1.32e+00

Pos logit contributions
arp+0.012
 Joey+0.012
 unst+0.012
 Mill+0.012
 scaven+0.011
Neg logit contributions
 aids-0.014
 jokes-0.011
 poems-0.011
 cheeks-0.011
 hair-0.011
Token girl
Token ID2576
Feature activation+2.09e-01

Pos logit contributions
 aids+0.080
 song+0.074
 hair+0.072
 wig+0.071
 jokes+0.070
Neg logit contributions
 unst-0.097
aved-0.093
arp-0.093
 sorts-0.093
neath-0.091
Token named
Token ID3706
Feature activation-1.53e+00

Pos logit contributions
arp+0.017
 unst+0.017
 Joey+0.017
 sorts+0.016
aved+0.016
Neg logit contributions
 aids-0.012
 song-0.010
 hair-0.010
 jokes-0.009
ggie-0.009
Token Jo
Token ID5302
Feature activation+1.82e+00

Pos logit contributions
 aids+0.090
 hair+0.074
 song+0.074
 jokes+0.073
ggie+0.071
Neg logit contributions
arp-0.122
 unst-0.119
 sorts-0.118
 Joey-0.117
aved-0.116
Tokenanna
Token ID7697
Feature activation-1.07e+01

Pos logit contributions
arp+0.116
 Joey+0.114
 sorts+0.113
 Mill+0.113
aved+0.112
Neg logit contributions
 aids-0.134
 jokes-0.117
 song-0.115
 poems-0.115
 wig-0.113
Token was
Token ID373
Feature activation+1.82e-01

Pos logit contributions
 aids+0.656
 hair+0.616
 song+0.567
 cheeks+0.560
ggie+0.555
Neg logit contributions
arp-0.763
 hed-0.729
 sorts-0.729
 Joey-0.727
 unst-0.726
Token walking
Token ID6155
Feature activation-2.76e+00

Pos logit contributions
 unst+0.012
 Joey+0.012
 Mill+0.012
 sorts+0.012
aved+0.011
Neg logit contributions
 aids-0.013
 jokes-0.011
 song-0.011
 wig-0.011
 poems-0.011
Token through
Token ID832
Feature activation+2.86e+00

Pos logit contributions
 aids+0.224
 song+0.195
 jokes+0.195
 hair+0.192
ggie+0.192
Neg logit contributions
arp-0.156
 unst-0.153
 Joey-0.152
 sorts-0.152
aved-0.148
Token a
Token ID257
Feature activation+1.68e-01

Pos logit contributions
arp+0.185
 unst+0.182
aved+0.177
 Joey+0.177
 sorts+0.174
Neg logit contributions
 aids-0.208
 song-0.182
 hair-0.182
 jokes-0.181
 poems-0.176
Token field
Token ID2214
Feature activation+2.31e+00

Pos logit contributions
 unst+0.010
arp+0.010
 Joey+0.010
 sorts+0.010
aved+0.010
Neg logit contributions
 aids-0.013
 song-0.011
 hair-0.011
 jokes-0.011
ggie-0.011
Token were
Token ID547
Feature activation+3.95e+00

Pos logit contributions
arp+0.016
 unst+0.016
 extingu+0.015
wood+0.015
aved+0.015
Neg logit contributions
 aids-0.011
ggie-0.010
 hair-0.009
 Dancing-0.009
 jokes-0.009
Token two
Token ID734
Feature activation+2.03e-01

Pos logit contributions
arp+0.264
 unst+0.259
 sorts+0.256
 Joey+0.254
aved+0.252
Neg logit contributions
 aids-0.275
 jokes-0.237
 song-0.237
 hair-0.234
ggie-0.231
Token friends
Token ID2460
Feature activation-2.10e+00

Pos logit contributions
arp+0.014
 Joey+0.014
 sorts+0.014
 unst+0.014
 Mill+0.013
Neg logit contributions
 aids-0.014
 Dancing-0.011
 song-0.011
 wig-0.011
ggie-0.011
Token,
Token ID11
Feature activation+2.23e-01

Pos logit contributions
 aids+0.152
 song+0.129
 jokes+0.128
 wig+0.127
 poems+0.126
Neg logit contributions
 Joey-0.139
arp-0.138
 sorts-0.135
 Mill-0.134
 unst-0.134
Token Bre
Token ID3719
Feature activation+8.41e-01

Pos logit contributions
arp+0.015
 unst+0.014
 sorts+0.014
aved+0.014
 Joey+0.014
Neg logit contributions
 aids-0.016
 song-0.014
 jokes-0.014
 hair-0.013
 wig-0.013
Tokenanna
Token ID7697
Feature activation-1.07e+01

Pos logit contributions
arp+0.066
 unst+0.065
 Joey+0.064
 sorts+0.064
aved+0.063
Neg logit contributions
 aids-0.049
 song-0.041
 jokes-0.041
ggie-0.040
 hair-0.040
Token and
Token ID290
Feature activation+2.10e-01

Pos logit contributions
 aids+0.684
 song+0.594
 hair+0.590
 jokes+0.582
ggie+0.576
Neg logit contributions
arp-0.756
 unst-0.738
 sorts-0.734
 Joey-0.730
aved-0.719
Token Mason
Token ID14737
Feature activation+1.05e+00

Pos logit contributions
 Joey+0.011
arp+0.011
 unst+0.011
 sorts+0.011
 Mill+0.011
Neg logit contributions
 aids-0.017
 song-0.015
 jokes-0.015
 hair-0.015
 wig-0.015
Token.
Token ID13
Feature activation-2.99e-02

Pos logit contributions
arp+0.070
 unst+0.069
 Joey+0.069
 sorts+0.068
aved+0.067
Neg logit contributions
 aids-0.074
 song-0.063
 jokes-0.062
 wig-0.061
 hair-0.061
Token They
Token ID1119
Feature activation+7.52e-01

Pos logit contributions
 aids+0.002
 song+0.002
 jokes+0.002
ggie+0.002
 wig+0.002
Neg logit contributions
arp-0.002
 Joey-0.002
 sorts-0.002
 unst-0.002
aved-0.002
Token were
Token ID547
Feature activation+3.94e+00

Pos logit contributions
arp+0.060
 unst+0.059
 extingu+0.057
rolley+0.056
ucer+0.055
Neg logit contributions
 aids-0.042
 jokes-0.039
 hair-0.038
 song-0.037
 Dancing-0.035
Token you
Token ID345
Feature activation+5.75e-01

Pos logit contributions
arp+0.195
 unst+0.191
 Joey+0.189
 sorts+0.189
aved+0.185
Neg logit contributions
 aids-0.251
 song-0.218
 jokes-0.218
 hair-0.214
ggie-0.213
Token?"
Token ID1701
Feature activation-2.70e+00

Pos logit contributions
arp+0.034
 unst+0.033
 Joey+0.033
 sorts+0.033
aved+0.032
Neg logit contributions
 aids-0.045
 song-0.039
 jokes-0.039
 hair-0.038
 wig-0.038
Token
Token ID198
Feature activation+1.07e-01

Pos logit contributions
 aids+0.238
 poems+0.213
 wig+0.208
 jokes+0.207
 song+0.205
Neg logit contributions
 Mill-0.139
 Joey-0.137
 sorts-0.135
arp-0.130
 Suz-0.130
Token
Token ID198
Feature activation+1.19e-01

Pos logit contributions
arp+0.007
 unst+0.007
 Joey+0.007
 sorts+0.007
aved+0.007
Neg logit contributions
 aids-0.008
 song-0.007
 jokes-0.007
 hair-0.007
ggie-0.007
TokenJo
Token ID9908
Feature activation-9.64e-01

Pos logit contributions
arp+0.008
 sorts+0.008
 Joey+0.008
 unst+0.008
 Mill+0.007
Neg logit contributions
 aids-0.009
 jokes-0.007
 song-0.007
 hair-0.007
 poems-0.007
Tokenanna
Token ID7697
Feature activation-1.07e+01

Pos logit contributions
 aids+0.052
 poems+0.046
 jokes+0.045
 wig+0.045
 Dancing+0.045
Neg logit contributions
arp-0.079
 Mill-0.078
 Joey-0.078
aved-0.075
 unst-0.075
Token was
Token ID373
Feature activation+3.85e-01

Pos logit contributions
 aids+0.720
 jokes+0.616
 hair+0.612
 song+0.611
ggie+0.601
Neg logit contributions
arp-0.742
 unst-0.718
 sorts-0.709
 Joey-0.699
aved-0.693
Token so
Token ID523
Feature activation-1.20e+00

Pos logit contributions
 Joey+0.021
 unst+0.021
 Mill+0.020
 sorts+0.020
 aback+0.019
Neg logit contributions
 aids-0.029
 wig-0.029
 song-0.028
 poems-0.028
uren-0.028
Token surprised
Token ID6655
Feature activation-2.64e-01

Pos logit contributions
 aids+0.074
 song+0.062
 jokes+0.062
 hair+0.060
 wig+0.060
Neg logit contributions
arp-0.090
 unst-0.089
 Joey-0.088
 sorts-0.088
aved-0.087
Token that
Token ID326
Feature activation-1.91e+00

Pos logit contributions
 aids+0.022
 wig+0.018
ggie+0.018
 hair+0.018
 song+0.018
Neg logit contributions
 Joey-0.016
 Mill-0.016
 sorts-0.015
arp-0.015
 unst-0.015
Token the
Token ID262
Feature activation+6.41e-01

Pos logit contributions
 aids+0.129
 jokes+0.109
 song+0.108
 wig+0.108
ggie+0.107
Neg logit contributions
 Joey-0.132
arp-0.132
 sorts-0.131
 unst-0.131
 Mill-0.129
Token a
Token ID257
Feature activation+3.50e-01

Pos logit contributions
arp+0.024
 unst+0.023
 sorts+0.023
 Joey+0.023
aved+0.023
Neg logit contributions
 aids-0.024
 jokes-0.021
 song-0.021
 hair-0.020
ggie-0.020
Token little
Token ID1310
Feature activation-1.12e+00

Pos logit contributions
arp+0.024
 Joey+0.024
 unst+0.023
 Mill+0.023
 sorts+0.023
Neg logit contributions
 aids-0.025
 jokes-0.020
 poems-0.020
 cheeks-0.020
ggie-0.019
Token girl
Token ID2576
Feature activation+3.86e-01

Pos logit contributions
 aids+0.066
 song+0.063
 hair+0.060
 jokes+0.059
 wig+0.059
Neg logit contributions
 unst-0.083
aved-0.081
arp-0.080
 sorts-0.079
neath-0.079
Token called
Token ID1444
Feature activation+8.67e-01

Pos logit contributions
arp+0.023
 sorts+0.023
 Mill+0.023
 Joey+0.022
 Suz+0.022
Neg logit contributions
 aids-0.031
 jokes-0.027
 poems-0.026
 cheeks-0.025
uren-0.025
Token Jo
Token ID5302
Feature activation+1.88e+00

Pos logit contributions
arp+0.063
 unst+0.062
 sorts+0.061
 Joey+0.061
aved+0.060
Neg logit contributions
 aids-0.056
 song-0.047
 jokes-0.047
 hair-0.047
ggie-0.046
Tokenanna
Token ID7697
Feature activation-1.06e+01

Pos logit contributions
arp+0.133
 Mill+0.133
 Joey+0.129
 sorts+0.129
 Suz+0.125
Neg logit contributions
 aids-0.129
 jokes-0.111
 poems-0.107
 wig-0.104
 hair-0.103
Token who
Token ID508
Feature activation-1.80e+00

Pos logit contributions
 aids+0.761
 jokes+0.647
 song+0.640
 wig+0.633
 poems+0.629
Neg logit contributions
arp-0.703
 unst-0.690
 Joey-0.687
 sorts-0.684
aved-0.674
Token lived
Token ID5615
Feature activation+1.84e+00

Pos logit contributions
 aids+0.122
 song+0.103
 jokes+0.103
 hair+0.101
 wig+0.101
Neg logit contributions
arp-0.125
 unst-0.123
 sorts-0.123
 Joey-0.123
aved-0.121
Token in
Token ID287
Feature activation-1.49e+00

Pos logit contributions
arp+0.128
 Joey+0.124
 sorts+0.124
 unst+0.123
 Mill+0.121
Neg logit contributions
 aids-0.122
 song-0.107
 hair-0.106
 jokes-0.105
ggie-0.104
Token the
Token ID262
Feature activation+4.88e-01

Pos logit contributions
 aids+0.108
 song+0.093
 jokes+0.092
 hair+0.091
ggie+0.090
Neg logit contributions
arp-0.097
 unst-0.095
 Joey-0.094
 sorts-0.094
aved-0.093
Token countryside
Token ID25708
Feature activation+3.60e+00

