TOP ACTIVATIONS
MAX = 15.152

very brave and smart . Of course you can have your
tomorrow and play again . Of course , she did and
an ugly little mouse . Of course , Joy couldn 't
to run too fast . Of course , Tommy was still
to go golf ing . Of course she said yes ,
folded it in two . Of course , it didn 't
moment . " Yes ! Of course ," he said .
a good brother too . Of course we can still be
are my best friend . Of course I include you in
his fish with him ! Of course , it wasn 't
said , " Yes ! Of course . I have a
you are very kind . Of course you can touch it
You can , Max . Of course you can , it
said , " Yes ! Of course you can borrow some
could hardly stand it ! Of course she wanted to go
ride in the wagon . Of course , Molly and Sam
said , " Yes ! Of course ." The
friends to go home . Of course , they had a
my cute little girl ! Of course you can have a
they could join her . Of course , she said yes

MIN ACTIVATIONS
MIN = -15.949

give away her things to strangers again . <|endoftext|> Once upon
rules . She knew that strangers could be dangerous and that
feelings and not to follow strangers . They learned to stay
that they should not trust strangers . They learned that they
promised never to frown on strangers again . They also promised
to their friends and to strangers . They hugged each other
friends and not talking to strangers . Lily thought that was
" You shouldn 't trust strangers !" in a harsh voice
be patient and not trust strangers . <|endoftext|> Once upon a
shy and does not like strangers ." " Thank
. They do not follow strangers . They are polite and
it . Finally , the strangers got angry . They started
day to be careful with strangers and to not trust them
match for the group of strangers . She realized that in
€ ™ t scared of strangers anymore - he was very
you know and not follow strangers , even if it 's
. Lily learned that sometimes strangers can be nice , but
is dangerous . You are strangers . You are big and
away . The strangers began to get dangerous .
them to stay away from strangers . But they did not

INTERVAL 7.377 - 15.152
CONTAINS 2.593%

there was a happy little boy named Tim . Tim loved
the table was set up with a big , red cake
he was climbing all the way up to the top of
envelop es united and became one big , happy family .
to become a great basketball player . Thanks to the

INTERVAL -0.399 - 7.377
CONTAINS 53.871%

reached for the ball . Suddenly , she saw a cute
, he saw a big , angry cat coming towards him
it , before putting on her shoes . She waved goodbye
't have any time to get a massage . She started
and started applaud ing louder . The performer was so embarrassed

INTERVAL -8.174 - -0.399
CONTAINS 43.160%

sun fl owers again . <|endoftext|> L ily and Ben were
." Her mom smiled and said , "
, but be careful and don 't lean too far ,"
great time at the event . <|endoftext|> Once upon a time
All of Bella 's friends wanted to see the triangle in

INTERVAL -15.949 - -8.174
CONTAINS 0.376%

Then , it started to rain . The bunny looked up
the lion flex ed his muscles and roared .
So , one of the cows offered to carry her out
ride together . The two ponies ran through the me adow
so happy and smiled at Billy . His mother hugged him
Token very
Token ID845
Feature activation-5.94e-01

Pos logit contributions
 strangers+0.217
 tresp+0.191
vern+0.185
unts+0.174
 cruel+0.173
Neg logit contributions
 Of-0.197
cy-0.196
 girl-0.186
sc-0.183
 Sure-0.177
Token brave
Token ID14802
Feature activation-3.75e+00

Pos logit contributions
 strangers+0.030
 tresp+0.026
vern+0.024
 supposed+0.022
 cruel+0.022
Neg logit contributions
 Of-0.037
cy-0.037
 girl-0.035
sc-0.035
 Sure-0.034
Token and
Token ID290
Feature activation-2.53e+00

Pos logit contributions
 strangers+0.231
 tresp+0.206
vern+0.194
 cruel+0.187
 supposed+0.185
Neg logit contributions
 Of-0.194
cy-0.193
sc-0.181
 Sure-0.177
 girl-0.175
Token smart
Token ID4451
Feature activation-2.88e+00

Pos logit contributions
 strangers+0.110
 tresp+0.095
vern+0.088
 cruel+0.088
 supposed+0.083
Neg logit contributions
cy-0.176
 Of-0.173
sc-0.167
 girl-0.163
 Sure-0.162
Token.
Token ID13
Feature activation-1.21e-02

Pos logit contributions
 strangers+0.187
 tresp+0.168
vern+0.160
 cruel+0.153
 supposed+0.153
Neg logit contributions
 Of-0.139
cy-0.138
sc-0.128
 Sure-0.126
 girl-0.125
Token Of
Token ID3226
Feature activation+1.49e+01

Pos logit contributions
 strangers+0.001
 tresp+0.001
isdom+0.001
vern+0.001
unts+0.001
Neg logit contributions
cy-0.001
 mixture-0.000
sc-0.000
 girl-0.000
 tin-0.000
Token course
Token ID1781
Feature activation-1.45e+00

Pos logit contributions
cy+0.768
 Of+0.767
 girl+0.759
sc+0.688
 tin+0.678
Neg logit contributions
 strangers-0.848
 tresp-0.752
vern-0.747
 supposed-0.735
cod-0.712
Token you
Token ID345
Feature activation+5.73e-01

Pos logit contributions
 strangers+0.091
 tresp+0.081
vern+0.076
 cruel+0.074
 supposed+0.072
Neg logit contributions
cy-0.073
 Of-0.073
sc-0.070
 Sure-0.067
 girl-0.066
Token can
Token ID460
Feature activation-4.46e+00

Pos logit contributions
cy+0.028
 girl+0.027
 Of+0.025
sc+0.025
 tin+0.025
Neg logit contributions
 strangers-0.038
 tresp-0.032
vern-0.032
Days-0.031
eping-0.030
Token have
Token ID423
Feature activation-3.06e+00

Pos logit contributions
 strangers+0.273
 tresp+0.247
 cruel+0.229
vern+0.227
cod+0.222
Neg logit contributions
cy-0.233
 Of-0.230
 girl-0.214
 tin-0.209
sc-0.207
Token your
Token ID534
Feature activation+6.88e-01

Pos logit contributions
 strangers+0.214
 tresp+0.196
vern+0.188
 cruel+0.180
 supposed+0.179
Neg logit contributions
 Of-0.131
cy-0.130
sc-0.120
 girl-0.120
 Sure-0.116
Token tomorrow
Token ID9439
Feature activation-5.81e-02

Pos logit contributions
 strangers+0.067
 tresp+0.059
vern+0.057
 supposed+0.054
 cruel+0.053
Neg logit contributions
 Of-0.055
cy-0.053
sc-0.052
 girl-0.051
 Sure-0.049
Token and
Token ID290
Feature activation-2.28e+00

Pos logit contributions
 strangers+0.004
 tresp+0.003
vern+0.003
 supposed+0.003
 cruel+0.003
Neg logit contributions
 Of-0.003
cy-0.003
sc-0.003
 girl-0.003
 Sure-0.003
Token play
Token ID711
Feature activation-6.94e-01

Pos logit contributions
 strangers+0.127
 tresp+0.110
 cruel+0.100
vern+0.099
 never+0.097
Neg logit contributions
cy-0.130
 Of-0.130
sc-0.126
 Sure-0.120
 girl-0.119
Token again
Token ID757
Feature activation+4.83e+00

Pos logit contributions
 strangers+0.052
 tresp+0.048
vern+0.046
 enemies+0.044
 cruel+0.044
Neg logit contributions
 Of-0.026
cy-0.025
 Sure-0.023
 girl-0.022
sc-0.021
Token.
Token ID13
Feature activation+3.58e-01

Pos logit contributions
 Of+0.237
cy+0.233
sc+0.221
 girl+0.216
 Sure+0.213
Neg logit contributions
 strangers-0.311
 tresp-0.276
vern-0.264
 cruel-0.253
 supposed-0.252
Token Of
Token ID3226
Feature activation+1.47e+01

Pos logit contributions
cy+0.019
sc+0.019
 tin+0.018
 girl+0.018
 mixture+0.018
Neg logit contributions
 strangers-0.020
 tresp-0.017
unts-0.016
vern-0.016
isdom-0.016
Token course
Token ID1781
Feature activation-1.56e+00

Pos logit contributions
cy+0.782
 Of+0.771
 girl+0.766
sc+0.701
 Sure+0.675
Neg logit contributions
 strangers-0.841
vern-0.768
 tresp-0.760
 supposed-0.739
unts-0.696
Token,
Token ID11
Feature activation+8.50e-01

Pos logit contributions
 strangers+0.096
 tresp+0.085
vern+0.080
 cruel+0.078
 supposed+0.076
Neg logit contributions
 Of-0.081
cy-0.080
sc-0.077
 girl-0.074
 Sure-0.074
Token she
Token ID673
Feature activation+1.95e+00

Pos logit contributions
cy+0.047
sc+0.046
 Of+0.046
 Sure+0.043
suit+0.042
Neg logit contributions
 strangers-0.049
 tresp-0.042
 never-0.039
 cruel-0.038
vern-0.038
Token did
Token ID750
Feature activation-1.85e+00

Pos logit contributions
cy+0.102
 Of+0.097
 girl+0.096
sc+0.094
 onto+0.089
Neg logit contributions
 strangers-0.121
 tresp-0.107
vern-0.105
 cruel-0.099
cod-0.098
Token and
Token ID290
Feature activation-2.22e+00

Pos logit contributions
 strangers+0.127
 tresp+0.115
vern+0.110
 cruel+0.108
unts+0.107
Neg logit contributions
 Of-0.082
cy-0.078
 girl-0.074
sc-0.073
 Sure-0.071
Token an
Token ID281
Feature activation-8.29e-01

Pos logit contributions
 Of+0.164
cy+0.163
sc+0.152
 girl+0.151
 Sure+0.147
Neg logit contributions
 strangers-0.252
 tresp-0.228
vern-0.221
 cruel-0.211
 supposed-0.209
Token ugly
Token ID13400
Feature activation-3.30e+00

Pos logit contributions
 strangers+0.046
vern+0.042
 tresp+0.041
unts+0.039
 cruel+0.037
Neg logit contributions
 girl-0.045
 Of-0.044
cy-0.043
 up-0.041
 tin-0.040
Token little
Token ID1310
Feature activation+8.62e-01

Pos logit contributions
 strangers+0.209
 tresp+0.188
vern+0.178
 cruel+0.172
 supposed+0.169
Neg logit contributions
 Of-0.164
cy-0.163
sc-0.154
 girl-0.149
 Sure-0.148
Token mouse
Token ID10211
Feature activation+1.35e+00

Pos logit contributions
 Of+0.043
cy+0.040
sc+0.040
 Sure+0.039
 onto+0.035
Neg logit contributions
 strangers-0.056
 tresp-0.050
 cruel-0.046
 mean-0.045
 liar-0.044
Token.
Token ID13
Feature activation+2.40e-01

Pos logit contributions
cy+0.062
 Of+0.060
 girl+0.059
sc+0.058
 onto+0.055
Neg logit contributions
 strangers-0.087
vern-0.081
 tresp-0.079
 cruel-0.074
unts-0.073
Token Of
Token ID3226
Feature activation+1.46e+01

Pos logit contributions
cy+0.011
 Of+0.010
sc+0.010
 girl+0.010
 Sure+0.009
Neg logit contributions
 strangers-0.016
 tresp-0.014
vern-0.014
unts-0.013
 cruel-0.013
Token course
Token ID1781
Feature activation-1.70e+00

Pos logit contributions
 Of+0.847
cy+0.842
 girl+0.806
sc+0.776
 Sure+0.762
Neg logit contributions
 strangers-0.803
 tresp-0.712
vern-0.694
 supposed-0.656
unts-0.642
Token,
Token ID11
Feature activation+5.89e-01

Pos logit contributions
 strangers+0.105
 tresp+0.095
vern+0.088
 cruel+0.086
 supposed+0.084
Neg logit contributions
cy-0.086
 Of-0.086
sc-0.082
 girl-0.078
 Sure-0.078
Token Joy
Token ID14087
Feature activation+5.00e+00