Pos logit contributions
 unst+0.028
arp+0.028
aved+0.027
 sorts+0.027
 Joey+0.027
Neg logit contributions
 aids-0.039
 song-0.034
 hair-0.034
 jokes-0.034
 Dancing-0.033
Token the
Token ID262
Feature activation+4.48e-01

Pos logit contributions
 aids+0.082
 jokes+0.074
 song+0.073
 hair+0.072
 poems+0.070
Neg logit contributions
arp-0.089
aved-0.085
 unst-0.082
ucer-0.080
 Joey-0.080
Token jungle
Token ID20712
Feature activation-1.92e+00

Pos logit contributions
 Joey+0.030
 unst+0.030
arp+0.030
aved+0.029
 sorts+0.029
Neg logit contributions
 aids-0.032
 song-0.029
 jokes-0.028
 wig-0.028
 hair-0.028
Token,
Token ID11
Feature activation+2.04e-01

Pos logit contributions
 aids+0.133
 song+0.115
 jokes+0.114
 hair+0.112
ggie+0.111
Neg logit contributions
arp-0.130
 unst-0.128
 Joey-0.127
 sorts-0.125
aved-0.124
Token the
Token ID262
Feature activation+4.44e-01

Pos logit contributions
 unst+0.013
 Joey+0.013
 sorts+0.012
arp+0.012
 Mill+0.012
Neg logit contributions
 aids-0.015
ggie-0.013
 song-0.013
 jokes-0.013
 hair-0.013
Token sav
Token ID6799
Feature activation+3.75e+00

Pos logit contributions
arp+0.032
 unst+0.032
 sorts+0.032
 Joey+0.032
aved+0.031
Neg logit contributions
 aids-0.028
 jokes-0.023
 song-0.023
ggie-0.023
 hair-0.023
Tokenanna
Token ID7697
Feature activation-1.06e+01

Pos logit contributions
arp+0.223
 unst+0.219
aved+0.205
ucer+0.202
rying+0.201
Neg logit contributions
 aids-0.300
 jokes-0.268
 song-0.268
ggie-0.255
 Dancing-0.252
Token,
Token ID11
Feature activation+2.40e-01

Pos logit contributions
 aids+0.726
 song+0.632
 jokes+0.627
 hair+0.625
 wig+0.610
Neg logit contributions
arp-0.720
 unst-0.700
 sorts-0.697
 Joey-0.696
aved-0.676
Token the
Token ID262
Feature activation+4.65e-01

Pos logit contributions
arp+0.016
 unst+0.015
 Joey+0.015
 sorts+0.015
aved+0.015
Neg logit contributions
 aids-0.017
 song-0.015
 jokes-0.015
 hair-0.015
 wig-0.015
Token desert
Token ID10326
Feature activation+4.31e-01

Pos logit contributions
arp+0.032
 unst+0.032
 sorts+0.032
 Joey+0.031
 hed+0.031
Neg logit contributions
 aids-0.031
ggie-0.026
 jokes-0.026
 song-0.025
 hair-0.025
Token and
Token ID290
Feature activation+1.64e-01

Pos logit contributions
arp+0.026
 Joey+0.025
 unst+0.025
 sorts+0.025
 Mill+0.025
Neg logit contributions
 aids-0.033
 song-0.028
 jokes-0.028
 wig-0.028
 Dancing-0.027
Token the
Token ID262
Feature activation+4.32e-01

Pos logit contributions
arp+0.010
 unst+0.010
 Joey+0.010
 sorts+0.010
aved+0.009
Neg logit contributions
 aids-0.013
 song-0.011
 jokes-0.011
 hair-0.011
 wig-0.011
Token the
Token ID262
Feature activation+5.99e-01

Pos logit contributions
 aids+0.081
 song+0.070
 wig+0.070
 jokes+0.069
ggie+0.069
Neg logit contributions
arp-0.058
 sorts-0.057
 unst-0.057
 Joey-0.057
 Mill-0.055
Token dolls
Token ID36062
Feature activation-3.63e+00

Pos logit contributions
arp+0.040
 sorts+0.040
 Joey+0.040
 unst+0.040
 hed+0.038
Neg logit contributions
 aids-0.041
ggie-0.034
 hair-0.033
 wig-0.033
 Dancing-0.033
Token.
Token ID13
Feature activation-6.53e-01

Pos logit contributions
 aids+0.283
 jokes+0.240
ggie+0.238
 wig+0.238
 song+0.238
Neg logit contributions
arp-0.214
 unst-0.213
 sorts-0.212
aved-0.207
 Joey-0.206
Token They
Token ID1119
Feature activation+2.17e-01

Pos logit contributions
 aids+0.055
 wig+0.052
ggie+0.051
ggy+0.048
 song+0.048
Neg logit contributions
 Mill-0.033
 Joey-0.032
 hed-0.032
 sorts-0.031
 unst-0.031
Token told
Token ID1297
Feature activation-2.05e-01

Pos logit contributions
arp+0.015
 unst+0.015
 sorts+0.015
 Joey+0.014
aved+0.014
Neg logit contributions
 aids-0.015
 song-0.013
 jokes-0.012
ggie-0.012
 hair-0.012
Token jokes
Token ID14532
Feature activation-1.06e+01

Pos logit contributions
 aids+0.015
 wig+0.014
ggie+0.014
uren+0.013
 Dancing+0.013
Neg logit contributions
 Joey-0.012
 Mill-0.012
 Bobby-0.011
 sorts-0.011
 hed-0.011
Token and
Token ID290
Feature activation-7.37e-02

Pos logit contributions
 aids+0.807
 blond+0.694
 hair+0.687
 wig+0.685
 cheeks+0.682
Neg logit contributions
 Joey-0.617
 sorts-0.616
arp-0.590
 Mill-0.586
 unst-0.584
Token stories
Token ID3923
Feature activation-5.71e+00

Pos logit contributions
 aids+0.004
ggie+0.004
uren+0.004
 Dancing+0.004
agging+0.004
Neg logit contributions
 sorts-0.005
 Joey-0.005
 hed-0.005
 Mill-0.005
 unst-0.005
Token.
Token ID13
Feature activation-6.87e-01

Pos logit contributions
 aids+0.419
 wig+0.357
 hair+0.352
ggie+0.350
 cheeks+0.349
Neg logit contributions
 sorts-0.350
 unst-0.346
arp-0.344
aved-0.339
 Joey-0.339
Token They
Token ID1119
Feature activation+2.07e-01

Pos logit contributions
 aids+0.058
ggie+0.057
 wig+0.057
ggy+0.054
 haircut+0.053
Neg logit contributions
 Mill-0.033
 Joey-0.033
 hed-0.030
 Bobby-0.030
neath-0.029
Token hugged
Token ID41130
Feature activation-1.01e+00

Pos logit contributions
 sorts+0.013
arp+0.013
 Joey+0.013
 unst+0.013
aved+0.013
Neg logit contributions
 aids-0.015
 song-0.013
ggie-0.012
 hair-0.012
 jokes-0.012
Token
Token ID198
Feature activation+1.88e-01

Pos logit contributions
arp+0.012
 Joey+0.012
 sorts+0.012
 unst+0.011
aved+0.011
Neg logit contributions
 aids-0.014
 jokes-0.013
 song-0.012
 wig-0.012
 hair-0.012
TokenOne
Token ID3198
Feature activation-3.15e+00

Pos logit contributions
 sorts+0.014
arp+0.014
 Mill+0.013
aved+0.013
 Joey+0.013
Neg logit contributions
 aids-0.012
 cheeks-0.010
 wig-0.010
 jokes-0.010
 poems-0.010
Token day
Token ID1110
Feature activation-1.57e+00

Pos logit contributions
 aids+0.266
 wig+0.233
 cheeks+0.229
 jokes+0.228
 poems+0.225
Neg logit contributions
 sorts-0.183
 Joey-0.178
arp-0.178
 Mill-0.170
 unst-0.167
Token,
Token ID11
Feature activation+1.91e-01

Pos logit contributions
 aids+0.117
 jokes+0.100
 song+0.100
 wig+0.098
 poems+0.098
Neg logit contributions
arp-0.098
 Joey-0.097
 unst-0.096
 sorts-0.096
 Mill-0.095
Token Jo
Token ID5302
Feature activation+1.84e+00

Pos logit contributions
arp+0.011
 unst+0.011
 Joey+0.011
 sorts+0.011
aved+0.011
Neg logit contributions
 aids-0.015
 song-0.013
 jokes-0.013
 hair-0.013
ggie-0.013
Tokenanna
Token ID7697
Feature activation-1.06e+01

Pos logit contributions
arp+0.178
 Mill+0.175
 Joey+0.172
aved+0.171
 sorts+0.171
Neg logit contributions
 aids-0.079
 jokes-0.064
 wig-0.060
 poems-0.059
 song-0.055
Token dared
Token ID28765
Feature activation+2.22e+00

Pos logit contributions
 aids+0.632
 hair+0.580
 song+0.543
ggie+0.528
 cheeks+0.524
Neg logit contributions
arp-0.764
 hed-0.764
 sorts-0.749
 Joey-0.746
 unst-0.746
Token to
Token ID284
Feature activation-1.18e+00

Pos logit contributions
 Mill+0.136
 Joey+0.133
 unst+0.125
 Suz+0.125
 hed+0.119
Neg logit contributions
 aids-0.174
 wig-0.153
ggie-0.149
 song-0.144
 Dancing-0.144
Token venture
Token ID13189
Feature activation+1.76e+00

Pos logit contributions
 aids+0.079
 song+0.069
 hair+0.069
 jokes+0.069
ggie+0.066
Neg logit contributions
arp-0.083
 unst-0.080
aved-0.078
 sorts-0.078
 Joey-0.078
Token into
Token ID656
Feature activation-1.55e-01

Pos logit contributions
arp+0.105
 sorts+0.100
aved+0.096
 Joey+0.095
 Mill+0.095
Neg logit contributions
 aids-0.132
 hair-0.125
 jokes-0.118
 song-0.116
 poems-0.114
Token the
Token ID262
Feature activation+3.25e-01

Pos logit contributions
 aids+0.009
 hair+0.008
 yoga+0.008
 poems+0.007
 song+0.007
Neg logit contributions
arp-0.013
aved-0.012
ucer-0.012
 unst-0.012
 Joey-0.011
Token "
Token ID366
Feature activation-7.88e-01

Pos logit contributions
 Joey+0.003
 Mill+0.003
 Bobby+0.003
 unst+0.003
 Suz+0.003
Neg logit contributions
 aids-0.005
 poems-0.004
ggie-0.004
 wig-0.004
 hair-0.004
TokenYes
Token ID5297
Feature activation+1.20e+00

Pos logit contributions
 aids+0.082
 cheeks+0.072
 poems+0.072
 hair+0.071
 jokes+0.071
Neg logit contributions
 sorts-0.028
arp-0.027
 Joey-0.026
 unst-0.025
aved-0.025
Token,
Token ID11
Feature activation+3.63e-02

Pos logit contributions
 Joey+0.069
arp+0.068
 unst+0.068
 Mill+0.066
 sorts+0.065
Neg logit contributions
 aids-0.096
 song-0.083
 jokes-0.083
 poems-0.082
 hair-0.081
Token I
Token ID314
Feature activation-1.13e+00

Pos logit contributions
 Joey+0.002
 Mill+0.002
 unst+0.002
arp+0.002
 sorts+0.002
Neg logit contributions
 aids-0.003
 hair-0.002
ggie-0.002
 poems-0.002
 wig-0.002
Token like
Token ID588
Feature activation+6.12e-01

Pos logit contributions
 aids+0.076
 song+0.069
 jokes+0.068
ggie+0.067
 wig+0.066
Neg logit contributions
arp-0.079
 Joey-0.075
 Mill-0.075
 hed-0.075
rolley-0.073
Token jokes
Token ID14532
Feature activation-1.06e+01

Pos logit contributions
 Joey+0.036
 sorts+0.034
 Mill+0.032
 Bobby+0.032
 hed+0.031
Neg logit contributions
 aids-0.048
 cheeks-0.041
 blond-0.041
agged-0.041
uren-0.041
Token!"
Token ID2474
Feature activation+3.03e+00

Pos logit contributions
 aids+1.072
 cheeks+0.936
 song+0.935
 hair+0.934
 wig+0.933
Neg logit contributions
 sorts-0.365
arp-0.364
 Joey-0.363
 unst-0.349
 Mill-0.334
Token Sally
Token ID25737
Feature activation+2.80e+00

Pos logit contributions
 Joey+0.165
 Mill+0.161
 unst+0.154
 sorts+0.153
 Suz+0.152
Neg logit contributions
 aids-0.261
ggie-0.237
 wig-0.227
 poems-0.224
 jokes-0.223
Token told
Token ID1297
Feature activation-2.11e-01

Pos logit contributions
 Joey+0.173
 sorts+0.171
 Mill+0.165
'll+0.161
 Bobby+0.157
Neg logit contributions
 aids-0.212
 Dancing-0.178
agging-0.177
 poems-0.176
 wig-0.173
Token a
Token ID257
Feature activation+2.14e-01