Pos logit contributions
cy+0.031
 Of+0.030
sc+0.030
 Sure+0.027
 girl+0.027
Neg logit contributions
 strangers-0.036
 tresp-0.032
vern-0.029
 cruel-0.029
 never-0.028
Token couldn
Token ID3521
Feature activation-5.93e+00

Pos logit contributions
cy+0.242
 girl+0.228
 Of+0.226
sc+0.220
 onto+0.208
Neg logit contributions
 strangers-0.326
 tresp-0.293
vern-0.292
 supposed-0.270
 cruel-0.270
Token't
Token ID470
Feature activation-2.98e+00

Pos logit contributions
 strangers+0.329
 tresp+0.288
vern+0.273
 cruel+0.263
unts+0.259
Neg logit contributions
 Of-0.343
cy-0.338
sc-0.325
 girl-0.315
 Sure-0.314
Token to
Token ID284
Feature activation-7.32e-01

Pos logit contributions
 strangers+0.273
vern+0.248
 tresp+0.247
unts+0.226
 cruel+0.225
Neg logit contributions
 Of-0.244
cy-0.243
 girl-0.230
sc-0.224
 Sure-0.219
Token run
Token ID1057
Feature activation-4.48e+00

Pos logit contributions
vern+0.042
 strangers+0.041
 tresp+0.040
unts+0.037
 cruel+0.037
Neg logit contributions
cy-0.035
 Of-0.035
 girl-0.034
 down-0.033
 up-0.032
Token too
Token ID1165
Feature activation+1.72e-01

Pos logit contributions
 strangers+0.348
 tresp+0.327
vern+0.324
isdom+0.310
unts+0.307
Neg logit contributions
cy-0.147
sc-0.142
 Of-0.141
 girl-0.132
 down-0.131
Token fast
Token ID3049
Feature activation-1.37e+00

Pos logit contributions
 down+0.009
cy+0.009
 onto+0.008
 up+0.008
sc+0.008
Neg logit contributions
 strangers-0.009
 tresp-0.009
isdom-0.009
cod-0.009
vern-0.009
Token.
Token ID13
Feature activation+2.66e-01

Pos logit contributions
 strangers+0.095
 tresp+0.088
vern+0.086
 cruel+0.082
unts+0.081
Neg logit contributions
 Of-0.056
cy-0.056
sc-0.053
 girl-0.052
 down-0.050
Token Of
Token ID3226
Feature activation+1.45e+01

Pos logit contributions
cy+0.012
sc+0.012
 Of+0.011
 girl+0.011
 tin+0.010
Neg logit contributions
 strangers-0.018
 tresp-0.016
vern-0.015
 hated-0.015
unts-0.015
Token course
Token ID1781
Feature activation-1.75e+00

Pos logit contributions
 girl+0.659
 Of+0.658
cy+0.626
sc+0.549
 cash+0.547
Neg logit contributions
 strangers-0.878
vern-0.855
 supposed-0.824
 tresp-0.812
unts-0.796
Token,
Token ID11
Feature activation+7.04e-01

Pos logit contributions
 strangers+0.109
 tresp+0.097
vern+0.091
 cruel+0.088
 supposed+0.087
Neg logit contributions
cy-0.090
 Of-0.089
sc-0.085
 girl-0.082
 Sure-0.081
Token Tommy
Token ID19919
Feature activation-2.48e+00

Pos logit contributions
cy+0.039
sc+0.038
 Of+0.037
 girl+0.035
 Sure+0.035
Neg logit contributions
 strangers-0.042
 tresp-0.036
vern-0.033
 hated-0.032
 never-0.032
Token was
Token ID373
Feature activation+3.00e+00

Pos logit contributions
 strangers+0.161
 tresp+0.144
vern+0.143
cod+0.134
 cruel+0.132
Neg logit contributions
cy-0.122
 girl-0.116
 Of-0.113
 down-0.110
 up-0.109
Token still
Token ID991
Feature activation-2.42e+00

Pos logit contributions
 up+0.165
 Of+0.164
 down+0.162
 girl+0.160
cy+0.160
Neg logit contributions
 strangers-0.167
 tresp-0.147
vern-0.139
unts-0.135
cod-0.135
Token to
Token ID284
Feature activation-8.91e-01

Pos logit contributions
 strangers+0.186
 tresp+0.169
vern+0.162
 cruel+0.155
 supposed+0.154
Neg logit contributions
 Of-0.127
cy-0.126
sc-0.118
 girl-0.117
 Sure-0.114
Token go
Token ID467
Feature activation-2.55e+00

Pos logit contributions
 strangers+0.058
 tresp+0.053
vern+0.049
cod+0.049
 cruel+0.049
Neg logit contributions
 Of-0.043
cy-0.042
 girl-0.039
sc-0.038
 onto-0.038
Token golf
Token ID13126
Feature activation-3.15e+00

Pos logit contributions
 strangers+0.170
 tresp+0.152
vern+0.146
 supposed+0.141
 cruel+0.138
Neg logit contributions
 Of-0.118
cy-0.116
sc-0.109
 girl-0.108
 Sure-0.107
Tokening
Token ID278
Feature activation+4.31e+00

Pos logit contributions
 strangers+0.212
 tresp+0.190
vern+0.187
 enemies+0.174
 cruel+0.172
Neg logit contributions
 Of-0.140
cy-0.135
 Sure-0.132
 girl-0.125
 Me-0.122
Token.
Token ID13
Feature activation+4.69e-02

Pos logit contributions
 Of+0.215
cy+0.211
 Sure+0.202
 girl+0.195
sc+0.194
Neg logit contributions
 strangers-0.276
 tresp-0.241
vern-0.225
 cruel-0.218
unts-0.216
Token Of
Token ID3226
Feature activation+1.44e+01

Pos logit contributions
cy+0.003
sc+0.003
 tin+0.002
fl+0.002
cer+0.002
Neg logit contributions
 strangers-0.002
 hated-0.002
 shouldn-0.002
lee-0.002
 tresp-0.002
Token course
Token ID1781
Feature activation-1.81e+00

Pos logit contributions
cy+0.848
 Of+0.848
 girl+0.808
sc+0.783
 Sure+0.761
Neg logit contributions
 strangers-0.775
 tresp-0.694
vern-0.671
 supposed-0.632
unts-0.619
Token she
Token ID673
Feature activation+1.62e+00

Pos logit contributions
 strangers+0.108
 tresp+0.093
vern+0.086
 cruel+0.085
 hated+0.084
Neg logit contributions
cy-0.094
sc-0.094
 Of-0.094
 Sure-0.089
 tin-0.087
Token said
Token ID531
Feature activation+3.96e+00

Pos logit contributions
cy+0.077
 Of+0.076
 girl+0.071
sc+0.071
 Sure+0.068
Neg logit contributions
 strangers-0.108
 tresp-0.097
vern-0.093
 cruel-0.089
 supposed-0.088
Token yes
Token ID3763
Feature activation+1.49e-01

Pos logit contributions
 Of+0.212
cy+0.206
sc+0.196
 girl+0.196
 Sure+0.191
Neg logit contributions
 strangers-0.236
 tresp-0.211
vern-0.200
 supposed-0.192
unts-0.191
Token,
Token ID11
Feature activation+5.92e-01

Pos logit contributions
 Of+0.007
cy+0.007
sc+0.007
 girl+0.007
 Sure+0.006
Neg logit contributions
 strangers-0.010
 tresp-0.009
vern-0.008
 cruel-0.008
 supposed-0.008
Token folded
Token ID24650
Feature activation+4.21e+00

Pos logit contributions
 strangers+0.110
 never+0.097
 tresp+0.097
eping+0.096
 hated+0.093
Neg logit contributions
 Of-0.167
umm-0.158
cy-0.157
 Me-0.145
 Sure-0.144
Token it
Token ID340
Feature activation-3.72e-01

Pos logit contributions
cy+0.300
 Of+0.288
 girl+0.278
 Sure+0.277
umm+0.274
Neg logit contributions
 strangers-0.155
eping-0.133
eps-0.124
ills-0.119
vern-0.116
Token in
Token ID287
Feature activation+2.72e+00

Pos logit contributions
 strangers+0.020
 never+0.020
 often+0.019
 supposed+0.019
Days+0.018
Neg logit contributions
cy-0.020
 Of-0.019
 girl-0.019
 therapist-0.017
 Sure-0.017
Token two
Token ID734
Feature activation+5.57e+00

Pos logit contributions
 Of+0.153
cy+0.153
sc+0.145
 Sure+0.139
 girl+0.135
Neg logit contributions
 strangers-0.152
 tresp-0.137
vern-0.130
unts-0.127
 supposed-0.124
Token.
Token ID13
Feature activation+1.51e-01

Pos logit contributions
 Of+0.222
cy+0.222
sc+0.205
 girl+0.203
 Sure+0.195
Neg logit contributions
 strangers-0.406
 tresp-0.371
vern-0.357
 cruel-0.344
 supposed-0.342
Token Of
Token ID3226
Feature activation+1.44e+01

Pos logit contributions
cy+0.009
 girl+0.008
sc+0.007
cer+0.007
 Of+0.007
Neg logit contributions
 strangers-0.008
 tresp-0.007
unts-0.007
isdom-0.007
 hated-0.007
Token course
Token ID1781
Feature activation-1.79e+00

Pos logit contributions
cy+0.764
 Of+0.759
 girl+0.752
sc+0.692
 Sure+0.664
Neg logit contributions
 strangers-0.821
vern-0.743
 tresp-0.735
 supposed-0.707
unts-0.674
Token,
Token ID11
Feature activation+6.95e-01

Pos logit contributions
 strangers+0.109
 tresp+0.098
vern+0.092
 cruel+0.089
 supposed+0.087
Neg logit contributions
 Of-0.093
cy-0.093
sc-0.089
 girl-0.086
 Sure-0.084
Token it
Token ID340
Feature activation-3.15e-01

Pos logit contributions
cy+0.037
sc+0.036
 Of+0.035
 Sure+0.032
suit+0.032
Neg logit contributions
 strangers-0.043
 tresp-0.038
 never-0.034
 cruel-0.034
 enemies-0.033
Token didn
Token ID1422
Feature activation-5.63e+00

Pos logit contributions
 strangers+0.019
 tresp+0.017
vern+0.016
 supposed+0.016
 hated+0.015
Neg logit contributions
 Of-0.017
cy-0.016
 Sure-0.015
sc-0.015
 girl-0.015
Token't
Token ID470
Feature activation-3.06e+00

Pos logit contributions
 strangers+0.301
 tresp+0.263
vern+0.245
 cruel+0.240
cod+0.234
Neg logit contributions
 Of-0.337
cy-0.326
sc-0.321
 Sure-0.308
 girl-0.307
Token moment
Token ID2589
Feature activation+1.00e+01

Pos logit contributions
cy+0.036
 Of+0.034
sc+0.027
 onto+0.025
 Sure+0.024
Neg logit contributions
 strangers-0.154
 tresp-0.145
vern-0.140
 cruel-0.137
 supposed-0.134
Token.
Token ID13
Feature activation+3.80e-01

Pos logit contributions
 Of+0.508
cy+0.506
sc+0.474
 girl+0.470
 Sure+0.459
Neg logit contributions
 strangers-0.627
 tresp-0.563
vern-0.538
 cruel-0.513
 supposed-0.509
Token "
Token ID366
Feature activation-2.67e+00

Pos logit contributions
cy+0.022
sc+0.020
 mixture+0.020
 tin+0.019
 Of+0.019
Neg logit contributions
 strangers-0.018
 shouldn-0.016
 tresp-0.016
unts-0.016
 never-0.016
TokenYes
Token ID5297
Feature activation+1.14e+01

Pos logit contributions
 strangers+0.161
Days+0.152
 never+0.149
 understand+0.146
 respected+0.144
Neg logit contributions
 up-0.114
cy-0.114
 onto-0.112
 down-0.111
 mixture-0.109
Token!
Token ID0
Feature activation-7.96e-01

Pos logit contributions
 Of+0.542
cy+0.535
 girl+0.505
sc+0.497
 Sure+0.484
Neg logit contributions
 strangers-0.745
 tresp-0.675
vern-0.647
 supposed-0.625
 cruel-0.620
Token Of
Token ID3226
Feature activation+1.44e+01

Pos logit contributions
 strangers+0.048
 tresp+0.043
isdom+0.043
 shouldn+0.042
vern+0.041
Neg logit contributions
cy-0.036
sc-0.034
 tin-0.034
 mixture-0.034
 girl-0.032
Token course
Token ID1781
Feature activation-1.83e+00

Pos logit contributions
 Of+0.728
cy+0.710
 girl+0.701
sc+0.662
 onto+0.642
Neg logit contributions
 strangers-0.848
 tresp-0.726
vern-0.724
 supposed-0.709
 hated-0.708
Token,"
Token ID553
Feature activation-3.08e-01

Pos logit contributions
 strangers+0.113
 tresp+0.102
vern+0.096
 cruel+0.092
 supposed+0.090
Neg logit contributions
cy-0.094
 Of-0.093
sc-0.089
 Sure-0.085
 girl-0.085
Token he
Token ID339
Feature activation+1.86e+00

Pos logit contributions
 strangers+0.016
 tresp+0.014
 cruel+0.013
 understand+0.013
 shouldn+0.013
Neg logit contributions
cy-0.017
 Of-0.016
umm-0.016
sc-0.016
suit-0.016
Token said
Token ID531
Feature activation+4.14e+00

Pos logit contributions
cy+0.106
 Of+0.100
 Sure+0.093
sc+0.093
 mixture+0.091
Neg logit contributions
 strangers-0.102
 tresp-0.094
 cruel-0.088
vern-0.088
 never-0.086
Token.
Token ID13
Feature activation+4.07e-01

Pos logit contributions
cy+0.251
 Of+0.228
sc+0.225
 girl+0.214
 Sure+0.212
Neg logit contributions
 strangers-0.215
vern-0.197
 tresp-0.191
 understand-0.189
 never-0.181
Token a
Token ID257
Feature activation+1.33e+00

Pos logit contributions
 strangers+0.232
vern+0.203
 tresp+0.200
unts+0.193
isdom+0.189
Neg logit contributions
 Of-0.222
 girl-0.219
cy-0.216
 up-0.212
 down-0.206
Token good
Token ID922
Feature activation+2.37e+00

Pos logit contributions
 girl+0.076
cy+0.075
 Of+0.074
sc+0.070
 Sure+0.068
Neg logit contributions
 strangers-0.073
 tresp-0.063
vern-0.061
isdom-0.059
 supposed-0.058
Token brother
Token ID3956
Feature activation-1.60e+00

Pos logit contributions
 Of+0.132
sc+0.128
cy+0.127
 Sure+0.121
 onto+0.119
Neg logit contributions
 strangers-0.137
 tresp-0.121
unts-0.115
 enemies-0.112
 cruel-0.111
Token too
Token ID1165
Feature activation-1.72e-01

Pos logit contributions
 strangers+0.109
 tresp+0.100
vern+0.097
 supposed+0.092
 cruel+0.092
Neg logit contributions
cy-0.069
 Of-0.068
 girl-0.066
sc-0.065
 Sure-0.059
Token.
Token ID13
Feature activation-6.20e-01

Pos logit contributions
 strangers+0.013
 tresp+0.012
vern+0.012
Days+0.012
isdom+0.012
Neg logit contributions
 Of-0.005
 girl-0.005
cy-0.005
sc-0.005
 down-0.005
Token Of
Token ID3226
Feature activation+1.43e+01

Pos logit contributions
 strangers+0.041
 tresp+0.038
 cruel+0.035
isdom+0.035
vern+0.034
Neg logit contributions
cy-0.028
 mixture-0.026
sc-0.026
 girl-0.025
 tin-0.024
Token course
Token ID1781
Feature activation-1.99e+00

Pos logit contributions
 girl+0.749
cy+0.746
 Of+0.744
sc+0.661
 tin+0.652
Neg logit contributions
 strangers-0.818
 tresp-0.736
vern-0.730
 supposed-0.712
cod-0.683
Token we
Token ID356
Feature activation+8.25e-01

Pos logit contributions
 strangers+0.122
 tresp+0.108
vern+0.100
 cruel+0.099
unts+0.094
Neg logit contributions
cy-0.104
 Of-0.103
sc-0.100
 Sure-0.095
 girl-0.093
Token can
Token ID460
Feature activation-4.94e+00

Pos logit contributions
cy+0.036
 girl+0.033
 down+0.030
 up+0.029
sc+0.028
Neg logit contributions
 strangers-0.059
vern-0.053
 tresp-0.051
opl-0.051
cod-0.051
Token still
Token ID991
Feature activation-2.69e+00

Pos logit contributions
 strangers+0.318
 tresp+0.294
 cruel+0.271
vern+0.268
 supposed+0.267
Neg logit contributions
cy-0.247
 Of-0.235
 up-0.223
 girl-0.221
 down-0.211
Token be
Token ID307
Feature activation+1.44e+00

Pos logit contributions
 strangers+0.179
 tresp+0.165
vern+0.156
 supposed+0.153
 cruel+0.152
Neg logit contributions
cy-0.128
 Of-0.121
 girl-0.116
sc-0.107
 down-0.107
Token are
Token ID389
Feature activation-4.24e+00

Pos logit contributions
cy+0.277
 girl+0.263
sc+0.251
 fits+0.250
 Of+0.244
Neg logit contributions
 strangers-0.305
vern-0.267
 tresp-0.262
Days-0.252
isdom-0.248
Token my
Token ID616
Feature activation+2.79e+00

Pos logit contributions
 strangers+0.293
 tresp+0.263
vern+0.261
unts+0.247
cod+0.244
Neg logit contributions
 Of-0.177
cy-0.173
 girl-0.170
 up-0.156
sc-0.155
Token best
Token ID1266
Feature activation+6.19e+00

Pos logit contributions
 Of+0.142
cy+0.140
sc+0.135
 Sure+0.129
 onto+0.123
Neg logit contributions
 strangers-0.175
 tresp-0.159
vern-0.152
 cruel-0.144
 supposed-0.141
Token friend
Token ID1545
Feature activation+2.98e+00

Pos logit contributions
 Of+0.322
cy+0.321
sc+0.306
 Sure+0.293
 girl+0.284
Neg logit contributions
 strangers-0.378
 tresp-0.343
vern-0.321
 supposed-0.308
unts-0.307
Token.
Token ID13
Feature activation-5.11e-01

Pos logit contributions
cy+0.131
 Of+0.129
 girl+0.123
sc+0.121
 Sure+0.113
Neg logit contributions
 strangers-0.204
 tresp-0.185
vern-0.180
 cruel-0.172
 supposed-0.170
Token Of
Token ID3226
Feature activation+1.43e+01

Pos logit contributions
 strangers+0.033
 tresp+0.030
isdom+0.028
unts+0.027
vern+0.027
Neg logit contributions
cy-0.024
 mixture-0.023
 tin-0.022
sc-0.021
 girl-0.021
Token course
Token ID1781
Feature activation-2.04e+00

Pos logit contributions
cy+0.760
 Of+0.750
 girl+0.748
sc+0.672
 tin+0.660
Neg logit contributions
 strangers-0.815
 tresp-0.724
vern-0.722
 supposed-0.694
cod-0.678
Token I
Token ID314
Feature activation+1.16e+00

Pos logit contributions
 strangers+0.123
 tresp+0.109
vern+0.101
 cruel+0.099
 supposed+0.095
Neg logit contributions
cy-0.107
 Of-0.107
sc-0.103
 Sure-0.099
 girl-0.096
Token include
Token ID2291
Feature activation+1.12e+00

Pos logit contributions
cy+0.056
 girl+0.050
sc+0.049
 Of+0.048
 Sure+0.044
Neg logit contributions
 strangers-0.082
 tresp-0.070
vern-0.068
 cruel-0.066
isdom-0.066
Token you
Token ID345
Feature activation+1.44e-02

Pos logit contributions
cy+0.057
 Of+0.057
sc+0.054
 Sure+0.053
 girl+0.053
Neg logit contributions
 strangers-0.070
 tresp-0.062
vern-0.059
 cruel-0.056
 supposed-0.056
Token in
Token ID287
Feature activation+2.48e+00

Pos logit contributions
cy+0.001
 Of+0.001
 girl+0.001
sc+0.001
 Sure+0.001
Neg logit contributions
 strangers-0.001
 tresp-0.001
vern-0.001
 cruel-0.001
unts-0.001
Token his
Token ID465
Feature activation+8.89e-01

Pos logit contributions
cy+0.157
 Of+0.151
 girl+0.143
sc+0.142
 Sure+0.141
Neg logit contributions
 strangers-0.163
 tresp-0.147
 supposed-0.132
vern-0.130
eping-0.127
Token fish
Token ID5916
Feature activation-2.60e-01

Pos logit contributions
 Of+0.042
cy+0.042
sc+0.039
 girl+0.039
 Sure+0.038
Neg logit contributions
 strangers-0.058
 tresp-0.053
vern-0.050
 cruel-0.048
 supposed-0.048
Token with
Token ID351
Feature activation+9.56e+00

Pos logit contributions
 strangers+0.018
 tresp+0.016
vern+0.016
 supposed+0.015
 cruel+0.015
Neg logit contributions
 Of-0.011
cy-0.011
sc-0.010
 Sure-0.010
 girl-0.010
Token him
Token ID683
Feature activation-5.12e+00

Pos logit contributions
 Of+0.597
cy+0.591
sc+0.565
 onto+0.555
 girl+0.553
Neg logit contributions
 strangers-0.473
 tresp-0.422
vern-0.408
 cruel-0.383
 supposed-0.374
Token!
Token ID0
Feature activation-1.14e+00

Pos logit contributions
 strangers+0.342
 tresp+0.311
vern+0.301
 cruel+0.288
unts+0.285
Neg logit contributions
 Of-0.234
cy-0.233
sc-0.217
 girl-0.215
 Sure-0.209
Token Of
Token ID3226
Feature activation+1.43e+01

Pos logit contributions
 strangers+0.067
 tresp+0.060
unts+0.058
vern+0.056
 supposed+0.056
Neg logit contributions
cy-0.058
 girl-0.055
 Of-0.055
sc-0.054
 tin-0.052
Token course
Token ID1781
Feature activation-1.94e+00

Pos logit contributions
 Of+0.755
cy+0.742
 girl+0.735
sc+0.680
 onto+0.658
Neg logit contributions
 strangers-0.821
vern-0.745
 tresp-0.734
 supposed-0.705
unts-0.687
Token,
Token ID11
Feature activation+4.18e-01

Pos logit contributions
 strangers+0.121
 tresp+0.109
vern+0.102
 cruel+0.099
 supposed+0.098
Neg logit contributions
cy-0.098
 Of-0.098
sc-0.093
 girl-0.090
 Sure-0.089
Token it
Token ID340
Feature activation-4.47e-01

Pos logit contributions
cy+0.022
 Of+0.021
sc+0.021
 girl+0.020
 Sure+0.019
Neg logit contributions
 strangers-0.026
 tresp-0.023
vern-0.021
 cruel-0.021
 supposed-0.020
Token wasn
Token ID2492
Feature activation-3.19e+00

Pos logit contributions
 strangers+0.028
 tresp+0.025
vern+0.024
 cruel+0.023
 supposed+0.023
Neg logit contributions
 Of-0.023
cy-0.022
sc-0.021
 Sure-0.020
 girl-0.020
Token't
Token ID470
Feature activation-3.23e+00