Pos logit contributions
 aids+0.016
 song+0.014
 wig+0.014
 poems+0.013
 Dancing+0.013
Neg logit contributions
 Joey-0.013
 Mill-0.013
 unst-0.013
arp-0.012
 Suz-0.012
Token funny
Token ID8258
Feature activation-4.84e+00

Pos logit contributions
 sorts+0.017
 Joey+0.016
 Mill+0.016
'll+0.016
 unst+0.015
Neg logit contributions
 aids-0.013
 hair-0.011
agged-0.011
 poems-0.011
agging-0.010
Token
Token ID198
Feature activation+1.77e-01

Pos logit contributions
arp+0.011
 unst+0.011
 Joey+0.011
 sorts+0.011
aved+0.011
Neg logit contributions
 aids-0.013
 song-0.011
 jokes-0.011
 hair-0.011
 wig-0.011
TokenOne
Token ID3198
Feature activation-3.27e+00

Pos logit contributions
 sorts+0.014
arp+0.014
aved+0.013
 Mill+0.013
 Joey+0.013
Neg logit contributions
 aids-0.011
 jokes-0.009
 wig-0.009
 cheeks-0.009
 poems-0.009
Token day
Token ID1110
Feature activation-1.58e+00

Pos logit contributions
 aids+0.303
 wig+0.269
 cheeks+0.266
 jokes+0.259
 hair+0.257
Neg logit contributions
 sorts-0.172
 Joey-0.159
 Mill-0.150
arp-0.143
 Suz-0.142
Token,
Token ID11
Feature activation+8.50e-02

Pos logit contributions
 aids+0.121
 jokes+0.104
 song+0.104
 poems+0.102
 wig+0.102
Neg logit contributions
 Joey-0.096
arp-0.096
 Mill-0.095
 sorts-0.095
 unst-0.094
Token Jo
Token ID5302
Feature activation+1.78e+00

Pos logit contributions
arp+0.005
 unst+0.005
 Joey+0.005
 sorts+0.005
aved+0.005
Neg logit contributions
 aids-0.007
 song-0.006
 jokes-0.006
 hair-0.006
ggie-0.006
Tokenanna
Token ID7697
Feature activation-1.06e+01

Pos logit contributions
arp+0.162
 Mill+0.160
 Joey+0.158
aved+0.158
 sorts+0.157
Neg logit contributions
 aids-0.084
 jokes-0.070
 poems-0.066
 wig-0.065
 song-0.063
Token saw
Token ID2497
Feature activation+4.73e-01

Pos logit contributions
 aids+0.603
 hair+0.572
 song+0.508
 cheeks+0.505
 jokes+0.499
Neg logit contributions
arp-0.799
 extingu-0.771
 unst-0.759
 hed-0.758
 Joey-0.748
Token a
Token ID257
Feature activation+2.21e-01

Pos logit contributions
arp+0.029
 Joey+0.029
 sorts+0.029
 unst+0.028
 Mill+0.028
Neg logit contributions
 aids-0.036
 song-0.031
 jokes-0.030
 wig-0.030
ggie-0.030
Token giant
Token ID6175
Feature activation-3.08e-01

Pos logit contributions
arp+0.015
 unst+0.015
 Joey+0.015
 sorts+0.014
aved+0.014
Neg logit contributions
 aids-0.015
 song-0.013
 jokes-0.013
 hair-0.013
 wig-0.013
Token stone
Token ID7815
Feature activation+3.36e+00

Pos logit contributions
 aids+0.025
 jokes+0.021
 Dancing+0.021
ggie+0.021
 song+0.021
Neg logit contributions
arp-0.017
 sorts-0.017
 Joey-0.017
 unst-0.017
 hed-0.016
Token wall
Token ID3355
Feature activation+2.42e+00

Pos logit contributions
arp+0.180
 sorts+0.179
 unst+0.177
aved+0.174
 Joey+0.172
Neg logit contributions
 aids-0.278
 jokes-0.239
uren-0.235
 Dancing-0.232
 cheeks-0.230
Token a
Token ID257
Feature activation+2.84e-01

Pos logit contributions
arp+0.020
 unst+0.020
 sorts+0.019
aved+0.019
 Joey+0.019
Neg logit contributions
 aids-0.019
 jokes-0.017
 hair-0.016
 song-0.016
ggie-0.016
Token smart
Token ID4451
Feature activation+1.44e-01

Pos logit contributions
arp+0.019
 Joey+0.019
 unst+0.018
 scaven+0.018
 sorts+0.018
Neg logit contributions
 aids-0.021
 jokes-0.017
 cheeks-0.017
 poems-0.016
 hair-0.016
Token princess
Token ID21752
Feature activation-4.74e+00

Pos logit contributions
 Joey+0.010
arp+0.010
 Mill+0.010
 sorts+0.010
 extingu+0.009
Neg logit contributions
 aids-0.010
 jokes-0.008
ggie-0.008
 poems-0.008
 wig-0.008
Token named
Token ID3706
Feature activation-1.35e+00

Pos logit contributions
 aids+0.386
 jokes+0.330
 cheeks+0.323
 Dancing+0.317
 wig+0.314
Neg logit contributions
arp-0.272
 sorts-0.270
 Mill-0.257
 Joey-0.253
aved-0.251
Token Jo
Token ID5302
Feature activation+1.77e+00

Pos logit contributions
 aids+0.092
 song+0.078
 jokes+0.077
ggie+0.076
 wig+0.076
Neg logit contributions
 Joey-0.093
 Mill-0.093
arp-0.091
 sorts-0.091
 unst-0.091
Tokenanna
Token ID7697
Feature activation-1.06e+01

Pos logit contributions
arp+0.138
 Mill+0.138
 Joey+0.138
 sorts+0.136
aved+0.133
Neg logit contributions
 aids-0.105
 jokes-0.089
 poems-0.085
 song-0.084
 wig-0.084
Token.
Token ID13
Feature activation-2.07e-01

Pos logit contributions
 aids+0.740
 jokes+0.631
 song+0.629
 wig+0.615
 hair+0.614
Neg logit contributions
arp-0.710
 unst-0.696
 Joey-0.694
 sorts-0.691
aved-0.682
Token She
Token ID1375
Feature activation+6.70e-01

Pos logit contributions
 aids+0.012
 Dancing+0.010
 song+0.010
 hair+0.010
 jokes+0.010
Neg logit contributions
 unst-0.016
arp-0.016
 Joey-0.015
aved-0.015
 extingu-0.015
Token lived
Token ID5615
Feature activation+1.72e+00

Pos logit contributions
 sorts+0.035
aved+0.034
arp+0.034
 Joey+0.033
 Mill+0.033
Neg logit contributions
 aids-0.057
 jokes-0.049
 song-0.048
 cheeks-0.048
 wig-0.047
Token in
Token ID287
Feature activation-1.70e+00

Pos logit contributions
arp+0.112
 unst+0.110
 Joey+0.109
 sorts+0.109
aved+0.107
Neg logit contributions
 aids-0.124
 song-0.107
 jokes-0.106
 hair-0.105
ggie-0.104
Token a
Token ID257
Feature activation+1.97e-01

Pos logit contributions
 aids+0.126
 jokes+0.109
 song+0.108
 wig+0.106
ggie+0.106
Neg logit contributions
arp-0.105
 sorts-0.104
 Joey-0.104
 unst-0.104
 Mill-0.101
Token really
Token ID1107
Feature activation-2.71e-02

Pos logit contributions
 aids+0.123
 song+0.108
 jokes+0.108
 hair+0.104
ggie+0.103
Neg logit contributions
arp-0.135
 unst-0.129
 sorts-0.128
aved-0.128
 Joey-0.127
Token special
Token ID2041
Feature activation+4.59e-01

Pos logit contributions
 aids+0.002
 song+0.002
 jokes+0.002
 hair+0.002
ggie+0.002
Neg logit contributions
arp-0.002
 unst-0.002
 Joey-0.002
 sorts-0.002
aved-0.002
Token inside
Token ID2641
Feature activation+4.60e+00

Pos logit contributions
arp+0.028
 unst+0.028
 Joey+0.027
aved+0.027
 sorts+0.026
Neg logit contributions
 aids-0.035
 song-0.031
 jokes-0.031
 hair-0.030
 poems-0.030
Token."
Token ID526
Feature activation+1.01e+00

Pos logit contributions
aved+0.320
arp+0.318
 unst+0.316
 extingu+0.310
erek+0.307
Neg logit contributions
 aids-0.308
 hair-0.267
 song-0.266
 jokes-0.266
 poems-0.261
Token Jo
Token ID5302
Feature activation+1.90e+00

Pos logit contributions
arp+0.066
 unst+0.065
 sorts+0.064
 Joey+0.064
aved+0.064
Neg logit contributions
 aids-0.072
 song-0.061
 jokes-0.061
 hair-0.060
 wig-0.060
Tokenanna
Token ID7697
Feature activation-1.06e+01

Pos logit contributions
 Joey+0.121
 Mill+0.118
 sorts+0.116
arp+0.110
 Bobby+0.110
Neg logit contributions
 aids-0.142
 poems-0.125
 wig-0.124
 jokes-0.123
 Dancing-0.121
Token was
Token ID373
Feature activation+5.48e-01

Pos logit contributions
 aids+0.672
 hair+0.598
 jokes+0.586
 cheeks+0.582
 song+0.582
Neg logit contributions
arp-0.763
 unst-0.730
 sorts-0.715
 hed-0.708
aved-0.700
Token very
Token ID845
Feature activation-5.99e-01

Pos logit contributions
 unst+0.034
 Joey+0.034
 sorts+0.034
 Mill+0.033
aved+0.032
Neg logit contributions
 aids-0.041
 song-0.035
 wig-0.035
 jokes-0.035
 poems-0.035
Token curious
Token ID11040
Feature activation-1.85e-03

Pos logit contributions
 aids+0.032
 jokes+0.027
 song+0.027
 hair+0.027
ggie+0.026
Neg logit contributions
arp-0.051
 unst-0.048
aved-0.048
 sorts-0.047
 Joey-0.047
Token and
Token ID290
Feature activation+4.25e-01

Pos logit contributions
 aids+0.000
 wig+0.000
ggie+0.000
 Dancing+0.000
uren+0.000
Neg logit contributions
 Joey-0.000
 sorts-0.000
 Mill-0.000
 unst-0.000
arp-0.000
Token couldn
Token ID3521
Feature activation+2.75e+00

Pos logit contributions
 Joey+0.026
 sorts+0.026
 unst+0.026
 Mill+0.026
arp+0.025
Neg logit contributions
 aids-0.032
 wig-0.028
ggie-0.027
 jokes-0.027
 song-0.027
Token's
Token ID338
Feature activation-3.06e+00

Pos logit contributions
 unst+0.020
arp+0.020
 Joey+0.020
aved+0.020
 scaven+0.020
Neg logit contributions
 aids-0.026
 Dancing-0.022
 song-0.022
 wig-0.022
 jokes-0.022
Token mom
Token ID1995
Feature activation-1.73e+00

Pos logit contributions
 aids+0.207
uren+0.171
ggie+0.165
 poems+0.163
 Dancing+0.162
Neg logit contributions
arp-0.205
 unst-0.205
 scaven-0.198
 shed-0.197
 Joey-0.193
Tokenmy
Token ID1820
Feature activation+8.87e-01

Pos logit contributions
 aids+0.129
 song+0.111
 jokes+0.111
ggie+0.109
 hair+0.109
Neg logit contributions
arp-0.108
 unst-0.107
 Joey-0.106
 sorts-0.105
aved-0.103
Token asked
Token ID1965
Feature activation-1.17e+00

Pos logit contributions
arp+0.065
 sorts+0.063
 unst+0.063
 Joey+0.063
aved+0.062
Neg logit contributions
 aids-0.056
 jokes-0.048
 song-0.047
 hair-0.047
 wig-0.047
Token her
Token ID607
Feature activation-7.34e-01

Pos logit contributions
 aids+0.076
 jokes+0.064
 song+0.064
 hair+0.063
 poems+0.062
Neg logit contributions
arp-0.086
 unst-0.084
 sorts-0.084
 Joey-0.084
aved-0.083
Token if
Token ID611
Feature activation+7.86e+00

Pos logit contributions
 aids+0.058
 song+0.050
 jokes+0.050
 wig+0.049
ggie+0.049
Neg logit contributions
arp-0.043
 unst-0.042
 Joey-0.042
 sorts-0.042
 Mill-0.041
Token she
Token ID673
Feature activation-8.63e-01

Pos logit contributions
 Joey+0.547
arp+0.547
 unst+0.545
 sorts+0.535
 Mill+0.534
Neg logit contributions
 aids-0.524
 song-0.442
 jokes-0.437
 wig-0.430
ggie-0.429
Token wanted
Token ID2227
Feature activation-8.32e-02

Pos logit contributions
 aids+0.065
 song+0.056
 jokes+0.055
 wig+0.055
 hair+0.054
Neg logit contributions
arp-0.053
 unst-0.053
 Joey-0.053
 sorts-0.052
aved-0.052
Token to
Token ID284
Feature activation-1.11e+00

Pos logit contributions
 aids+0.006
 song+0.005
 jokes+0.005
 hair+0.005
ggie+0.005
Neg logit contributions
arp-0.006
 unst-0.006
 Joey-0.006
 sorts-0.006
aved-0.006
Token help
Token ID1037
Feature activation+3.36e+00

Pos logit contributions
 aids+0.079
 hair+0.070
 song+0.070
 jokes+0.070
ggie+0.068
Neg logit contributions
arp-0.072
 sorts-0.069
 Joey-0.069
 unst-0.068
aved-0.068
Token clean
Token ID3424
Feature activation+4.24e+00

Pos logit contributions
arp+0.226
 unst+0.224
 Joey+0.223
 sorts+0.220
 Mill+0.217
Neg logit contributions
 aids-0.234
 song-0.199
 jokes-0.198
 wig-0.195
ggie-0.194
Token scream
Token ID8196
Feature activation+7.76e-02

Pos logit contributions
arp+0.016
 unst+0.015
 Joey+0.015
 sorts+0.015
aved+0.015
Neg logit contributions
 aids-0.011
 song-0.009
 jokes-0.009
 hair-0.009
 wig-0.009
Token.
Token ID13
Feature activation-2.84e-01

Pos logit contributions
arp+0.005
 unst+0.005
 Joey+0.005
 sorts+0.005
aved+0.005
Neg logit contributions
 aids-0.006
 wig-0.005
ggie-0.005
 jokes-0.005
 song-0.005
Token
Token ID198
Feature activation+1.18e-01

Pos logit contributions
 aids+0.024
 song+0.021
 wig+0.021
 jokes+0.021
 poems+0.021
Neg logit contributions
 Joey-0.015
arp-0.015
 unst-0.015
 Mill-0.015
 sorts-0.014
Token
Token ID198
Feature activation+1.40e-01

Pos logit contributions
arp+0.010
 unst+0.010
 sorts+0.009
aved+0.009
wood+0.009
Neg logit contributions
 aids-0.006
 Dancing-0.005
ggie-0.005
 song-0.005
 jokes-0.005
TokenThe
Token ID464
Feature activation-9.21e-01

Pos logit contributions
arp+0.011
 Joey+0.011
 sorts+0.011
 unst+0.011
 Mill+0.011
Neg logit contributions
 aids-0.008
 song-0.007
ggie-0.007
 jokes-0.007
 hair-0.007
Token box
Token ID3091
Feature activation+7.83e+00

Pos logit contributions
 aids+0.062
 song+0.057
 jokes+0.056
 hair+0.054
 wig+0.053
Neg logit contributions
 sorts-0.063
 Joey-0.063
 unst-0.063
arp-0.062
 Mill-0.062
Token reaches
Token ID12229
Feature activation-3.50e+00

Pos logit contributions
 sorts+0.452
 unst+0.449
aved+0.438
arp+0.438
 deeper+0.434
Neg logit contributions
 aids-0.576
uren-0.512
ggie-0.511
 wig-0.510
 blond-0.500
Token the
Token ID262
Feature activation+4.76e-01

Pos logit contributions
 hair+0.155
 aids+0.143
 song+0.131
 jokes+0.129
 eyes+0.124
Neg logit contributions
arp-0.323
rolley-0.316
pling-0.315
aved-0.314
ucer-0.304
Token end
Token ID886
Feature activation-6.16e-02

Pos logit contributions
 sorts+0.037
 Mill+0.037
 Joey+0.037
aved+0.036
irs+0.035
Neg logit contributions
 song-0.028
 hair-0.027
 wig-0.025
 clown-0.025
 aids-0.025
Token of
Token ID286
Feature activation+8.82e-02

Pos logit contributions
 aids+0.004
 song+0.003
 hair+0.003
ggie+0.003
 Dancing+0.003
Neg logit contributions
 unst-0.004
 Joey-0.004
aved-0.004
 sorts-0.004
arp-0.004
Token the
Token ID262
Feature activation+4.96e-01

Pos logit contributions
aved+0.007
arp+0.007
 unst+0.007
'll+0.007
vell+0.007
Neg logit contributions
 aids-0.005
 hair-0.004
 song-0.004
 jokes-0.004
 poems-0.004
Token.
Token ID13
Feature activation-6.82e-01

Pos logit contributions
arp+0.079
 unst+0.076
 sorts+0.076
 Joey+0.075
 Mill+0.074
Neg logit contributions
 aids-0.062
 jokes-0.053
 hair-0.053
 song-0.052
ggie-0.051
Token They
Token ID1119
Feature activation+1.34e-01

Pos logit contributions
 aids+0.048
 song+0.041
 jokes+0.041
 hair+0.040
 wig+0.040
Neg logit contributions
arp-0.046
 Joey-0.045
 unst-0.045
 sorts-0.045
aved-0.044
Token also
Token ID635
Feature activation-2.03e-01

Pos logit contributions
arp+0.010
rolley+0.009
ucer+0.009
 unst+0.009
 sorts+0.009
Neg logit contributions
 aids-0.009
 jokes-0.008
 hair-0.008
 cheeks-0.008
 wig-0.007
Token want
Token ID765
Feature activation+9.89e-01

Pos logit contributions
 aids+0.014
 hair+0.012
 jokes+0.012
 wig+0.012
 song+0.012
Neg logit contributions
arp-0.015
 Mill-0.013
ucer-0.013
 Joey-0.013
rolley-0.013
Token the
Token ID262
Feature activation+2.16e-01

Pos logit contributions
arp+0.082
aved+0.080
 unst+0.079
 sorts+0.078
ucer+0.078
Neg logit contributions
 aids-0.054
 jokes-0.048
 hair-0.046
 song-0.045
 poems-0.044
Token box
Token ID3091
Feature activation+7.45e+00

Pos logit contributions
irs+0.012
 Mill+0.012
ucer+0.012
aved+0.012
 sorts+0.012
Neg logit contributions
 song-0.015
 jokes-0.015
 hair-0.015
 aids-0.014
 wig-0.014
Token.
Token ID13
Feature activation-6.87e-01

Pos logit contributions
arp+0.576
neath+0.545
 sorts+0.544
 Joey+0.544
aved+0.540
Neg logit contributions
 aids-0.434
 song-0.388
 hair-0.383
 jokes-0.372
ggie-0.359
Token
Token ID198
Feature activation-1.94e-01

Pos logit contributions
 aids+0.050
 song+0.043
 jokes+0.043
 hair+0.042
ggie+0.042
Neg logit contributions
arp-0.045
 unst-0.044
 Joey-0.044
 sorts-0.043
aved-0.043
Token
Token ID198
Feature activation-1.89e-01

Pos logit contributions
 aids+0.010
ggie+0.009
 Dancing+0.008
ggy+0.008
 jokes+0.008
Neg logit contributions
 unst-0.016
arp-0.016
aved-0.016
 extingu-0.015
wood-0.015
Token"
Token ID1
Feature activation-8.21e-03

Pos logit contributions
 aids+0.012
ggie+0.010
 song+0.010
 jokes+0.010
 wig+0.010
Neg logit contributions
 unst-0.014
arp-0.013
 Joey-0.013
 sorts-0.013
 Mill-0.013
TokenLet
Token ID5756
Feature activation+2.56e+00

Pos logit contributions
 aids+0.001
 jokes+0.001
 song+0.001
 hair+0.001
 poems+0.001
Neg logit contributions
arp-0.001
 unst-0.001
 Joey-0.001
 sorts-0.000
aved-0.000
Token bunny
Token ID44915
Feature activation-2.11e-01

Pos logit contributions
 aids+0.136
 jokes+0.115
ggie+0.114
 wig+0.113
 Dancing+0.112
Neg logit contributions
arp-0.095
 Joey-0.094
 unst-0.093
 sorts-0.090
 Mill-0.090
Token said
Token ID531
Feature activation+8.71e-02

Pos logit contributions
 aids+0.018
 Dancing+0.015
 wig+0.015
 poems+0.015
 jokes+0.015
Neg logit contributions
 Joey-0.011
 Mill-0.011
 sorts-0.011
 scaven-0.010
'll-0.010
Token hello
Token ID23748
Feature activation-4.47e+00

Pos logit contributions
 Joey+0.005
 Mill+0.005
 unst+0.004
 Bobby+0.004
 deeper+0.004
Neg logit contributions
 aids-0.007
 wig-0.007
 poems-0.006
uren-0.006
 song-0.006
Token and
Token ID290
Feature activation+2.99e-02

Pos logit contributions
 aids+0.356
 poems+0.297
 jokes+0.297
ggie+0.295
 wig+0.291
Neg logit contributions
 Joey-0.268
 unst-0.265
arp-0.262
 Mill-0.259
wood-0.249
Token asked
Token ID1965
Feature activation-1.32e+00

Pos logit contributions
arp+0.002
aved+0.002
 unst+0.002
 sorts+0.002
rolley+0.002
Neg logit contributions
 aids-0.002
 song-0.002
 jokes-0.002
 hair-0.002
 wig-0.002
Token if
Token ID611
Feature activation+7.76e+00

Pos logit contributions
 aids+0.091
 jokes+0.083
 song+0.080
 poems+0.079
 hair+0.079
Neg logit contributions
arp-0.096
aved-0.091
rolley-0.088
 sorts-0.087
 unst-0.087
Token the
Token ID262
Feature activation+4.93e-01

Pos logit contributions
arp+0.488
 unst+0.476
 sorts+0.473
 Joey+0.471
aved+0.465
Neg logit contributions
 aids-0.575
 song-0.497
 jokes-0.497
 hair-0.488
ggie-0.486
Token bird
Token ID6512
Feature activation-1.73e+00

Pos logit contributions
arp+0.030
 Joey+0.029
 unst+0.029
 Mill+0.028
 sorts+0.028
Neg logit contributions
 aids-0.038
 jokes-0.032
ggie-0.032
 wig-0.032
 poems-0.031
Token wanted
Token ID2227
Feature activation-1.69e-01

Pos logit contributions
 aids+0.139
 wig+0.119
 song+0.119
 hair+0.118
 poems+0.117
Neg logit contributions
 Joey-0.101
 Mill-0.097
 sorts-0.097
 unst-0.095
arp-0.093
Token to
Token ID284
Feature activation-1.22e+00

Pos logit contributions
 aids+0.013
 wig+0.011
 song+0.011
uren+0.011
ggie+0.011
Neg logit contributions
 Joey-0.011
 unst-0.010
 Mill-0.010
 sorts-0.010
arp-0.010
Token be
Token ID307
Feature activation-4.19e+00

Pos logit contributions
 aids+0.093
 jokes+0.079
 song+0.079
 poems+0.079
 wig+0.078
Neg logit contributions
arp-0.074
 unst-0.073
 Joey-0.073
 sorts-0.072
 Mill-0.071
Token grass
Token ID8701
Feature activation+1.28e+00

Pos logit contributions
 sorts+0.031
 Joey+0.031
aved+0.029
 Suz+0.029
 aback+0.029
Neg logit contributions
 song-0.029
 hair-0.029
 aids-0.028
 wig-0.027
 songs-0.026
Token.
Token ID13
Feature activation-2.31e-01

Pos logit contributions
 unst+0.104
 Joey+0.103
 sorts+0.103
arp+0.103
 Mill+0.102
Neg logit contributions
 aids-0.064
 song-0.056
 hair-0.056
 wig-0.053
ggie-0.052
Token She
Token ID1375
Feature activation+7.50e-01

Pos logit contributions
 aids+0.013
 hair+0.011
 Dancing+0.011
 jokes+0.010
 wig+0.010
Neg logit contributions
arp-0.019
 sorts-0.018
 unst-0.018
aved-0.018
 Joey-0.018
Token turned
Token ID2900
Feature activation-7.13e-01

Pos logit contributions
arp+0.059
 Joey+0.058
 Mill+0.055
 sorts+0.055
wood+0.054
Neg logit contributions
 aids-0.042
 hair-0.040
 wig-0.039
 song-0.037
ggie-0.037
Token the
Token ID262
Feature activation+4.64e-01

Pos logit contributions
 aids+0.043
 hair+0.041
 poems+0.036
 song+0.036
 jokes+0.035
Neg logit contributions
arp-0.053
 sorts-0.051
rolley-0.051
wood-0.049
erek-0.048
Token box
Token ID3091
Feature activation+7.87e+00

Pos logit contributions
 Joey+0.030
 sorts+0.030
 Suz+0.028
 Mill+0.027
 Bobby+0.026
Neg logit contributions
 song-0.035
 hair-0.033
 aids-0.033
 poems-0.032
 songs-0.032
Token upside
Token ID17196
Feature activation+1.09e+00