Pos logit contributions
 strangers+0.206
 tresp+0.181
cod+0.180
isdom+0.178
 enemies+0.173
Neg logit contributions
 Of-0.151
 onto-0.149
sc-0.149
 up-0.141
cy-0.139
Token said
Token ID531
Feature activation+3.92e+00

Pos logit contributions
 strangers+0.136
 tresp+0.116
 hated+0.115
 cruel+0.114
 never+0.109
Neg logit contributions
sc-0.139
cy-0.138
 Of-0.134
 Sure-0.124
suit-0.122
Token,
Token ID11
Feature activation+5.48e-01

Pos logit contributions
cy+0.194
 Of+0.194
sc+0.182
 girl+0.180
 Sure+0.176
Neg logit contributions
 strangers-0.247
 tresp-0.223
vern-0.213
 cruel-0.203
 supposed-0.201
Token "
Token ID366
Feature activation-2.84e+00

Pos logit contributions
 Of+0.026
cy+0.026
sc+0.024
 girl+0.024
 Sure+0.024
Neg logit contributions
 strangers-0.035
 tresp-0.032
vern-0.031
 cruel-0.029
 supposed-0.029
TokenYes
Token ID5297
Feature activation+1.13e+01

Pos logit contributions
 strangers+0.182
Days+0.174
 never+0.171
 understand+0.167
vern+0.164
Neg logit contributions
 up-0.105
cy-0.104
 onto-0.100
 down-0.099
 into-0.095
Token!
Token ID0
Feature activation-1.01e+00

Pos logit contributions
 Of+0.533
cy+0.527
 girl+0.495
sc+0.490
 Sure+0.473
Neg logit contributions
 strangers-0.742
 tresp-0.673
vern-0.647
 supposed-0.622
 cruel-0.618
Token Of
Token ID3226
Feature activation+1.43e+01

Pos logit contributions
 strangers+0.062
 tresp+0.056
isdom+0.055
 shouldn+0.054
unts+0.053
Neg logit contributions
cy-0.042
 mixture-0.039
sc-0.039
 girl-0.038
 tin-0.038
Token course
Token ID1781
Feature activation-1.93e+00

Pos logit contributions
 Of+0.711
cy+0.707
 girl+0.690
sc+0.642
 tin+0.624
Neg logit contributions
 strangers-0.848
 tresp-0.742
vern-0.738
ache-0.718
 supposed-0.713
Token.
Token ID13
Feature activation+1.24e-01

Pos logit contributions
 strangers+0.125
 tresp+0.113
vern+0.107
 cruel+0.103
 supposed+0.102
Neg logit contributions
cy-0.093
 Of-0.092
sc-0.087
 girl-0.084
 Sure-0.084
Token I
Token ID314
Feature activation+1.30e+00

Pos logit contributions
cy+0.005
 girl+0.005
 mixture+0.005
 tin+0.005
sc+0.005
Neg logit contributions
 strangers-0.008
 tresp-0.007
isdom-0.007
 shouldn-0.007
 never-0.007
Token have
Token ID423
Feature activation-3.38e+00

Pos logit contributions
cy+0.072
 Of+0.066
 girl+0.065
sc+0.065
 Sure+0.062
Neg logit contributions
 strangers-0.083
 tresp-0.070
vern-0.067
 cruel-0.065
 supposed-0.062
Token a
Token ID257
Feature activation+1.58e+00

Pos logit contributions
 strangers+0.248
 tresp+0.226
vern+0.220
unts+0.212
 cruel+0.211
Neg logit contributions
 Of-0.131
cy-0.127
 girl-0.121
sc-0.121
 Sure-0.114
Token you
Token ID345
Feature activation-5.09e-02

Pos logit contributions
 Of+0.001
cy+0.001
 girl+0.001
sc+0.001
 Sure+0.001
Neg logit contributions
 strangers-0.002
 tresp-0.002
vern-0.002
 supposed-0.002
unts-0.002
Token are
Token ID389
Feature activation-4.27e+00

Pos logit contributions
 strangers+0.003
 tresp+0.002
vern+0.002
 cruel+0.002
cod+0.002
Neg logit contributions
 Of-0.003
cy-0.003
 girl-0.003
sc-0.003
 Sure-0.003
Token very
Token ID845
Feature activation-1.08e+00

Pos logit contributions
 strangers+0.252
 tresp+0.224
vern+0.214
 cruel+0.203
unts+0.201
Neg logit contributions
 Of-0.232
cy-0.231
 girl-0.217
sc-0.217
 Sure-0.211
Token kind
Token ID1611
Feature activation-3.91e+00

Pos logit contributions
 strangers+0.049
 tresp+0.043
vern+0.041
 cruel+0.038
 supposed+0.038
Neg logit contributions
cy-0.072
 Of-0.072
sc-0.070
 Sure-0.068
 girl-0.068
Token.
Token ID13
Feature activation-5.40e-01

Pos logit contributions
 strangers+0.225
 tresp+0.196
vern+0.183
unts+0.178
 supposed+0.174
Neg logit contributions
 Of-0.218
cy-0.218
 Sure-0.206
sc-0.205
 mixture-0.196
Token Of
Token ID3226
Feature activation+1.43e+01

Pos logit contributions
 strangers+0.035
 tresp+0.032
isdom+0.030
vern+0.029
unts+0.029
Neg logit contributions
cy-0.024
 mixture-0.023
sc-0.023
 girl-0.022
 tin-0.022
Token course
Token ID1781
Feature activation-2.06e+00

Pos logit contributions
cy+0.761
 Of+0.754
 girl+0.743
sc+0.682
 tin+0.658
Neg logit contributions
 strangers-0.804
 tresp-0.715
vern-0.708
 supposed-0.686
ache-0.674
Token you
Token ID345
Feature activation-3.58e-02

Pos logit contributions
 strangers+0.127
 tresp+0.113
vern+0.105
 cruel+0.102
 supposed+0.099
Neg logit contributions
cy-0.107
 Of-0.106
sc-0.102
 Sure-0.098
 girl-0.095
Token can
Token ID460
Feature activation-5.07e+00

Pos logit contributions
 strangers+0.002
 tresp+0.002
vern+0.002
Days+0.002
eping+0.002
Neg logit contributions
cy-0.002
 girl-0.002
sc-0.002
 Of-0.002
 up-0.001
Token touch
Token ID3638
Feature activation+2.44e+00

Pos logit contributions
 strangers+0.334
 tresp+0.306
 cruel+0.290
vern+0.285
 enemies+0.279
Neg logit contributions
cy-0.251
 Of-0.239
 girl-0.222
 up-0.216
 onto-0.214
Token it
Token ID340
Feature activation-6.33e-01

Pos logit contributions
 Of+0.117
cy+0.116
sc+0.109
 girl+0.107
 Sure+0.106
Neg logit contributions
 strangers-0.160
 tresp-0.143
vern-0.137
 cruel-0.132
 supposed-0.130
TokenYou
Token ID1639
Feature activation+2.94e+00

Pos logit contributions
 strangers+0.166
 never+0.151
 hated+0.151
 cruel+0.149
vern+0.146
Neg logit contributions
cy-0.153
 onto-0.145
 down-0.144
 Of-0.143
 girl-0.139
Token can
Token ID460
Feature activation-5.05e+00

Pos logit contributions
cy+0.162
 girl+0.156
 Of+0.156
sc+0.145
 down+0.143
Neg logit contributions
 strangers-0.173
 tresp-0.149
vern-0.148
cod-0.140
Days-0.140
Token,
Token ID11
Feature activation+2.85e-01

Pos logit contributions
 strangers+0.311
 tresp+0.282
vern+0.264
 cruel+0.260
 supposed+0.256
Neg logit contributions
cy-0.268
 Of-0.263
sc-0.241
 girl-0.238
 Sure-0.234
Token Max
Token ID5436
Feature activation-2.88e+00

Pos logit contributions
 Of+0.012
cy+0.012
 girl+0.011
sc+0.011
 Sure+0.010
Neg logit contributions
 strangers-0.020
 tresp-0.018
vern-0.018
 supposed-0.017
unts-0.017
Token.
Token ID13
Feature activation-2.35e-01

Pos logit contributions
 strangers+0.188
 tresp+0.170
vern+0.162
 cruel+0.155
 supposed+0.154
Neg logit contributions
 Of-0.138
cy-0.137
sc-0.128
 girl-0.126
 Sure-0.124
Token Of
Token ID3226
Feature activation+1.42e+01

Pos logit contributions
 strangers+0.015
 tresp+0.014
isdom+0.013
 shouldn+0.013
 cruel+0.013
Neg logit contributions
cy-0.010
 girl-0.010
sc-0.009
 mixture-0.009
 tin-0.009
Token course
Token ID1781
Feature activation-2.09e+00

Pos logit contributions
 Of+0.738
cy+0.730
 girl+0.725
sc+0.656
 tin+0.641
Neg logit contributions
 strangers-0.824
vern-0.723
 tresp-0.722
 supposed-0.695
cod-0.684
Token you
Token ID345
Feature activation-3.32e-02

Pos logit contributions
 strangers+0.136
 tresp+0.122
vern+0.115
 cruel+0.112
 supposed+0.109
Neg logit contributions
cy-0.102
 Of-0.100
sc-0.096
 girl-0.092
 Sure-0.091
Token can
Token ID460
Feature activation-5.04e+00

Pos logit contributions
 strangers+0.002
 tresp+0.002
vern+0.002
cod+0.002
eping+0.002
Neg logit contributions
cy-0.002
sc-0.001
 girl-0.001
 Of-0.001
 up-0.001
Token,
Token ID11
Feature activation+2.66e-01

Pos logit contributions
 strangers+0.328
 tresp+0.297
 cruel+0.278
vern+0.277
 supposed+0.268
Neg logit contributions
cy-0.252
 Of-0.243
 girl-0.225
sc-0.224
 up-0.220
Token it
Token ID340
Feature activation-5.94e-01

Pos logit contributions
 Of+0.012
cy+0.012
 girl+0.011
sc+0.011
 Sure+0.010
Neg logit contributions
 strangers-0.018
 tresp-0.017
vern-0.016
 supposed-0.015
 cruel-0.015
Token said
Token ID531
Feature activation+3.78e+00

Pos logit contributions
 strangers+0.080
 tresp+0.072
vern+0.069
 cruel+0.066
 supposed+0.066
Neg logit contributions
 Of-0.058
cy-0.058
sc-0.054
 girl-0.054
 Sure-0.052
Token,
Token ID11
Feature activation+3.56e-01

Pos logit contributions
cy+0.191
 Of+0.191
sc+0.179
 girl+0.177
 Sure+0.173
Neg logit contributions
 strangers-0.235
 tresp-0.211
vern-0.202
 cruel-0.193
 supposed-0.190
Token "
Token ID366
Feature activation-2.96e+00

Pos logit contributions
cy+0.018
 Of+0.018
sc+0.017
 girl+0.017
 Sure+0.016
Neg logit contributions
 strangers-0.022
 tresp-0.019
vern-0.019
 cruel-0.018
unts-0.018
TokenYes
Token ID5297
Feature activation+1.12e+01

Pos logit contributions
 strangers+0.171
 understand+0.151
 never+0.149
Days+0.147
cod+0.144
Neg logit contributions
 up-0.136
 down-0.130
 onto-0.129
cy-0.128
 Of-0.128
Token!
Token ID0
Feature activation-1.31e+00

Pos logit contributions
 Of+0.501
cy+0.493
 girl+0.469
sc+0.451
 Sure+0.441
Neg logit contributions
 strangers-0.759
 tresp-0.690
vern-0.666
 supposed-0.647
 cruel-0.638
Token Of
Token ID3226
Feature activation+1.42e+01

Pos logit contributions
 strangers+0.082
 tresp+0.075
isdom+0.074
 shouldn+0.071
vern+0.070
Neg logit contributions
cy-0.055
sc-0.053
 girl-0.050
 tin-0.049
 mixture-0.049
Token course
Token ID1781
Feature activation-2.09e+00

Pos logit contributions
 Of+0.686
cy+0.671
 girl+0.664
sc+0.608
 onto+0.602
Neg logit contributions
 strangers-0.857
vern-0.752
 tresp-0.738
ache-0.735
 hated-0.728
Token you
Token ID345
Feature activation-2.09e-02

Pos logit contributions
 strangers+0.129
 tresp+0.116
vern+0.109
 cruel+0.105
 supposed+0.104
Neg logit contributions
cy-0.107
 Of-0.107
sc-0.101
 girl-0.097
 Sure-0.097
Token can
Token ID460
Feature activation-5.07e+00

Pos logit contributions
 strangers+0.001
vern+0.001
 tresp+0.001
cod+0.001
eping+0.001
Neg logit contributions
cy-0.001
 girl-0.001
sc-0.001
 tin-0.001
 Of-0.001
Token borrow
Token ID8804
Feature activation-2.20e+00

Pos logit contributions
 strangers+0.315
 tresp+0.281
 cruel+0.262
vern+0.261
 supposed+0.252
Neg logit contributions
cy-0.265
 Of-0.263
sc-0.246
 girl-0.242
 Sure-0.236
Token some
Token ID617
Feature activation+3.18e+00

Pos logit contributions
 strangers+0.152
 tresp+0.139
vern+0.133
 cruel+0.128
 supposed+0.128
Neg logit contributions
 Of-0.096
cy-0.095
sc-0.088
 girl-0.087
 Sure-0.084
Token could
Token ID714
Feature activation-5.22e+00

Pos logit contributions
cy+0.071
 Of+0.070
 girl+0.069
sc+0.068
 Sure+0.065
Neg logit contributions
 strangers-0.089
vern-0.078
 tresp-0.078
 cruel-0.071
unts-0.071
Token hardly
Token ID8941
Feature activation-4.12e+00

Pos logit contributions
 strangers+0.302
 tresp+0.278
cod+0.269
ills+0.253
 cruel+0.252
Neg logit contributions
 Of-0.293
 onto-0.277
cy-0.269
 Sure-0.267
 down-0.265
Token stand
Token ID1302
Feature activation+3.06e+00

Pos logit contributions
 strangers+0.226
 tresp+0.197
vern+0.188
 cruel+0.179
 supposed+0.177
Neg logit contributions
cy-0.238
 Of-0.238
sc-0.226
 girl-0.224
 Sure-0.218
Token it
Token ID340
Feature activation-6.11e-01

Pos logit contributions
cy+0.073
 Of+0.072
 girl+0.062
sc+0.061
 Sure+0.056
Neg logit contributions
 strangers-0.271
 tresp-0.252
vern-0.246
unts-0.237
 cruel-0.236
Token!
Token ID0
Feature activation-1.27e+00

Pos logit contributions
 strangers+0.038
 tresp+0.033
vern+0.032
 supposed+0.032
 cruel+0.031
Neg logit contributions
 Of-0.031
cy-0.030
 girl-0.028
 Sure-0.028
sc-0.027
Token Of
Token ID3226
Feature activation+1.42e+01

Pos logit contributions
 strangers+0.074
 hated+0.061
 tresp+0.060
unts+0.059
isdom+0.059
Neg logit contributions
cy-0.069
sc-0.067
 Of-0.061
cer-0.060
 mixture-0.060
Token course
Token ID1781
Feature activation-2.10e+00

Pos logit contributions
 Of+0.768
cy+0.767
 girl+0.753
sc+0.696
 Sure+0.671
Neg logit contributions
 strangers-0.793
 tresp-0.718
vern-0.711
 supposed-0.681
unts-0.657
Token she
Token ID673
Feature activation+1.44e+00

Pos logit contributions
 strangers+0.123
 tresp+0.108
vern+0.100
 cruel+0.098
 supposed+0.097
Neg logit contributions
cy-0.114
 Of-0.114
sc-0.112
 Sure-0.104
 tin-0.103
Token wanted
Token ID2227
Feature activation-2.84e+00

Pos logit contributions
cy+0.075
 girl+0.070
 Of+0.070
sc+0.067
 Sure+0.066
Neg logit contributions
 strangers-0.093
vern-0.081
 tresp-0.080
 cruel-0.075
unts-0.073
Token to
Token ID284
Feature activation-1.01e+00

Pos logit contributions
 strangers+0.189
 tresp+0.171
vern+0.164
 cruel+0.157
 supposed+0.156
Neg logit contributions
 Of-0.134
cy-0.134
sc-0.124
 girl-0.123
 Sure-0.120
Token go
Token ID467
Feature activation-2.64e+00

Pos logit contributions
 strangers+0.066
 tresp+0.060
 cruel+0.058
vern+0.057
cod+0.056
Neg logit contributions
 Of-0.048
cy-0.046
 girl-0.044
 onto-0.042
 down-0.041
Token ride
Token ID6594
Feature activation-2.06e+00

Pos logit contributions
 strangers+0.049
 tresp+0.046
vern+0.044
 supposed+0.044
 cruel+0.043
Neg logit contributions
 Of-0.035
cy-0.034
 girl-0.032
 tin-0.031
sc-0.030
Token in
Token ID287
Feature activation+2.62e+00

Pos logit contributions
 strangers+0.137
 tresp+0.118
vern+0.111
 cruel+0.107
 enemies+0.105
Neg logit contributions
 Of-0.095
cy-0.092
 Sure-0.088
sc-0.088
 mixture-0.086
Token the
Token ID262
Feature activation-9.95e-01

Pos logit contributions
 Of+0.122
cy+0.122
sc+0.113
 girl+0.113
 Sure+0.109
Neg logit contributions
 strangers-0.173
 tresp-0.157
vern-0.151
 cruel-0.145
 supposed-0.143
Token wagon
Token ID31860
Feature activation-4.45e+00

Pos logit contributions
 strangers+0.062
 tresp+0.055
vern+0.053
 cruel+0.050
 supposed+0.050
Neg logit contributions
 Of-0.051
cy-0.051
sc-0.048
 girl-0.047
 Sure-0.046
Token.
Token ID13
Feature activation+2.39e-03

Pos logit contributions
 strangers+0.275
 tresp+0.239
vern+0.230
 cruel+0.218
 never+0.217
Neg logit contributions
 Of-0.222
cy-0.213
 Sure-0.201
sc-0.201
 girl-0.197
Token Of
Token ID3226
Feature activation+1.41e+01

Pos logit contributions
cy+0.000
sc+0.000
 girl+0.000
 mixture+0.000
 Of+0.000
Neg logit contributions
 strangers-0.000
 tresp-0.000
unts-0.000
vern-0.000
isdom-0.000
Token course
Token ID1781
Feature activation-2.14e+00

Pos logit contributions
 Of+0.795
cy+0.783
 girl+0.754
sc+0.706
 Sure+0.698
Neg logit contributions
 strangers-0.783
 tresp-0.708
vern-0.681
 supposed-0.664
unts-0.641
Token,
Token ID11
Feature activation+4.91e-01

Pos logit contributions
 strangers+0.124
 tresp+0.108
 never+0.099
 cruel+0.095
vern+0.094
Neg logit contributions
cy-0.115
sc-0.114
 Of-0.111
 mixture-0.106
 Sure-0.105
Token Molly
Token ID30236
Feature activation+7.34e+00

Pos logit contributions
cy+0.024
sc+0.023
 mixture+0.022
 Of+0.021
umm+0.021
Neg logit contributions
 strangers-0.031
 tresp-0.027
 never-0.026
 understand-0.025
 cruel-0.024
Token and
Token ID290
Feature activation-2.64e+00

Pos logit contributions
cy+0.335
 Of+0.330
 girl+0.314
sc+0.304
 Sure+0.297
Neg logit contributions
 strangers-0.497
 tresp-0.449
vern-0.433
 supposed-0.415
 cruel-0.413
Token Sam
Token ID3409
Feature activation-3.16e+00

Pos logit contributions
 strangers+0.162
 tresp+0.140
vern+0.126
 cruel+0.125
isdom+0.123
Neg logit contributions
sc-0.139
cy-0.139
 Of-0.137
 Sure-0.127
 mixture-0.126
Token said
Token ID531
Feature activation+3.66e+00

Pos logit contributions
 Of+0.066
cy+0.066
 girl+0.063
sc+0.061
 Sure+0.060
Neg logit contributions
 strangers-0.093
 tresp-0.084
vern-0.082
 supposed-0.077
 cruel-0.075
Token,
Token ID11
Feature activation+3.05e-01

Pos logit contributions
cy+0.190
 Of+0.186
sc+0.177
 girl+0.174
 Sure+0.170
Neg logit contributions
 strangers-0.224
 tresp-0.202
vern-0.193
 cruel-0.185
 supposed-0.180
Token "
Token ID366
Feature activation-3.09e+00

Pos logit contributions
 Of+0.014
cy+0.014
sc+0.013
 girl+0.013
 Sure+0.013
Neg logit contributions
 strangers-0.020
 tresp-0.018
vern-0.018
 cruel-0.017
 supposed-0.017
TokenYes
Token ID5297
Feature activation+1.11e+01

Pos logit contributions
 strangers+0.181
 understand+0.159
 never+0.158
Days+0.155
 respected+0.155
Neg logit contributions
cy-0.137
 up-0.134
 Of-0.132
 onto-0.132
sc-0.131
Token!
Token ID0
Feature activation-1.26e+00

Pos logit contributions
 Of+0.514
cy+0.504
 girl+0.479
sc+0.458
 Sure+0.452
Neg logit contributions
 strangers-0.736
 tresp-0.665
vern-0.645
 supposed-0.625
unts-0.618
Token Of
Token ID3226
Feature activation+1.41e+01

Pos logit contributions
 strangers+0.079
 tresp+0.072
isdom+0.069
 shouldn+0.067
 cruel+0.067
Neg logit contributions
cy-0.057
sc-0.056
 mixture-0.052
 girl-0.052
 tin-0.051
Token course
Token ID1781
Feature activation-2.19e+00

Pos logit contributions
 Of+0.701
cy+0.691
 girl+0.676
 onto+0.615
 tin+0.611
Neg logit contributions
 strangers-0.844
vern-0.740
 tresp-0.723
 supposed-0.713
 hated-0.709
Token."
Token ID526
Feature activation-5.01e-01

Pos logit contributions
 strangers+0.137
 tresp+0.124
vern+0.116
 cruel+0.112
 supposed+0.110
Neg logit contributions
cy-0.111
 Of-0.110
sc-0.105
 girl-0.101
 Sure-0.101
Token
Token ID198
Feature activation+6.24e-01

Pos logit contributions
 strangers+0.022
unts+0.019
 tresp+0.019
 never+0.019
 understand+0.018
Neg logit contributions
cy-0.031
 mixture-0.028
sc-0.028
fl-0.027
 girl-0.027
Token
Token ID198
Feature activation+6.21e-01

Pos logit contributions
 Of+0.025
cy+0.024
sc+0.023
 girl+0.022
 Sure+0.022
Neg logit contributions
 strangers-0.046
 tresp-0.042
vern-0.040
 cruel-0.039
 supposed-0.039
TokenThe
Token ID464
Feature activation-3.18e+00

Pos logit contributions
 Of+0.034
cy+0.034
sc+0.032
 girl+0.032
 Sure+0.031
Neg logit contributions
 strangers-0.036
 tresp-0.032
vern-0.030
 cruel-0.029
 supposed-0.029
Token friends
Token ID2460
Feature activation-7.81e-01

Pos logit contributions
 girl+0.045
 Of+0.042
cy+0.042
 moment+0.039
 mixture+0.039
Neg logit contributions
 strangers-0.053
 tresp-0.050
cod-0.048
isdom-0.047
unts-0.047
Token to
Token ID284
Feature activation-1.09e+00

Pos logit contributions
 strangers+0.054
 tresp+0.049
vern+0.047
 cruel+0.046
unts+0.045
Neg logit contributions
cy-0.034
 Of-0.034
sc-0.032
 girl-0.031
 Sure-0.030
Token go
Token ID467
Feature activation-2.78e+00