Pos logit contributions
arp+0.556
 Joey+0.541
 sorts+0.530
 unst+0.528
aved+0.522
Neg logit contributions
 aids-0.522
 song-0.456
 hair-0.451
 jokes-0.441
 poems-0.433
Token down
Token ID866
Feature activation+2.78e-01

Pos logit contributions
 sorts+0.060
 Joey+0.054
 hed+0.054
arp+0.054
 Mill+0.053
Neg logit contributions
 aids-0.084
 hair-0.083
 wig-0.079
 song-0.078
 cheeks-0.078
Token and
Token ID290
Feature activation+3.25e-01

Pos logit contributions
arp+0.025
aved+0.024
 Joey+0.024
 sorts+0.024
ylan+0.024
Neg logit contributions
 aids-0.011
 hair-0.010
 song-0.010
 poems-0.009
 curly-0.009
Token cut
Token ID2005
Feature activation+1.44e+00

Pos logit contributions
arp+0.025
 sorts+0.023
 Joey+0.023
rolley+0.023
aved+0.022
Neg logit contributions
 aids-0.020
 hair-0.019
 wig-0.018
 jokes-0.017
 song-0.017
Token a
Token ID257
Feature activation+5.33e-01

Pos logit contributions
 sorts+0.101
arp+0.098
 Joey+0.096
 scaven+0.094
rolley+0.094
Neg logit contributions
 aids-0.095
 hair-0.095
 poems-0.081
ggie-0.080
 song-0.080
Token should
Token ID815
Feature activation+3.59e+00

Pos logit contributions
arp+0.053
rolley+0.052
 hed+0.051
 unst+0.050
ylan+0.050
Neg logit contributions
 aids-0.044
 jokes-0.040
ggie-0.039
 hair-0.038
 song-0.037
Token not
Token ID407
Feature activation-2.53e+00

Pos logit contributions
arp+0.315
 unst+0.311
 sorts+0.311
aved+0.306
 Joey+0.306
Neg logit contributions
 aids-0.176
 jokes-0.144
 song-0.144
 hair-0.141
ggie-0.140
Token climb
Token ID12080
Feature activation+6.35e-01

Pos logit contributions
 aids+0.182
 jokes+0.155
 song+0.154
 poems+0.154
 wig+0.152
Neg logit contributions
arp-0.165
 unst-0.163
 Joey-0.162
 sorts-0.160
aved-0.159
Token the
Token ID262
Feature activation+6.07e-01

Pos logit contributions
arp+0.046
 sorts+0.046
rolley+0.043
aved+0.043
ucer+0.043
Neg logit contributions
 aids-0.040
 hair-0.037
 jokes-0.035
 poems-0.035
 song-0.034
Token ladder
Token ID18002
Feature activation+3.32e+00

Pos logit contributions
 Joey+0.042
 sorts+0.040
aved+0.039
arp+0.039
 Mill+0.039
Neg logit contributions
 aids-0.040
 hair-0.039
 song-0.039
 yoga-0.035
 jokes-0.035
Token without
Token ID1231
Feature activation+4.44e+00

Pos logit contributions
arp+0.258
 Joey+0.257
 Mill+0.253
 sorts+0.251
aved+0.249
Neg logit contributions
 aids-0.189
 song-0.163
 hair-0.162
 jokes-0.157
ggie-0.154
Token me
Token ID502
Feature activation-1.75e+00

Pos logit contributions
arp+0.312
 unst+0.309
 Joey+0.308
 sorts+0.304
aved+0.299
Neg logit contributions
 aids-0.295
 song-0.250
 jokes-0.248
 hair-0.244
ggie-0.243
Token.
Token ID13
Feature activation-3.32e-01

Pos logit contributions
 aids+0.117
 song+0.100
 hair+0.099
 jokes+0.099
ggie+0.098
Neg logit contributions
arp-0.122
 sorts-0.119
 Joey-0.119
 unst-0.118
aved-0.117
Token It
Token ID632
Feature activation-1.91e+00

Pos logit contributions
 aids+0.022
 song+0.019
 jokes+0.019
ggie+0.019
 hair+0.019
Neg logit contributions
arp-0.023
 unst-0.023
 Joey-0.023
 sorts-0.022
aved-0.022
Token is
Token ID318
Feature activation+5.63e-01

Pos logit contributions
 aids+0.127
 song+0.108
 jokes+0.108
ggie+0.106
 hair+0.106
Neg logit contributions
arp-0.134
 Joey-0.132
 sorts-0.130
 unst-0.130
 Mill-0.128
Token dangerous
Token ID4923
Feature activation+4.02e+00

Pos logit contributions
arp+0.045
 Joey+0.044
 sorts+0.044
aved+0.044
 unst+0.044
Neg logit contributions
 aids-0.032
 song-0.027
 jokes-0.026
 hair-0.026
ggie-0.026
Token find
Token ID1064
Feature activation+4.00e+00

Pos logit contributions
 aids+0.076
ggie+0.067
 cheeks+0.067
agged+0.063
ggy+0.063
Neg logit contributions
 sorts-0.062
 Joey-0.057
 unst-0.055
 hed-0.054
neath-0.053
Token some
Token ID617
Feature activation-1.26e+00

Pos logit contributions
arp+0.279
 unst+0.276
aved+0.270
 Joey+0.269
 Mill+0.263
Neg logit contributions
 aids-0.270
 jokes-0.240
 song-0.235
 hair-0.235
 poems-0.233
Token.
Token ID13
Feature activation-1.82e-01

Pos logit contributions
 aids+0.083
ggie+0.068
uren+0.067
 wig+0.067
 cheeks+0.066
Neg logit contributions
 sorts-0.092
arp-0.088
 hed-0.086
 unst-0.085
 Joey-0.085
Token He
Token ID679
Feature activation+9.76e-02

Pos logit contributions
 aids+0.012
 song+0.010
 wig+0.010
 jokes+0.010
 poems+0.010
Neg logit contributions
 Joey-0.013
 sorts-0.013
arp-0.013
 unst-0.012
 Mill-0.012
Token wandered
Token ID36036
Feature activation-6.64e-01

Pos logit contributions
arp+0.006
 unst+0.006
 Joey+0.006
 sorts+0.006
aved+0.006
Neg logit contributions
 aids-0.007
 song-0.006
 jokes-0.006
 hair-0.006
 wig-0.006
Token through
Token ID832
Feature activation+3.09e+00

Pos logit contributions
 hair+0.033
 aids+0.033
 song+0.032
 songs+0.032
 jokes+0.031
Neg logit contributions
 extingu-0.052
arp-0.051
 unst-0.049
pling-0.049
rolley-0.048
Token the
Token ID262
Feature activation+6.40e-01

Pos logit contributions
arp+0.241
 unst+0.237
ucer+0.229
aved+0.228
ylan+0.226
Neg logit contributions
 aids-0.180
 hair-0.171
 jokes-0.166
 song-0.163
 poems-0.163
Token forest
Token ID8222
Feature activation+2.37e+00

Pos logit contributions
 Joey+0.038
 unst+0.038
arp+0.036
aved+0.036
 Mill+0.036
Neg logit contributions
 aids-0.049
 hair-0.045
 song-0.045
 jokes-0.044
 poems-0.043
Token until
Token ID1566
Feature activation+2.47e+00

Pos logit contributions
arp+0.200
 unst+0.191
 Joey+0.188
neath+0.188
aved+0.185
Neg logit contributions
 aids-0.119
 song-0.111
 hair-0.109
 jokes-0.106
 songs-0.101
Token he
Token ID339
Feature activation-4.39e-01

Pos logit contributions
arp+0.184
 sorts+0.179
 unst+0.178
 Joey+0.174
aved+0.173
Neg logit contributions
 aids-0.155
 song-0.130
 jokes-0.130
 hair-0.129
ggie-0.127
Token found
Token ID1043
Feature activation+4.36e+00

Pos logit contributions
 aids+0.035
 song+0.030
 jokes+0.030
 hair+0.030
 wig+0.030
Neg logit contributions
arp-0.025
 unst-0.025
 Joey-0.025
 sorts-0.025
aved-0.024
Token a
Token ID257
Feature activation+3.35e-01

Pos logit contributions
arp+0.026
 sorts+0.025
 unst+0.025
aved+0.025
rolley+0.024
Neg logit contributions
 aids-0.025
 jokes-0.022
 hair-0.022
 song-0.022
ggie-0.022
Token wise
Token ID10787
Feature activation+9.94e-01

Pos logit contributions
 Joey+0.023
arp+0.023
 unst+0.023
 sorts+0.023
 Mill+0.022
Neg logit contributions
 aids-0.022
 jokes-0.019
 hair-0.018
 poems-0.018
 Dancing-0.018
Token old
Token ID1468
Feature activation+1.84e+00

Pos logit contributions
arp+0.071
 Joey+0.071
 sorts+0.070
 unst+0.070
 Mill+0.069
Neg logit contributions
 aids-0.064
 jokes-0.054
 song-0.053
ggie-0.053
 hair-0.053
Token crab
Token ID32202
Feature activation-1.72e+00

Pos logit contributions
 Joey+0.133
arp+0.133
 sorts+0.131
 unst+0.130
 Mill+0.129
Neg logit contributions
 aids-0.118
 jokes-0.098
 song-0.096
ggie-0.096
 hair-0.096
Token crawled
Token ID45668
Feature activation+4.52e-01

Pos logit contributions
 aids+0.137
 jokes+0.119
 song+0.119
 hair+0.118
 poems+0.118
Neg logit contributions
arp-0.098
 Joey-0.096
 unst-0.096
aved-0.095
 sorts-0.094
Token up
Token ID510
Feature activation+1.91e+00

Pos logit contributions
 sorts+0.030
arp+0.029
rolley+0.028
pling+0.027
ucer+0.027
Neg logit contributions
 aids-0.029
 hair-0.027
 song-0.026
 jokes-0.025
 poems-0.025
Token to
Token ID284
Feature activation-1.17e+00

Pos logit contributions
arp+0.151
aved+0.141
ucer+0.140
rolley+0.139
 sorts+0.139
Neg logit contributions
 aids-0.114
 song-0.096
 hair-0.096
 jokes-0.095
ggie-0.090
Token them
Token ID606
Feature activation-1.61e+00

Pos logit contributions
 aids+0.071
 jokes+0.065
 song+0.063
 wig+0.060
 hair+0.059
Neg logit contributions
arp-0.092
aved-0.088
rolley-0.087
ucer-0.084
pling-0.084
Token and
Token ID290
Feature activation+1.54e-01

Pos logit contributions
 aids+0.100
 song+0.086
 jokes+0.085
 hair+0.084
ggie+0.082
Neg logit contributions
arp-0.120
 unst-0.116
 sorts-0.116
aved-0.115
 Joey-0.114
Token said
Token ID531
Feature activation+7.59e-02

Pos logit contributions
arp+0.012
 sorts+0.011
aved+0.011
 unst+0.011
 Joey+0.011
Neg logit contributions
 aids-0.010
 jokes-0.008
 song-0.008
 wig-0.008
 hair-0.008
Token,
Token ID11
Feature activation+2.97e-01

Pos logit contributions
 Joey+0.005
 Mill+0.004
 unst+0.004
 Suz+0.004
 Bobby+0.004
Neg logit contributions
 aids-0.006
 song-0.005
 wig-0.005
 poems-0.005
 Dancing-0.005
Token'm
Token ID1101
Feature activation+1.36e+00

Pos logit contributions
 aids+0.041
 jokes+0.037
 song+0.037
ggie+0.036
 hair+0.036
Neg logit contributions
arp-0.026
 Joey-0.024
 Mill-0.024
 unst-0.024
 hed-0.024
Token glad
Token ID9675
Feature activation+1.51e+00

Pos logit contributions
 Joey+0.087
 unst+0.086
 Mill+0.084
 sorts+0.084
arp+0.081
Neg logit contributions
 aids-0.099
 song-0.086
 jokes-0.085
 cheeks-0.085
 wig-0.084
Token we
Token ID356
Feature activation+9.86e-01

Pos logit contributions
 Joey+0.072
 Mill+0.068
 Bobby+0.063
 Suz+0.061
 sorts+0.059
Neg logit contributions
 aids-0.141
 wig-0.124
ggie-0.121
 hair-0.120
 blond-0.119
Token grew
Token ID6348
Feature activation-1.33e+00

Pos logit contributions
arp+0.071
 extingu+0.067
 hed+0.065
rolley+0.064
 Mill+0.064
Neg logit contributions
 aids-0.063
 jokes-0.059
 hair-0.057
 song-0.057
 Dancing-0.054
Token them
Token ID606
Feature activation-1.46e+00