Pos logit contributions
 strangers+0.067
 cruel+0.062
 tresp+0.062
 hated+0.062
cod+0.061
Neg logit contributions
cy-0.048
 onto-0.047
 up-0.046
 down-0.046
 girl-0.045
Token home
Token ID1363
Feature activation+2.68e+00

Pos logit contributions
 strangers+0.204
 tresp+0.186
vern+0.179
 cruel+0.172
 supposed+0.171
Neg logit contributions
 Of-0.110
cy-0.109
sc-0.101
 girl-0.099
 Sure-0.097
Token.
Token ID13
Feature activation-1.25e-01

Pos logit contributions
cy+0.115
 Of+0.115
 girl+0.106
sc+0.106
 Sure+0.102
Neg logit contributions
 strangers-0.187
 tresp-0.170
vern-0.162
 cruel-0.157
unts-0.155
Token Of
Token ID3226
Feature activation+1.41e+01

Pos logit contributions
 strangers+0.007
 tresp+0.007
vern+0.006
unts+0.006
 hated+0.006
Neg logit contributions
cy-0.006
sc-0.006
 girl-0.006
 Of-0.006
 tin-0.006
Token course
Token ID1781
Feature activation-2.16e+00

Pos logit contributions
cy+0.732
 girl+0.728
 Of+0.726
sc+0.653
 Sure+0.630
Neg logit contributions
 strangers-0.819
vern-0.745
 tresp-0.740
 supposed-0.723
unts-0.686
Token,
Token ID11
Feature activation+3.17e-01

Pos logit contributions
 strangers+0.133
 tresp+0.119
vern+0.111
 cruel+0.108
 supposed+0.105
Neg logit contributions
cy-0.111
 Of-0.111
sc-0.106
 girl-0.102
 Sure-0.101
Token they
Token ID484
Feature activation-2.65e-01

Pos logit contributions
cy+0.017
sc+0.016
 Of+0.016
 Sure+0.015
 girl+0.015
Neg logit contributions
 strangers-0.019
 tresp-0.017
 never-0.015
 cruel-0.015
vern-0.015
Token had
Token ID550
Feature activation-4.73e+00

Pos logit contributions
 strangers+0.017
 tresp+0.015
vern+0.015
cod+0.015
 cruel+0.015
Neg logit contributions
cy-0.014
 girl-0.013
 down-0.013
 onto-0.012
 up-0.012
Token a
Token ID257
Feature activation+1.40e+00

Pos logit contributions
 strangers+0.337
 tresp+0.297
vern+0.287
 cruel+0.284
cod+0.281
Neg logit contributions
 Of-0.197
cy-0.196
 girl-0.184
sc-0.182
 Sure-0.180
Token my
Token ID616
Feature activation+2.73e+00

Pos logit contributions
 Of+0.014
cy+0.013
sc+0.013
 girl+0.012
 Sure+0.012
Neg logit contributions
 strangers-0.019
 tresp-0.017
vern-0.016
 cruel-0.015
 supposed-0.015
Token cute
Token ID13779
Feature activation-2.41e+00

Pos logit contributions
cy+0.148
sc+0.146
 Of+0.146
 girl+0.132
 Sure+0.132
Neg logit contributions
 strangers-0.156
 tresp-0.141
vern-0.135
 cruel-0.128
 hated-0.127
Token little
Token ID1310
Feature activation+1.98e-01

Pos logit contributions
 strangers+0.161
 tresp+0.144
vern+0.137
 supposed+0.132
 cruel+0.132
Neg logit contributions
 Of-0.111
cy-0.109
sc-0.106
 Sure-0.099
 girl-0.098
Token girl
Token ID2576
Feature activation+1.06e+01

Pos logit contributions
sc+0.007
 Of+0.007
antly+0.006
ipt+0.006
iffs+0.006
Neg logit contributions
 strangers-0.015
 tresp-0.013
 mean-0.013
 enemies-0.012
 liar-0.012
Token!
Token ID0
Feature activation-1.28e+00

Pos logit contributions
cy+0.507
 Of+0.504
 girl+0.468
sc+0.467
 Sure+0.453
Neg logit contributions
 strangers-0.689
 tresp-0.619
vern-0.597
 cruel-0.571
unts-0.561
Token Of
Token ID3226
Feature activation+1.41e+01

Pos logit contributions
 strangers+0.075
isdom+0.070
 shouldn+0.070
 tresp+0.069
 never+0.068
Neg logit contributions
cy-0.054
 mixture-0.053
 tin-0.052
sc-0.051
 up-0.048
Token course
Token ID1781
Feature activation-2.19e+00

Pos logit contributions
cy+0.653
 girl+0.652
 Of+0.650
 tin+0.568
sc+0.567
Neg logit contributions
 strangers-0.868
vern-0.765
 tresp-0.765
ache-0.761
 supposed-0.754
Token you
Token ID345
Feature activation-9.24e-02

Pos logit contributions
 strangers+0.137
 tresp+0.123
vern+0.115
 cruel+0.111
 supposed+0.110
Neg logit contributions
cy-0.110
 Of-0.110
sc-0.106
 Sure-0.101
 girl-0.100
Token can
Token ID460
Feature activation-5.17e+00

Pos logit contributions
 strangers+0.007
 tresp+0.006
vern+0.006
cod+0.006
 cruel+0.005
Neg logit contributions
cy-0.004
 girl-0.004
sc-0.004
 Of-0.004
 up-0.004
Token have
Token ID423
Feature activation-3.74e+00

Pos logit contributions
 strangers+0.343
 tresp+0.309
 cruel+0.296
vern+0.285
cod+0.283
Neg logit contributions
cy-0.255
 Of-0.250
 girl-0.229
 onto-0.224
 Sure-0.223
Token a
Token ID257
Feature activation+1.34e+00

Pos logit contributions
 strangers+0.279
 tresp+0.262
vern+0.251
unts+0.247
 cruel+0.243
Neg logit contributions
 Of-0.137
cy-0.125
 girl-0.124
sc-0.120
 onto-0.118
Token they
Token ID484
Feature activation-2.37e-01

Pos logit contributions
cy+0.123
 Of+0.120
sc+0.115
 girl+0.110
 Sure+0.109
Neg logit contributions
 strangers-0.199
 tresp-0.177
vern-0.168
 cruel-0.164
 supposed-0.160
Token could
Token ID714
Feature activation-5.25e+00

Pos logit contributions
 strangers+0.015
vern+0.014
 tresp+0.014
opl+0.014
cod+0.014
Neg logit contributions
cy-0.012
 Of-0.011
 girl-0.011
 onto-0.010
ed-0.010
Token join
Token ID4654
Feature activation+3.03e+00

Pos logit contributions
 strangers+0.335
 tresp+0.308
cod+0.290
vern+0.289
 cruel+0.287
Neg logit contributions
cy-0.255
 Of-0.254
 onto-0.233
 up-0.231
sc-0.228
Token her
Token ID607
Feature activation-1.69e-01

Pos logit contributions
cy+0.144
 Of+0.144
sc+0.135
 girl+0.133
 Sure+0.133
Neg logit contributions
 strangers-0.199
 tresp-0.176
vern-0.166
 cruel-0.160
 supposed-0.159
Token.
Token ID13
Feature activation-8.38e-02

Pos logit contributions
 strangers+0.011
 tresp+0.010
vern+0.009
 supposed+0.009
 cruel+0.009
Neg logit contributions
 Of-0.008
cy-0.008
sc-0.008
 Sure-0.008
 girl-0.007
Token Of
Token ID3226
Feature activation+1.41e+01

Pos logit contributions
 strangers+0.005
unts+0.004
 hated+0.004
 tresp+0.004
vern+0.004
Neg logit contributions
cy-0.005
 tin-0.004
 girl-0.004
 mixture-0.004
sc-0.004
Token course
Token ID1781
Feature activation-2.24e+00

Pos logit contributions
 Of+0.850
cy+0.848
 girl+0.803
sc+0.801
 Sure+0.774
Neg logit contributions
 strangers-0.733
 tresp-0.648
vern-0.620
 supposed-0.583
 cruel-0.574
Token,
Token ID11
Feature activation+4.30e-01

Pos logit contributions
 strangers+0.138
 tresp+0.119
 cruel+0.108
 never+0.107
 hated+0.106
Neg logit contributions
cy-0.115
 Of-0.114
sc-0.110
 Sure-0.110
 tin-0.108
Token she
Token ID673
Feature activation+1.46e+00

Pos logit contributions
cy+0.024
ASH+0.024
 Sure+0.022
 tin+0.022
sc+0.022
Neg logit contributions
 strangers-0.025
 tresp-0.020
 never-0.020
 cruel-0.019
 mean-0.019
Token said
Token ID531
Feature activation+3.81e+00

Pos logit contributions
cy+0.076
 Of+0.074
 girl+0.072
sc+0.071
 Sure+0.068
Neg logit contributions
 strangers-0.090
 tresp-0.080
vern-0.077
 supposed-0.072
 cruel-0.072
Token yes
Token ID3763
Feature activation-2.79e-01

Pos logit contributions
 Of+0.199
cy+0.190
 girl+0.182
sc+0.182
 Sure+0.178
Neg logit contributions
 strangers-0.233
 tresp-0.209
vern-0.198
 supposed-0.191
unts-0.190
Token give
Token ID1577
Feature activation+3.83e+00

Pos logit contributions
 strangers+0.384
 tresp+0.344
vern+0.330
 cruel+0.310
 supposed+0.308
Neg logit contributions
 Of-0.374
cy-0.372
 girl-0.350
sc-0.349
 Sure-0.339
Token away
Token ID1497
Feature activation+7.40e+00

Pos logit contributions
 Of+0.137
cy+0.134
sc+0.125
 girl+0.120
 Sure+0.120
Neg logit contributions
 strangers-0.300
 tresp-0.271
vern-0.260
 cruel-0.253
 supposed-0.252
Token her
Token ID607
Feature activation-4.29e-01

Pos logit contributions
 Of+0.335
 girl+0.333
cy+0.333
 down+0.304
 up+0.298
Neg logit contributions
 strangers-0.460
vern-0.435
 tresp-0.434
unts-0.417
 supposed-0.413
Token things
Token ID1243
Feature activation+1.85e+00

Pos logit contributions
 strangers+0.030
 tresp+0.028
vern+0.027
 cruel+0.026
 supposed+0.026
Neg logit contributions
cy-0.018
 Of-0.018
 girl-0.017
sc-0.016
 Sure-0.016
Token to
Token ID284
Feature activation-1.18e+00

Pos logit contributions
cy+0.079
 Of+0.079
sc+0.073
 girl+0.073
 Sure+0.069
Neg logit contributions
 strangers-0.129
 tresp-0.118
vern-0.113
 cruel-0.109
unts-0.109
Token strangers
Token ID18981
Feature activation-1.59e+01

Pos logit contributions
 strangers+0.069
 tresp+0.069
vern+0.066
unts+0.064
 supposed+0.063
Neg logit contributions
 Of-0.058
cy-0.056
 girl-0.055
 up-0.049
 down-0.049
Token again
Token ID757
Feature activation+4.10e+00

Pos logit contributions
 strangers+1.149
 tresp+1.058
vern+1.022
 cruel+0.978
 supposed+0.973
Neg logit contributions
cy-0.643
 Of-0.638
sc-0.590
 girl-0.587
 Sure-0.562
Token.
Token ID13
Feature activation-3.39e-01

Pos logit contributions
cy+0.155
 Of+0.153
 girl+0.145
 down+0.132
sc+0.131
Neg logit contributions
 strangers-0.298
 tresp-0.283
vern-0.275
 cruel-0.258
 supposed-0.257
Token<|endoftext|>
Token ID50256
Feature activation-7.19e+00

Pos logit contributions
 strangers+0.020
 tresp+0.018
vern+0.017
unts+0.017
 supposed+0.017
Neg logit contributions
cy-0.018
 Of-0.017
sc-0.017
 girl-0.016
 tin-0.016
TokenOnce
Token ID7454
Feature activation-2.89e-01

Pos logit contributions
 strangers+0.417
 tresp+0.366
vern+0.353
unts+0.345
 supposed+0.333
Neg logit contributions
 Of-0.374
cy-0.367
 girl-0.350
 mixture-0.346
sc-0.346
Token upon
Token ID2402
Feature activation-4.20e-01

Pos logit contributions
 strangers+0.022
 tresp+0.021
vern+0.019
cod+0.019
 cruel+0.019
Neg logit contributions
cy-0.011
 Of-0.011
 girl-0.010
 Sure-0.009
 down-0.009
Token rules
Token ID3173
Feature activation+1.03e+00

Pos logit contributions
 strangers+0.022
 tresp+0.019
vern+0.018
 cruel+0.018
 enemies+0.017
Neg logit contributions
cy-0.016
 Of-0.015
sc-0.015
 Sure-0.014
 girl-0.014
Token.
Token ID13
Feature activation-3.59e-01

Pos logit contributions
cy+0.041
 Of+0.040
sc+0.039
 girl+0.038
 down+0.036
Neg logit contributions
 strangers-0.073
 tresp-0.068
vern-0.064
 cruel-0.064
cod-0.063
Token She
Token ID1375
Feature activation-6.22e-02

Pos logit contributions
 strangers+0.022
 tresp+0.019
vern+0.019
unts+0.019
isdom+0.018
Neg logit contributions
cy-0.018
sc-0.018
 Of-0.017
 mixture-0.017
 tin-0.016
Token knew
Token ID2993
Feature activation-4.30e+00

Pos logit contributions
 strangers+0.003
 tresp+0.003
vern+0.003
 supposed+0.003
 cruel+0.003
Neg logit contributions
cy-0.004
 girl-0.004
 Of-0.003
sc-0.003
 Sure-0.003
Token that
Token ID326
Feature activation-1.47e+00

Pos logit contributions
 strangers+0.252
 tresp+0.228
vern+0.217
unts+0.207
 cruel+0.206
Neg logit contributions
 Of-0.233
cy-0.228
 girl-0.217
sc-0.213
 Sure-0.211
Token strangers
Token ID18981
Feature activation-1.59e+01

Pos logit contributions
 strangers+0.096
 tresp+0.086
vern+0.082
 cruel+0.079
 supposed+0.079
Neg logit contributions
cy-0.070
 Of-0.070
sc-0.066
 girl-0.065
 Sure-0.063
Token could
Token ID714
Feature activation-5.28e+00

Pos logit contributions
 strangers+0.948
vern+0.947
 tresp+0.901
unts+0.884
cod+0.860
Neg logit contributions
cy-0.821
 girl-0.751
sc-0.745
 Of-0.733
 up-0.718
Token be
Token ID307
Feature activation+1.25e+00

Pos logit contributions
 strangers+0.291
ills+0.286
lee+0.281
 tresp+0.281
eping+0.281
Neg logit contributions
 up-0.242
cy-0.238
 Of-0.236
 with-0.229
 girl-0.228
Token dangerous
Token ID4923
Feature activation-1.02e+01

Pos logit contributions
 girl+0.069
 up+0.068
 down+0.067
cy+0.067
 Of+0.065
Neg logit contributions
 strangers-0.065
 tresp-0.059
vern-0.059
unts-0.056
isdom-0.054
Token and
Token ID290
Feature activation-2.90e+00

Pos logit contributions
 strangers+0.640
 tresp+0.578
vern+0.555
 cruel+0.528
 supposed+0.523
Neg logit contributions
 Of-0.508
cy-0.507
sc-0.475
 girl-0.473
 Sure-0.458
Token that
Token ID326
Feature activation-1.46e+00

Pos logit contributions
 strangers+0.143
vern+0.141
 tresp+0.138
unts+0.131
eping+0.126
Neg logit contributions
 Of-0.164
 girl-0.164
cy-0.157
 down-0.156
 up-0.153
Token feelings
Token ID7666
Feature activation-3.21e+00

Pos logit contributions
 strangers+0.143
 tresp+0.136
eping+0.134
vern+0.133
 supposed+0.132
Neg logit contributions
 girl-0.092
cy-0.086
 Of-0.083
 up-0.074
 Sure-0.074
Token and
Token ID290
Feature activation-3.06e+00

Pos logit contributions
 strangers+0.210
 tresp+0.195
vern+0.184
 cruel+0.178
 supposed+0.178
Neg logit contributions
 Of-0.147
cy-0.145
sc-0.140
 girl-0.139
 onto-0.130
Token not
Token ID407
Feature activation-5.09e+00

Pos logit contributions
 strangers+0.155
 tresp+0.140
vern+0.137
unts+0.127
eping+0.125
Neg logit contributions
 Of-0.184
cy-0.178
 girl-0.176
 Sure-0.167
sc-0.166
Token to
Token ID284
Feature activation-1.08e+00

Pos logit contributions
 strangers+0.308
vern+0.285
 tresp+0.282
unts+0.256
 cruel+0.255
Neg logit contributions
 Of-0.255
cy-0.254
 girl-0.239
sc-0.233
 down-0.229
Token follow
Token ID1061
Feature activation+2.88e+00

Pos logit contributions
vern+0.063
 strangers+0.062
 tresp+0.061
eping+0.057
 supposed+0.056
Neg logit contributions
cy-0.052
 Of-0.051
 girl-0.050
 down-0.047
 up-0.046
Token strangers
Token ID18981
Feature activation-1.59e+01

Pos logit contributions
 Of+0.132
cy+0.130
 up+0.128
 down+0.127
 girl+0.124
Neg logit contributions
vern-0.171
 strangers-0.167
 tresp-0.166
unts-0.159
 supposed-0.158
Token.
Token ID13
Feature activation-5.62e-01

Pos logit contributions
 strangers+1.083
 tresp+0.994
vern+0.959
 cruel+0.917
 supposed+0.910
Neg logit contributions
cy-0.700
 Of-0.695
sc-0.651
 girl-0.642
 Sure-0.619
Token They
Token ID1119
Feature activation+4.38e-01

Pos logit contributions
 strangers+0.037
 tresp+0.034
vern+0.032
unts+0.031
 cruel+0.031
Neg logit contributions
cy-0.026
 Of-0.026
sc-0.025
 girl-0.024
 Sure-0.023
Token learned
Token ID4499
Feature activation-6.45e+00

Pos logit contributions
cy+0.027
 girl+0.026
 Of+0.023
 cash+0.023
 boy+0.023
Neg logit contributions
 strangers-0.022
ills-0.020
vern-0.020
eping-0.020
 tresp-0.020
Token to
Token ID284
Feature activation-1.08e+00

Pos logit contributions
 strangers+0.393
 tresp+0.357
vern+0.336
cod+0.328
unts+0.328
Neg logit contributions
 Of-0.329
cy-0.309
 girl-0.303
sc-0.297
 Sure-0.295
Token stay
Token ID2652
Feature activation-1.24e+00

Pos logit contributions
 strangers+0.058
 tresp+0.052
vern+0.049
 cruel+0.048
eping+0.047
Neg logit contributions
 Of-0.059
cy-0.059
 girl-0.057
sc-0.054
 Sure-0.053
Token that
Token ID326
Feature activation-1.43e+00

Pos logit contributions
 strangers+0.379
 tresp+0.342
cod+0.320
vern+0.319
 supposed+0.311
Neg logit contributions
 Of-0.347
 girl-0.318
cy-0.315
 up-0.312
 Sure-0.311
Token they
Token ID484
Feature activation-2.45e-01

Pos logit contributions
 strangers+0.079
 tresp+0.071
vern+0.069
 cruel+0.064
unts+0.064
Neg logit contributions
 Of-0.081
cy-0.078
 girl-0.075
sc-0.074
 Sure-0.073
Token should
Token ID815
Feature activation-7.59e+00

Pos logit contributions
 strangers+0.013
 tresp+0.013
ules+0.012
vern+0.012
eping+0.012
Neg logit contributions
cy-0.014
 girl-0.013
 fits-0.013
 up-0.013
 Of-0.012
Token not
Token ID407
Feature activation-5.02e+00

Pos logit contributions
 strangers+0.390
eping+0.365
 tresp+0.361
cod+0.355
ache+0.337
Neg logit contributions
 Of-0.412
 girl-0.394
cy-0.393
 up-0.384
 with-0.383
Token trust
Token ID3774
Feature activation-1.78e+00

Pos logit contributions
 strangers+0.290
vern+0.281
 tresp+0.273
eping+0.260
cod+0.253
Neg logit contributions
 Of-0.256
cy-0.249
 girl-0.232
 down-0.227
sc-0.223
Token strangers
Token ID18981
Feature activation-1.59e+01

Pos logit contributions
vern+0.098
 tresp+0.092
Days+0.090
 strangers+0.088
ache+0.087
Neg logit contributions
cy-0.094
 Of-0.091
 up-0.090
 down-0.090
 girl-0.089
Token.
Token ID13
Feature activation-5.60e-01

Pos logit contributions
 strangers+1.063
 tresp+1.040
vern+1.038
eping+1.004
unts+0.998
Neg logit contributions
cy-0.650
sc-0.608
 Of-0.605
 girl-0.597
 up-0.585
Token They
Token ID1119
Feature activation+4.68e-01

Pos logit contributions
 strangers+0.039
 tresp+0.036
vern+0.034
 cruel+0.033
 supposed+0.033
Neg logit contributions
 Of-0.024
cy-0.024
sc-0.022
 girl-0.022
 Sure-0.022
Token learned
Token ID4499
Feature activation-6.45e+00

Pos logit contributions
 girl+0.029
cy+0.029
 Of+0.027
 boy+0.026
 up+0.025
Neg logit contributions
 strangers-0.023
eping-0.021
 tresp-0.021
ills-0.020
 supposed-0.019
Token that
Token ID326
Feature activation-1.43e+00

Pos logit contributions
 strangers+0.373
 tresp+0.337
vern+0.314
cod+0.313
 supposed+0.307
Neg logit contributions
 Of-0.350
 girl-0.321
cy-0.320
 Sure-0.315
 up-0.315
Token they
Token ID484
Feature activation-2.26e-01

Pos logit contributions
 strangers+0.080
 tresp+0.073
vern+0.072
unts+0.066
 cruel+0.065
Neg logit contributions
 Of-0.079
cy-0.076
 girl-0.073
sc-0.071
 Sure-0.071
Token promised
Token ID8072
Feature activation-1.98e+00

Pos logit contributions
 strangers+0.157
 tresp+0.140
vern+0.132
 cruel+0.126
 supposed+0.125
Neg logit contributions
 Of-0.145
cy-0.144
sc-0.136
 girl-0.135
 Sure-0.132
Token never
Token ID1239
Feature activation-6.67e+00

Pos logit contributions
 strangers+0.130
 tresp+0.119
vern+0.114
 cruel+0.109
 supposed+0.108
Neg logit contributions
 Of-0.093
cy-0.091
 girl-0.085
sc-0.085
 Sure-0.083
Token to
Token ID284
Feature activation-1.09e+00

Pos logit contributions
 strangers+0.429
 tresp+0.383
vern+0.362
 cruel+0.352
 supposed+0.351
Neg logit contributions
cy-0.328
 Of-0.326
sc-0.309
 girl-0.300
 Sure-0.297
Token frown
Token ID22002
Feature activation-2.00e+00

Pos logit contributions
 strangers+0.064
 tresp+0.059
vern+0.058
cod+0.054
 cruel+0.053
Neg logit contributions
 Of-0.057
cy-0.056
 girl-0.053
 down-0.050
sc-0.050
Token on
Token ID319
Feature activation+3.59e+00