Pos logit contributions
 hair+0.075
 jokes+0.074
 aids+0.073
 poems+0.070
 song+0.070
Neg logit contributions
erek-0.101
aved-0.099
arp-0.099
ylan-0.099
rolley-0.098
Token together
Token ID1978
Feature activation+3.20e+00

Pos logit contributions
 song+0.099
 aids+0.097
 jokes+0.096
 hair+0.093
 poems+0.093
Neg logit contributions
arp-0.098
aved-0.097
erek-0.093
neath-0.092
 sorts-0.092
Token.
Token ID13
Feature activation-2.68e-01

Pos logit contributions
arp+0.220
 unst+0.212
aved+0.212
 Joey+0.209
 sorts+0.206
Neg logit contributions
 aids-0.218
 song-0.199
 jokes-0.194
 hair-0.190
 poems-0.188
Token Can
Token ID1680
Feature activation-2.26e+00

Pos logit contributions
 aids+0.019
 song+0.016
 jokes+0.016
 hair+0.016
ggie+0.016
Neg logit contributions
arp-0.018
 unst-0.018
 Joey-0.017
 sorts-0.017
aved-0.017
Token we
Token ID356
Feature activation+7.06e-01

Pos logit contributions
 aids+0.241
 poems+0.210
ggie+0.209
 wig+0.209
 jokes+0.208
Neg logit contributions
 Joey-0.078
 Mill-0.074
 Bobby-0.070
arp-0.063
'll-0.061
Token still
Token ID991
Feature activation+3.45e-01

Pos logit contributions
arp+0.052
 unst+0.051
 sorts+0.051
 Joey+0.051
aved+0.050
Neg logit contributions
 aids-0.043
 song-0.038
 jokes-0.038
 hair-0.037
 wig-0.036
Token be
Token ID307
Feature activation-4.07e+00

Pos logit contributions
arp+0.026
 unst+0.026
 Joey+0.026
 sorts+0.026
aved+0.025
Neg logit contributions
 aids-0.021
 song-0.017
 jokes-0.017
 hair-0.017
ggie-0.017
Token smiled
Token ID13541
Feature activation-1.94e+00

Pos logit contributions
 Joey+0.079
 Mill+0.077
 Suz+0.076
 unst+0.076
 extingu+0.075
Neg logit contributions
 aids-0.093
 poems-0.081
 Dancing-0.080
 song-0.078
 hair-0.076
Token and
Token ID290
Feature activation-1.19e-01

Pos logit contributions
 aids+0.174
ggie+0.157
 wig+0.153
uren+0.151
 jokes+0.146
Neg logit contributions
 unst-0.094
arp-0.092
 Joey-0.090
 sorts-0.088
 deeper-0.087
Token said
Token ID531
Feature activation-8.04e-02

Pos logit contributions
 aids+0.009
ggie+0.007
 song+0.007
 poems+0.007
 jokes+0.007
Neg logit contributions
 unst-0.008
 Joey-0.008
 sorts-0.008
 Mill-0.008
arp-0.008
Token,
Token ID11
Feature activation-1.73e-02

Pos logit contributions
 aids+0.007
 song+0.006
 wig+0.006
 jokes+0.006
 poems+0.006
Neg logit contributions
 unst-0.004
 Joey-0.004
 Mill-0.004
arp-0.004
aved-0.004
Token "
Token ID366
Feature activation-7.43e-01

Pos logit contributions
 aids+0.001
 poems+0.001
ggie+0.001
 jokes+0.001
 wig+0.001
Neg logit contributions
 Mill-0.001
 Joey-0.001
 unst-0.001
 Bobby-0.001
 extingu-0.001
TokenDon
Token ID3987
Feature activation+4.58e+00

Pos logit contributions
 aids+0.067
 jokes+0.059
 hair+0.059
ggie+0.058
 cheeks+0.058
Neg logit contributions
arp-0.038
 sorts-0.036
 unst-0.035
 Joey-0.034
 Mill-0.034
Token't
Token ID470
Feature activation-1.91e+00

Pos logit contributions
arp+0.339
 unst+0.338
 Joey+0.331
 Mill+0.325
 sorts+0.325
Neg logit contributions
 aids-0.288
 jokes-0.244
 wig-0.240
 hair-0.240
 song-0.240
Token be
Token ID307
Feature activation-4.19e+00

Pos logit contributions
 aids+0.182
 poems+0.164
ggie+0.160
uren+0.157
 wig+0.157
Neg logit contributions
 Joey-0.093
 Mill-0.088
 unst-0.085
 Suz-0.082
arp-0.076
Token scared
Token ID12008
Feature activation+7.89e-01

Pos logit contributions
 aids+0.334
 song+0.293
 poems+0.292
 cheeks+0.291
 wig+0.289
Neg logit contributions
 unst-0.249
 Joey-0.239
 Mill-0.230
 sorts-0.229
 hed-0.227
Token,
Token ID11
Feature activation+1.84e-03

Pos logit contributions
arp+0.050
 unst+0.050
 Joey+0.049
 sorts+0.049
 Mill+0.048
Neg logit contributions
 aids-0.058
 song-0.050
 jokes-0.049
 wig-0.049
 hair-0.049
Token Anna
Token ID11735
Feature activation-4.88e+00

Pos logit contributions
 Joey+0.000
 Mill+0.000
 unst+0.000
arp+0.000
 sorts+0.000
Neg logit contributions
 aids-0.000
ggie-0.000
 wig-0.000
 Dancing-0.000
 hair-0.000
Token was
Token ID373
Feature activation+4.76e-01

Pos logit contributions
 Joey+0.102
 Mill+0.099
 unst+0.097
 sorts+0.096
 Suz+0.093
Neg logit contributions
 aids-0.137
 poems-0.119
 Dancing-0.116
 wig-0.116
 song-0.115
Token so
Token ID523
Feature activation-1.11e+00

Pos logit contributions
 unst+0.026
 Joey+0.025
 sorts+0.025
 Mill+0.024
 Suz+0.023
Neg logit contributions
 aids-0.039
 poems-0.036
 wig-0.035
 song-0.035
 jokes-0.035
Token happy
Token ID3772
Feature activation-1.05e+00

Pos logit contributions
 aids+0.065
 jokes+0.053
 song+0.053
 hair+0.053
ggie+0.052
Neg logit contributions
arp-0.091
 unst-0.086
 Joey-0.085
 sorts-0.085
aved-0.085
Token and
Token ID290
Feature activation+2.32e-01

Pos logit contributions
 aids+0.080
 song+0.067
 jokes+0.067
 wig+0.067
 hair+0.067
Neg logit contributions
 Joey-0.066
arp-0.064
 sorts-0.064
 unst-0.063
 Mill-0.063
Token he
Token ID339
Feature activation-5.67e-01

Pos logit contributions
 Joey+0.015
 unst+0.015
 sorts+0.015
 Mill+0.014
arp+0.014
Neg logit contributions
 aids-0.017
 wig-0.015
 jokes-0.014
 poems-0.014
 song-0.014
Token bark
Token ID21405
Feature activation-3.83e+00

Pos logit contributions
 aids+0.042
 jokes+0.035
 song+0.035
 wig+0.034
 poems+0.034
Neg logit contributions
 unst-0.036
 Joey-0.036
 sorts-0.036
 Mill-0.035
arp-0.035
Tokened
Token ID276
Feature activation+6.82e-01

Pos logit contributions
 aids+0.353
 wig+0.311
 jokes+0.310
 song+0.310
 poems+0.309
Neg logit contributions
 unst-0.173
arp-0.169
 Joey-0.168
aved-0.167
 sorts-0.167
Token with
Token ID351
Feature activation-7.15e-01

Pos logit contributions
 Joey+0.041
 unst+0.041
 sorts+0.040
arp+0.039
 Mill+0.039
Neg logit contributions
 aids-0.053
 wig-0.045
ggie-0.045
 song-0.045
 poems-0.045
Token joy
Token ID8716
Feature activation+1.83e+00

Pos logit contributions
 aids+0.057
 jokes+0.050
 song+0.050
 hair+0.049
 wig+0.048
Neg logit contributions
arp-0.043
 unst-0.041
 Joey-0.040
aved-0.040
 sorts-0.040
Token.
Token ID13
Feature activation-1.77e-01

Pos logit contributions
 Joey+0.108
 Mill+0.102
arp+0.102
 unst+0.100
 sorts+0.097
Neg logit contributions
 aids-0.150
 Dancing-0.126
 wig-0.126
ggie-0.125
 song-0.123
Token He
Token ID679
Feature activation+2.42e-02

Pos logit contributions
 aids+0.013
 song+0.012
 wig+0.012
ggie+0.012
 jokes+0.011
Neg logit contributions
 Joey-0.011
 Mill-0.010
 unst-0.010
 Bobby-0.010
 sorts-0.010
Token sheep
Token ID15900
Feature activation-1.82e+00

Pos logit contributions
arp+0.040
 unst+0.039
 Joey+0.039
 sorts+0.038
aved+0.038
Neg logit contributions
 aids-0.038
 jokes-0.031
 song-0.031
ggie-0.031
 wig-0.030
Token,
Token ID11
Feature activation+2.71e-01

Pos logit contributions
 aids+0.128
 song+0.110
 jokes+0.110
 hair+0.108
ggie+0.107
Neg logit contributions
arp-0.121
 unst-0.119
 Joey-0.118
 sorts-0.117
aved-0.115
Token and
Token ID290
Feature activation+2.24e-01

Pos logit contributions
arp+0.022
aved+0.020
 unst+0.020
 Joey+0.020
 sorts+0.020
Neg logit contributions
 aids-0.016
 hair-0.014
 song-0.014
 jokes-0.014
 poems-0.013
Token the
Token ID262
Feature activation+5.67e-01

Pos logit contributions
 Joey+0.013
arp+0.013
 unst+0.013
 sorts+0.013
 Mill+0.013
Neg logit contributions
 aids-0.017
 song-0.015
 jokes-0.015
ggie-0.015
 hair-0.015
Token dog
Token ID3290
Feature activation-8.92e-01

Pos logit contributions
arp+0.039
 unst+0.039
 Joey+0.038
 sorts+0.038
aved+0.037
Neg logit contributions
 aids-0.039
 jokes-0.032
ggie-0.032
 song-0.032
 Dancing-0.031
Token.
Token ID13
Feature activation-1.18e-01

Pos logit contributions
 aids+0.067
 song+0.057
 jokes+0.057
 wig+0.056
 poems+0.056
Neg logit contributions
 unst-0.055
arp-0.054
 sorts-0.054
 Joey-0.054
aved-0.053
Token
Token ID220
Feature activation-7.78e-01

Pos logit contributions
 aids+0.009
 song+0.008
 wig+0.008
ggie+0.008
 jokes+0.008
Neg logit contributions
 Joey-0.008
arp-0.007
 sorts-0.007
 unst-0.007
 Mill-0.007
Token
Token ID198
Feature activation+3.70e-01

Pos logit contributions
 aids+0.045
 Dancing+0.037
ggie+0.037
 jokes+0.036
 hair+0.036
Neg logit contributions
arp-0.061
 unst-0.060
aved-0.059
 sorts-0.059
 extingu-0.058
Token
Token ID198
Feature activation+3.67e-01

Pos logit contributions
 unst+0.026
arp+0.026
aved+0.025
 Joey+0.025
 sorts+0.025
Neg logit contributions
 aids-0.024
 song-0.021
ggie-0.020
 jokes-0.020
 Dancing-0.020
TokenAt
Token ID2953
Feature activation-4.47e-01

Pos logit contributions
arp+0.023
 sorts+0.023
 Joey+0.022
aved+0.022
neath+0.022
Neg logit contributions
 aids-0.027
 cheeks-0.024
 hair-0.024
 wig-0.023
 jokes-0.023
Token first
Token ID717
Feature activation-5.33e-01

Pos logit contributions
 aids+0.029
 song+0.027
 jokes+0.026
 hair+0.026
ggie+0.026
Neg logit contributions
arp-0.032
aved-0.029
 Joey-0.029
 unst-0.029
rolley-0.029
Token bug
Token ID5434
Feature activation-1.64e+00

Pos logit contributions
arp+0.038
 unst+0.037
aved+0.037
 sorts+0.037
 Joey+0.036
Neg logit contributions
 aids-0.040
 song-0.036
 jokes-0.035
 hair-0.035
 wig-0.034
Token!
Token ID0
Feature activation+4.01e+00

Pos logit contributions
 aids+0.117
 song+0.103
 jokes+0.101
 hair+0.101
ggie+0.100
Neg logit contributions
arp-0.107
 unst-0.105
 Joey-0.104
 sorts-0.103
aved-0.102
Token Sarah
Token ID10490
Feature activation+1.20e+00

Pos logit contributions
 Mill+0.218
 sorts+0.217
 unst+0.216
 Joey+0.210
arp+0.203
Neg logit contributions
 aids-0.324
 wig-0.301
ggie-0.299
 song-0.290
 jokes-0.290
Token was
Token ID373
Feature activation+3.42e-01

Pos logit contributions
arp+0.073
 Joey+0.072
 unst+0.072
 sorts+0.072
aved+0.071
Neg logit contributions
 aids-0.091
 song-0.078
 jokes-0.078
 wig-0.077
 poems-0.076
Token surprised
Token ID6655
Feature activation-2.50e-01

Pos logit contributions
 unst+0.021
 Joey+0.020
 Mill+0.020
 sorts+0.019
 deeper+0.019
Neg logit contributions
 aids-0.026
uren-0.023
 wig-0.023
 poems-0.023
 cheeks-0.022
Token to
Token ID284
Feature activation-1.15e+00

Pos logit contributions
 aids+0.019
 song+0.016
 wig+0.016
 jokes+0.016
ggie+0.016
Neg logit contributions
 Joey-0.016
arp-0.016
 sorts-0.016
 unst-0.016
 Mill-0.015
Token find
Token ID1064
Feature activation+3.87e+00

Pos logit contributions
 aids+0.112
 poems+0.100
ggie+0.100
 song+0.098
 wig+0.098
Neg logit contributions
 Joey-0.048
 unst-0.047
 Mill-0.046
 sorts-0.045
aved-0.044
Token a
Token ID257
Feature activation+3.38e-01

Pos logit contributions
rolley+0.286
ylan+0.283
wood+0.282
arp+0.280
erek+0.278
Neg logit contributions
 aids-0.237
 hair-0.223
 song-0.206
 jokes-0.201
 poems-0.198
Token dead
Token ID2636
Feature activation+6.16e-01

Pos logit contributions
arp+0.024
aved+0.024
 sorts+0.023
 Joey+0.023
 unst+0.023
Neg logit contributions
 aids-0.022
 song-0.020
 hair-0.019
 wig-0.019
 jokes-0.019
Token bug
Token ID5434
Feature activation-1.61e+00

Pos logit contributions
arp+0.042
 unst+0.042
 Joey+0.041
 sorts+0.041
aved+0.041
Neg logit contributions
 aids-0.042
 song-0.036
 jokes-0.036
 hair-0.035
 wig-0.035
Token and
Token ID290
Feature activation+1.82e-01

Pos logit contributions
 aids+0.108
 song+0.094
 jokes+0.094
 hair+0.092
 wig+0.092
Neg logit contributions
arp-0.111
 unst-0.108
 Joey-0.108
 sorts-0.107
aved-0.106
Token who
Token ID508
Feature activation-1.56e+00

Pos logit contributions
 unst+0.085
 Joey+0.082
arp+0.082
 sorts+0.081
aved+0.079
Neg logit contributions
 aids-0.104
uren-0.091
 poems-0.090
 cheeks-0.087
 song-0.087
Token had
Token ID550
Feature activation-1.11e+00

Pos logit contributions
 aids+0.119
 song+0.102
 jokes+0.102
 wig+0.101
 hair+0.101
Neg logit contributions
 Joey-0.094
arp-0.094
 sorts-0.093
 unst-0.093
aved-0.091
Token fallen
Token ID9292
Feature activation+2.95e+00

Pos logit contributions
 aids+0.092
uren+0.079
 song+0.079
 Dancing+0.079
 jokes+0.078
Neg logit contributions
 unst-0.061
 Joey-0.058
 sorts-0.056
 Mill-0.056
arp-0.055
Token down
Token ID866
Feature activation+4.19e-01

Pos logit contributions
arp+0.176
 sorts+0.175
 Joey+0.171
ylan+0.169
erek+0.168
Neg logit contributions
 aids-0.217
 hair-0.209
 song-0.197
 wig-0.189
 jokes-0.186
Token and
Token ID290
Feature activation+6.39e-01

Pos logit contributions
arp+0.037
ylan+0.037
erek+0.036
aved+0.036
ucer+0.036
Neg logit contributions
 aids-0.018
 hair-0.016
 song-0.015
 poems-0.014
 curly-0.013
Token hurt
Token ID5938
Feature activation-1.72e+00

Pos logit contributions
arp+0.047
 sorts+0.045
 Joey+0.044
aved+0.044
 unst+0.044
Neg logit contributions
 aids-0.042
 song-0.035
 jokes-0.035
 hair-0.035
 wig-0.035
Token his
Token ID465
Feature activation-1.22e+00

Pos logit contributions
 aids+0.114
 song+0.096
 jokes+0.096
ggie+0.094
 wig+0.094
Neg logit contributions
arp-0.122
 unst-0.120
 Joey-0.120
 sorts-0.118
aved-0.116
Token knee
Token ID10329
Feature activation-4.02e+00

Pos logit contributions
 aids+0.068
uren+0.056
 Dancing+0.051
ggie+0.050
 poems+0.049
Neg logit contributions
 unst-0.105
arp-0.101
 extingu-0.098
 Joey-0.097
 afloat-0.096
Token,
Token ID11
Feature activation+6.56e-01

Pos logit contributions
 aids+0.302
 jokes+0.259
 wig+0.254
ggie+0.253
 song+0.252
Neg logit contributions
 unst-0.256
arp-0.250
aved-0.241
 sorts-0.239
 Joey-0.237
Token just
Token ID655
Feature activation+6.10e-01

Pos logit contributions
 unst+0.039
 Joey+0.039
 Mill+0.037
 sorts+0.037
arp+0.037
Neg logit contributions
 aids-0.050
ggie-0.044
 jokes-0.043
 wig-0.043
 Dancing-0.043
Token like
Token ID588
Feature activation+1.27e+00

Pos logit contributions
 unst+0.038
 Joey+0.038
 sorts+0.037
 Mill+0.037
aved+0.036
Neg logit contributions
 aids-0.046
ggie-0.039
 wig-0.039
 song-0.039
 jokes-0.038
Token
Token ID198
Feature activation+5.73e-01

Pos logit contributions
arp+0.038
 unst+0.038
 Joey+0.037
 sorts+0.037
aved+0.037
Neg logit contributions
 aids-0.040
 jokes-0.034
 song-0.034
ggie-0.033
 hair-0.033
TokenThe
Token ID464
Feature activation-5.53e-01

Pos logit contributions
arp+0.036
 sorts+0.036
 Joey+0.035
 unst+0.035
neath+0.034
Neg logit contributions
 aids-0.042
 hair-0.036
 wig-0.036
 jokes-0.036
 cheeks-0.036
Token doctor
Token ID6253
Feature activation-1.28e-01

Pos logit contributions
 aids+0.039
 cheeks+0.033
uren+0.033
 jokes+0.032
 Dancing+0.032
Neg logit contributions
 handy-0.036
 unst-0.034
 deeper-0.034
rolley-0.031
 shed-0.031
Token then
Token ID788
Feature activation-2.84e+00

Pos logit contributions
 aids+0.009
 jokes+0.008
 song+0.008
 hair+0.008
 wig+0.008
Neg logit contributions
arp-0.008
 unst-0.008
 Joey-0.008
 sorts-0.008
 Mill-0.008
Token said
Token ID531
Feature activation+5.21e-01

Pos logit contributions
 aids+0.197
 jokes+0.169
 song+0.169
 hair+0.165
ggie+0.164
Neg logit contributions
arp-0.194
 unst-0.188
 Joey-0.185
 sorts-0.185
aved-0.184
Token Molly
Token ID30236
Feature activation+9.47e-02

Pos logit contributions
 Joey+0.029
 Mill+0.028
 Bobby+0.027
 unst+0.026
 if+0.025
Neg logit contributions
 aids-0.041
 wig-0.037
 song-0.036
 Dancing-0.036
 hair-0.036
Token should
Token ID815
Feature activation+3.91e+00

Pos logit contributions
 Joey+0.005
 unst+0.005
 Mill+0.005
 sorts+0.005
arp+0.005
Neg logit contributions
 aids-0.007
 wig-0.007
 song-0.007
 jokes-0.006
 Dancing-0.006
Token be
Token ID307
Feature activation-3.79e+00

Pos logit contributions
arp+0.272
 unst+0.267
 Joey+0.265
 sorts+0.264
aved+0.260
Neg logit contributions
 aids-0.263
 song-0.224
 jokes-0.223
 hair-0.219
ggie-0.218
Token honest
Token ID5508
Feature activation+1.59e+00

Pos logit contributions
 aids+0.267
 song+0.227
 jokes+0.226
 wig+0.223
ggie+0.221
Neg logit contributions
 unst-0.252
arp-0.249
 sorts-0.249
 Joey-0.248
aved-0.241
Token and
Token ID290
Feature activation+6.52e-01

Pos logit contributions
arp+0.114
 unst+0.111
aved+0.110
 Joey+0.110
 sorts+0.108
Neg logit contributions
 aids-0.104
 song-0.090
 jokes-0.090
 hair-0.089
 poems-0.087
Token not
Token ID407
Feature activation-2.27e+00

Pos logit contributions
arp+0.044
 unst+0.044
 Joey+0.044
 sorts+0.044
aved+0.043
Neg logit contributions
 aids-0.044
 song-0.038
 jokes-0.037
 hair-0.037
 wig-0.037
Token,
Token ID11
Feature activation+1.87e+00

Pos logit contributions
 Joey+0.137
 Mill+0.132
 unst+0.124
 Suz+0.122
 Bobby+0.122
Neg logit contributions
 aids-0.185
 song-0.162
 wig-0.161
 Dancing-0.158
 poems-0.157
Token "
Token ID366
Feature activation+6.63e-01

Pos logit contributions
 Joey+0.133
 Mill+0.128
 unst+0.123
 Bobby+0.120
 Suz+0.119
Neg logit contributions
 aids-0.125
ggie-0.109
 wig-0.106
 poems-0.104
 jokes-0.104
TokenI
Token ID40
Feature activation+2.21e+00

Pos logit contributions
arp+0.035
 Joey+0.034
 sorts+0.034
 Mill+0.033
neath+0.033
Neg logit contributions
 aids-0.056
 jokes-0.051
 cheeks-0.050
 hair-0.050
 poems-0.049
Token miss
Token ID2051
Feature activation-1.14e+00

Pos logit contributions
arp+0.117
 Joey+0.108
 unst+0.108
 hed+0.106
 sorts+0.105
Neg logit contributions
 aids-0.189
 jokes-0.169
 song-0.168
ggie-0.167
 hair-0.167
Token you
Token ID345
Feature activation+1.06e+00

Pos logit contributions
 aids+0.092
 song+0.080
 jokes+0.080
 wig+0.079
ggie+0.079
Neg logit contributions
arp-0.063
 Joey-0.062
 unst-0.062
 sorts-0.061
 Mill-0.060
Token too
Token ID1165
Feature activation-5.18e+00

Pos logit contributions
arp+0.064
 unst+0.063
 Joey+0.063
 sorts+0.062
aved+0.061
Neg logit contributions
 aids-0.080
 song-0.069
 jokes-0.069
 hair-0.068
 wig-0.068
Token,
Token ID11
Feature activation+6.27e-01

Pos logit contributions
 aids+0.342
 song+0.303
 hair+0.302
 jokes+0.299
ggie+0.290
Neg logit contributions
arp-0.373
 unst-0.356
aved-0.353
neath-0.348
erek-0.342
Token daddy
Token ID35822
Feature activation+2.67e+00

Pos logit contributions
 Joey+0.044
arp+0.043
 unst+0.043
 Mill+0.042
 sorts+0.042
Neg logit contributions
 aids-0.042
 song-0.034
 jokes-0.034
ggie-0.034
 hair-0.034
Token.
Token ID13
Feature activation-8.16e-02

Pos logit contributions
arp+0.180
 unst+0.177
aved+0.175
 sorts+0.173
 Joey+0.173
Neg logit contributions
 aids-0.183
 song-0.161
 jokes-0.159
 hair-0.156
ggie-0.156
Token But
Token ID887
Feature activation-1.19e+00

Pos logit contributions
 aids+0.006
 song+0.005
 jokes+0.005
ggie+0.005
 wig+0.005
Neg logit contributions
 Joey-0.005
arp-0.005
 Mill-0.005
 unst-0.005
 sorts-0.005
Token don
Token ID836
Feature activation+4.39e+00

Pos logit contributions
 aids+0.081
 song+0.072
 jokes+0.072
 hair+0.070
 wig+0.069
Neg logit contributions
arp-0.084
aved-0.080
 sorts-0.079
 unst-0.078
rolley-0.076
Token go
Token ID467
Feature activation-1.43e-01

Pos logit contributions
 aids+0.068
 poems+0.059
uren+0.058
 wig+0.058
 cheeks+0.058
Neg logit contributions
 Joey-0.047
 sorts-0.047
 unst-0.046
 Mill-0.045
arp-0.045
Token to
Token ID284
Feature activation-8.44e-01

Pos logit contributions
 aids+0.010
 song+0.009
 jokes+0.009
 hair+0.009
 wig+0.009
Neg logit contributions
arp-0.009
 unst-0.009
 Joey-0.009
 sorts-0.009
aved-0.009
Token a
Token ID257
Feature activation+5.99e-01

Pos logit contributions
 aids+0.062
 jokes+0.055
 song+0.055
 hair+0.054
 poems+0.053
Neg logit contributions
arp-0.054
 unst-0.052
aved-0.052
 Joey-0.051
 sorts-0.050
Token meeting
Token ID3249
Feature activation-4.55e+00

Pos logit contributions
arp+0.035
 Joey+0.034
 sorts+0.034
 unst+0.034
 scaven+0.034
Neg logit contributions
 aids-0.048
 cheeks-0.041
 hair-0.040
 jokes-0.040
 poems-0.039
Token.
Token ID13
Feature activation+1.16e-01

Pos logit contributions
 aids+0.374
 cheeks+0.320
uren+0.317
 wig+0.317
 Dancing+0.315
Neg logit contributions
 sorts-0.256
 Joey-0.242
 unst-0.241
arp-0.238
 Mill-0.236
Token His
Token ID2399
Feature activation-5.32e+00

Pos logit contributions
arp+0.008
 unst+0.008
aved+0.008
 Joey+0.008
 sorts+0.008
Neg logit contributions
 aids-0.008
 jokes-0.007
 song-0.007
 hair-0.006
 poems-0.006
Token mum
Token ID25682
Feature activation-1.16e+00

Pos logit contributions
 aids+0.384
 wig+0.302
 poems+0.298
 song+0.295
uren+0.286
Neg logit contributions
 Joey-0.349
 Mill-0.349
erek-0.336
 shed-0.334
 barrel-0.334
Token told
Token ID1297
Feature activation+3.03e-01

Pos logit contributions
 aids+0.071
 song+0.062
ggie+0.062
 hair+0.061
 jokes+0.061
Neg logit contributions
arp-0.086
 unst-0.083
 hed-0.083
aved-0.081
 Joey-0.080
Token him
Token ID683
Feature activation+3.54e+00

Pos logit contributions
arp+0.015
 unst+0.014
aved+0.014
 sorts+0.014
 Joey+0.013
Neg logit contributions
 aids-0.027
 jokes-0.024
 song-0.024
 poems-0.024
 hair-0.024
Token,
Token ID11
Feature activation+5.45e-01

Pos logit contributions
 Joey+0.227
 Mill+0.221
arp+0.215
 sorts+0.214
 unst+0.211
Neg logit contributions
 aids-0.256
 wig-0.224
 song-0.222
 hair-0.216
 Dancing-0.214
Token
Token ID6184
Feature activation+1.91e+00

Pos logit contributions
 Joey+0.041
 Mill+0.040
 unst+0.039
 sorts+0.039
arp+0.039
Neg logit contributions
 aids-0.034
ggie-0.028
 wig-0.028
 song-0.028
 jokes-0.028
Token hospital
Token ID4436
Feature activation+9.72e-01

Pos logit contributions
arp+0.035
 unst+0.034
 sorts+0.032
 Joey+0.032
aved+0.031
Neg logit contributions
 aids-0.058
 poems-0.051
 jokes-0.051
 cheeks-0.050
 song-0.050
Token,
Token ID11
Feature activation+5.09e-01

Pos logit contributions
 unst+0.054
 Mill+0.052
 sorts+0.051
 Joey+0.051
arp+0.051
Neg logit contributions
 aids-0.079
 wig-0.069
 jokes-0.069
 Dancing-0.068
ggie-0.068
Token but
Token ID475
Feature activation+3.68e-01

Pos logit contributions
arp+0.039
aved+0.037
 sorts+0.037
 Joey+0.036
wood+0.036
Neg logit contributions
 aids-0.032
 song-0.028
 hair-0.027
 jokes-0.027
 wig-0.026
Token it
Token ID340
Feature activation+1.58e+00

Pos logit contributions
arp+0.028
aved+0.027
 sorts+0.027
 extingu+0.026
 Joey+0.026
Neg logit contributions
 aids-0.023
 song-0.020
 hair-0.020
 jokes-0.020
 poems-0.019
Token was
Token ID373
Feature activation+6.85e-01

Pos logit contributions
arp+0.096
 unst+0.093
 Joey+0.093
 sorts+0.093
aved+0.091
Neg logit contributions
 aids-0.121
 song-0.106
 jokes-0.105
ggie-0.103
 hair-0.103
Token too
Token ID1165
Feature activation-5.48e+00

Pos logit contributions
arp+0.053
 unst+0.052
 Joey+0.052
 sorts+0.052
aved+0.051
Neg logit contributions
 aids-0.041
 song-0.034
 jokes-0.034
 hair-0.033
 wig-0.033
Token late
Token ID2739
Feature activation+4.63e+00

Pos logit contributions
 aids+0.407
 song+0.371
 poems+0.360
 hair+0.357
 jokes+0.352
Neg logit contributions
arp-0.323
 sorts-0.319
 Joey-0.318
aved-0.314
 unst-0.310
Token.
Token ID13
Feature activation+1.29e-01

Pos logit contributions
arp+0.306
 unst+0.302
 Joey+0.300
 sorts+0.298
aved+0.292
Neg logit contributions
 aids-0.326
 jokes-0.278
 song-0.278
 wig-0.273
 hair-0.272
Token The
Token ID383
Feature activation-1.28e+00

Pos logit contributions
 unst+0.008
 Mill+0.008
 Joey+0.007
 Bobby+0.007
arp+0.007
Neg logit contributions
 aids-0.010
 wig-0.009
ggie-0.009
 song-0.009
 jokes-0.009
Token water
Token ID1660
Feature activation+2.29e+00

Pos logit contributions
 aids+0.096
uren+0.084
 poems+0.083
 blond+0.082
ggie+0.081
Neg logit contributions
arp-0.078
 unst-0.075
 deeper-0.073
 hed-0.071
aved-0.070
Token from
Token ID422
Feature activation+5.79e+00

Pos logit contributions
arp+0.144
 unst+0.141
 sorts+0.140
 Joey+0.140
aved+0.137
Neg logit contributions
 aids-0.170
 song-0.147
 jokes-0.146
 hair-0.144
ggie-0.143
Token
Token ID95
Feature activation+8.31e-01

Pos logit contributions
 Joey+0.109
arp+0.106
 unst+0.103
aved+0.103
 scaven+0.099
Neg logit contributions
 aids-0.141
 poems-0.127
 song-0.122
 jokes-0.119
 hair-0.117
Token
Token ID26391
Feature activation-5.29e+00

Pos logit contributions
 sorts+0.052
arp+0.052
 unst+0.051
 Joey+0.051
 aback+0.049
Neg logit contributions
 aids-0.056
 poems-0.053
 cheeks-0.052
 jokes-0.050
 song-0.050
Token
Token ID129
Feature activation-4.23e-01

Pos logit contributions
 aids+0.388
 song+0.334
 jokes+0.334
 wig+0.325
 hair+0.324
Neg logit contributions
arp-0.332
 Joey-0.330
 unst-0.329
 sorts-0.325
aved-0.320
Token
Token ID241
Feature activation-3.73e+00

Pos logit contributions
 aids+0.027
 wig+0.025
 cheeks+0.024
 song+0.024
 poems+0.023
Neg logit contributions
 unst-0.029
 Joey-0.028
 sorts-0.028
arp-0.027
aved-0.026
TokenMe
Token ID5308
Feature activation-8.56e-01

Pos logit contributions
 aids+0.296
 jokes+0.251
 cheeks+0.251
 poems+0.248
 hair+0.247
Neg logit contributions
 Joey-0.221
 sorts-0.220
arp-0.209
 Mill-0.209
 unst-0.207
Token too
Token ID1165
Feature activation-5.31e+00

Pos logit contributions
 aids+0.057
 poems+0.047
 wig+0.047
 jokes+0.045
 song+0.045
Neg logit contributions
 Joey-0.063
 unst-0.062
 Mill-0.060
 sorts-0.059
 Suz-0.058
Token!
Token ID0
Feature activation+4.47e+00

Pos logit contributions
 aids+0.480
 song+0.428
 jokes+0.427
 hair+0.421
ggie+0.420
Neg logit contributions
arp-0.247
 unst-0.240
 Joey-0.236
 sorts-0.235
aved-0.231
Token I
Token ID314
Feature activation-5.27e-01

Pos logit contributions
 Joey+0.287
arp+0.286
 unst+0.283
 sorts+0.281
 Mill+0.277
Neg logit contributions
 aids-0.321
 song-0.277
 jokes-0.276
ggie-0.272
 wig-0.271
Token like
Token ID588
Feature activation+1.25e+00

Pos logit contributions
 aids+0.045
 song+0.040
 jokes+0.040
 hair+0.039
ggie+0.039
Neg logit contributions
arp-0.028
 unst-0.026
 Joey-0.026
 Mill-0.025
 sorts-0.025
Token to
Token ID284
Feature activation-7.28e-01

Pos logit contributions
 Joey+0.073
 sorts+0.072
 unst+0.070
 Mill+0.070
arp+0.070
Neg logit contributions
 aids-0.098
ggie-0.085
 wig-0.084
 song-0.083
 cheeks-0.082
Token talk
Token ID1561
Feature activation-3.12e+00

Pos logit contributions
 aids+0.051
 poems+0.043
 song+0.043
ggie+0.043
 jokes+0.043
Neg logit contributions
 Joey-0.047
arp-0.047
 unst-0.047
 sorts-0.047
 Mill-0.046
Token clown
Token ID25573
Feature activation-8.30e+00

Pos logit contributions
 aids+0.101
ggie+0.085
uren+0.083
anna+0.077
ggy+0.076
Neg logit contributions
 barrel-0.128
 treasure-0.120
 treasures-0.118
 sorts-0.117
 lighthouse-0.116
Token liked
Token ID8288
Feature activation-2.63e+00

Pos logit contributions
 aids+0.686
 cheeks+0.566
 blond+0.565
 wig+0.564
uren+0.561
Neg logit contributions
 sorts-0.489
 Joey-0.445
aved-0.445
arp-0.439
'll-0.426
Token to
Token ID284
Feature activation-1.25e+00

Pos logit contributions
 aids+0.234
uren+0.206
ggie+0.202
 cheeks+0.199
 Dancing+0.196
Neg logit contributions
 Joey-0.137
 sorts-0.127
 Mill-0.122
 scaven-0.121
 Bobby-0.120
Token make
Token ID787
Feature activation-2.51e-01

Pos logit contributions
 aids+0.099
ggie+0.084
uren+0.084
 Dancing+0.084
 poems+0.083
Neg logit contributions
 sorts-0.070
 Joey-0.068
aved-0.065
 Mill-0.065
 Suz-0.064
Token people
Token ID661
Feature activation-6.88e-01

Pos logit contributions
 aids+0.017
 wig+0.014
 song+0.014
 Dancing+0.014
 cheeks+0.014
Neg logit contributions
 sorts-0.018
 Joey-0.017
arp-0.017
 unst-0.017
 Mill-0.017
Token laugh
Token ID6487
Feature activation-5.48e+00

Pos logit contributions
 aids+0.052
uren+0.046
ggie+0.045
 blond+0.043
 Dancing+0.042
Neg logit contributions
 sorts-0.044
 Joey-0.042
arp-0.041
 unst-0.041
 Mill-0.040
Token.
Token ID13
Feature activation-4.54e-01

Pos logit contributions
 aids+0.410
 wig+0.350
ggie+0.344
 hair+0.341
 song+0.341
Neg logit contributions
arp-0.337
 sorts-0.335
 unst-0.332
 Joey-0.331
aved-0.321
Token
Token ID198
Feature activation+1.30e-01

Pos logit contributions
 aids+0.039
 wig+0.035
ggie+0.035
 song+0.035
 poems+0.035
Neg logit contributions
 Joey-0.024
 sorts-0.022
 Mill-0.021
arp-0.021
 Bobby-0.021
Token
Token ID198
Feature activation+1.45e-01

Pos logit contributions
arp+0.008
 Joey+0.008
 unst+0.008
 sorts+0.008
aved+0.008
Neg logit contributions
 aids-0.010
 jokes-0.008
 song-0.008
 hair-0.008
 wig-0.008
TokenOne
Token ID3198
Feature activation-3.20e+00

Pos logit contributions
 sorts+0.008
arp+0.008
 scaven+0.007
 hed+0.007
 deeper+0.007
Neg logit contributions
 aids-0.012
 cheeks-0.012
 throat-0.011
 wig-0.011
 hair-0.011
Token day
Token ID1110
Feature activation-1.53e+00

Pos logit contributions
 aids+0.313
 cheeks+0.278
 wig+0.271
 blond+0.267
uren+0.264
Neg logit contributions
 sorts-0.152
 Joey-0.134
arp-0.126
cy-0.121
 deeper-0.119