Pos logit contributions
 strangers+0.147
 tresp+0.131
vern+0.126
 cruel+0.124
 supposed+0.123
Neg logit contributions
 Of-0.080
cy-0.079
sc-0.073
 Sure-0.072
 girl-0.071
Token strangers
Token ID18981
Feature activation-1.59e+01

Pos logit contributions
 Of+0.162
cy+0.159
 girl+0.151
sc+0.147
 up+0.144
Neg logit contributions
 strangers-0.226
vern-0.213
 tresp-0.212
unts-0.200
 supposed-0.200
Token again
Token ID757
Feature activation+4.24e+00

Pos logit contributions
 strangers+1.224
 tresp+1.105
vern+1.062
 cruel+1.028
 supposed+1.022
Neg logit contributions
 Of-0.577
cy-0.567
sc-0.518
 girl-0.511
 Sure-0.506
Token.
Token ID13
Feature activation-6.46e-02

Pos logit contributions
 Of+0.183
cy+0.182
 girl+0.168
sc+0.166
 Sure+0.161
Neg logit contributions
 strangers-0.291
 tresp-0.269
vern-0.260
 cruel-0.247
 supposed-0.245
Token They
Token ID1119
Feature activation+6.48e-01

Pos logit contributions
 strangers+0.005
 tresp+0.004
vern+0.004
unts+0.004
 supposed+0.004
Neg logit contributions
cy-0.003
 Of-0.003
sc-0.002
 girl-0.002
 tin-0.002
Token also
Token ID635
Feature activation-2.46e+00

Pos logit contributions
cy+0.036
 girl+0.032
 Of+0.031
 onto+0.031
 down+0.030
Neg logit contributions
 strangers-0.039
vern-0.036
 tresp-0.036
 supposed-0.033
cod-0.033
Token promised
Token ID8072
Feature activation-1.98e+00

Pos logit contributions
 strangers+0.142
vern+0.127
 tresp+0.124
 supposed+0.115
Days+0.113
Neg logit contributions
cy-0.142
 Of-0.131
 girl-0.131
 tin-0.122
 onto-0.120
Token to
Token ID284
Feature activation-1.05e+00

Pos logit contributions
 strangers+0.073
 tresp+0.066
vern+0.064
 cruel+0.061
 supposed+0.060
Neg logit contributions
cy-0.059
 Of-0.059
 girl-0.056
sc-0.055
 Sure-0.053
Token their
Token ID511
Feature activation-2.08e+00

Pos logit contributions
vern+0.064
ache+0.062
 tresp+0.060
eping+0.059
 strangers+0.058
Neg logit contributions
 Of-0.048
 girl-0.045
 up-0.043
cy-0.043
 down-0.041
Token friends
Token ID2460
Feature activation-8.33e-01

Pos logit contributions
 strangers+0.119
 tresp+0.109
vern+0.106
 supposed+0.101
 cruel+0.099
Neg logit contributions
cy-0.113
 Of-0.111
 girl-0.108
sc-0.100
 Sure-0.100
Token and
Token ID290
Feature activation-2.98e+00

Pos logit contributions
 strangers+0.056
 tresp+0.053
vern+0.050
 cruel+0.049
 supposed+0.049
Neg logit contributions
cy-0.036
 Of-0.036
sc-0.034
 girl-0.034
 down-0.031
Token to
Token ID284
Feature activation-1.06e+00

Pos logit contributions
 strangers+0.165
 tresp+0.150
vern+0.145
eping+0.138
cod+0.136
Neg logit contributions
 Of-0.166
cy-0.161
 girl-0.159
 Sure-0.149
sc-0.148
Token strangers
Token ID18981
Feature activation-1.59e+01

Pos logit contributions
 strangers+0.056
vern+0.056
ache+0.056
 tresp+0.055
eping+0.054
Neg logit contributions
 Of-0.053
 girl-0.050
cy-0.049
 up-0.048
 down-0.048
Token.
Token ID13
Feature activation-4.76e-01

Pos logit contributions
 strangers+1.130
 tresp+1.069
vern+1.040
 supposed+0.993
 cruel+0.985
Neg logit contributions
cy-0.634
 Of-0.613
 girl-0.581
sc-0.578
 down-0.540
Token They
Token ID1119
Feature activation+5.67e-01

Pos logit contributions
 strangers+0.033
 tresp+0.030
vern+0.029
 cruel+0.028
 supposed+0.028
Neg logit contributions
 Of-0.021
cy-0.021
sc-0.019
 girl-0.019
 Sure-0.019
Token hugged
Token ID41130
Feature activation-1.94e+00

Pos logit contributions
cy+0.035
 girl+0.034
 Of+0.030
sc+0.029
 boy+0.029
Neg logit contributions
 strangers-0.029
eping-0.026
ills-0.026
 tresp-0.025
 supposed-0.025
Token each
Token ID1123
Feature activation-4.57e+00

Pos logit contributions
 strangers+0.116
vern+0.114
 tresp+0.114
 supposed+0.109
 cruel+0.102
Neg logit contributions
cy-0.097
 Of-0.097
 girl-0.095
 down-0.088
sc-0.088
Token other
Token ID584
Feature activation-2.85e-01

Pos logit contributions
 strangers+0.302
 tresp+0.281
vern+0.272
 cruel+0.259
 supposed+0.257
Neg logit contributions
cy-0.206
 Of-0.205
 girl-0.200
sc-0.193
 Sure-0.182
Token friends
Token ID2460
Feature activation-7.38e-01

Pos logit contributions
 strangers+0.023
 tresp+0.021
vern+0.019
 supposed+0.019
 cruel+0.019
Neg logit contributions
 Of-0.018
cy-0.018
sc-0.017
 Sure-0.016
 girl-0.016
Token and
Token ID290
Feature activation-2.86e+00

Pos logit contributions
 strangers+0.050
 tresp+0.046
vern+0.044
 cruel+0.042
unts+0.042
Neg logit contributions
cy-0.033
 Of-0.033
sc-0.031
 girl-0.030
 Sure-0.029
Token not
Token ID407
Feature activation-5.05e+00

Pos logit contributions
 strangers+0.153
 tresp+0.136
vern+0.131
 cruel+0.122
unts+0.121
Neg logit contributions
 Of-0.167
cy-0.166
 girl-0.158
sc-0.157
 Sure-0.153
Token talking
Token ID3375
Feature activation-6.06e-01

Pos logit contributions
 strangers+0.263
vern+0.238
 tresp+0.235
unts+0.212
 cruel+0.211
Neg logit contributions
 Of-0.293
cy-0.290
 girl-0.284
sc-0.271
 down-0.270
Token to
Token ID284
Feature activation-1.09e+00

Pos logit contributions
 strangers+0.041
 tresp+0.039
vern+0.038
cod+0.036
unts+0.036
Neg logit contributions
 Of-0.025
cy-0.024
sc-0.023
 down-0.023
 girl-0.023
Token strangers
Token ID18981
Feature activation-1.59e+01

Pos logit contributions
vern+0.064
 tresp+0.059
eping+0.055
 strangers+0.055
unts+0.055
Neg logit contributions
 girl-0.054
 Of-0.054
 down-0.050
cy-0.050
 up-0.050
Token.
Token ID13
Feature activation-1.75e-01

Pos logit contributions
 strangers+1.102
 tresp+1.032
vern+1.014
unts+0.962
 cruel+0.958
Neg logit contributions
cy-0.658
 Of-0.642
sc-0.614
 girl-0.608
 down-0.576
Token Lily
Token ID20037
Feature activation+3.84e+00

Pos logit contributions
 strangers+0.011
 hated+0.010
 shouldn+0.009
 never+0.009
unts+0.009
Neg logit contributions
cy-0.008
cer-0.008
sc-0.007
 mixture-0.007
fl-0.007
Token thought
Token ID1807
Feature activation+3.38e+00

Pos logit contributions
cy+0.209
 Of+0.207
 girl+0.200
sc+0.194
 Sure+0.187
Neg logit contributions
 strangers-0.224
 tresp-0.202
vern-0.195
 supposed-0.183
 cruel-0.180
Token that
Token ID326
Feature activation-1.47e+00

Pos logit contributions
 up+0.159
 Of+0.141
 onto+0.138
 girl+0.133
 down+0.131
Neg logit contributions
cod-0.211
unts-0.209
 tresp-0.205
vern-0.201
 liar-0.196
Token was
Token ID373
Feature activation+2.58e+00

Pos logit contributions
 strangers+0.097
 tresp+0.088
vern+0.086
 cruel+0.081
unts+0.081
Neg logit contributions
 Of-0.069
cy-0.067
 girl-0.064
sc-0.063
 Sure-0.061
Token "
Token ID366
Feature activation-3.12e+00

Pos logit contributions
 Of+0.013
cy+0.012
 girl+0.011
sc+0.011
 Sure+0.011
Neg logit contributions
 strangers-0.019
 tresp-0.017
vern-0.016
 supposed-0.016
 cruel-0.015
TokenYou
Token ID1639
Feature activation+2.87e+00

Pos logit contributions
 strangers+0.195
 tresp+0.168
 never+0.167
vern+0.166
 cruel+0.164
Neg logit contributions
cy-0.142
 Of-0.141
sc-0.140
 onto-0.136
suit-0.135
Token shouldn
Token ID6584
Feature activation-1.24e+01

Pos logit contributions
cy+0.167
 girl+0.160
 Of+0.157
 onto+0.147
 fits+0.147
Neg logit contributions
 strangers-0.161
vern-0.134
 tresp-0.132
Days-0.132
cod-0.132
Token't
Token ID470
Feature activation-3.55e+00

Pos logit contributions
 strangers+0.671
 tresp+0.591
vern+0.556
cod+0.539
 cruel+0.537
Neg logit contributions
 Of-0.739
cy-0.720
 girl-0.687
sc-0.678
 Sure-0.663
Token trust
Token ID3774
Feature activation-1.83e+00

Pos logit contributions
 strangers+0.201
 tresp+0.181
vern+0.175
 cruel+0.164
 supposed+0.162
Neg logit contributions
 Of-0.201
cy-0.199
 girl-0.186
sc-0.184
 Sure-0.179
Token strangers
Token ID18981
Feature activation-1.59e+01

Pos logit contributions
vern+0.118
 tresp+0.115
 strangers+0.112
cod+0.110
unts+0.110
Neg logit contributions
 Of-0.076
cy-0.073
 up-0.073
 down-0.073
 girl-0.073
Token!"
Token ID2474
Feature activation-6.94e-01

Pos logit contributions
 strangers+1.075
 tresp+1.004
vern+1.003
unts+0.953
 cruel+0.943
Neg logit contributions
cy-0.675
 Of-0.657
sc-0.632
 girl-0.621
 down-0.599
Token in
Token ID287
Feature activation+2.37e+00

Pos logit contributions
 strangers+0.042
 hated+0.037
unts+0.036
 never+0.036
 tresp+0.035
Neg logit contributions
cy-0.033
sc-0.032
suit-0.030
 tin-0.030
 Of-0.030
Token a
Token ID257
Feature activation+1.33e+00

Pos logit contributions
 Of+0.117
cy+0.117
sc+0.110
 girl+0.108
 Sure+0.106
Neg logit contributions
 strangers-0.152
 tresp-0.136
vern-0.130
 cruel-0.125
 supposed-0.123
Token harsh
Token ID11859
Feature activation-5.57e+00

Pos logit contributions
 Of+0.074
cy+0.073
 girl+0.072
sc+0.070
 Sure+0.067
Neg logit contributions
 strangers-0.076
 tresp-0.068
vern-0.064
 supposed-0.063
isdom-0.060
Token voice
Token ID3809
Feature activation+2.52e+00

Pos logit contributions
 strangers+0.391
 tresp+0.359
vern+0.348
 supposed+0.332
 cruel+0.330
Neg logit contributions
 Of-0.235
cy-0.232
 girl-0.218
sc-0.213
 Sure-0.206
Token be
Token ID307
Feature activation+1.27e+00

Pos logit contributions
 strangers+0.070
 tresp+0.067
vern+0.067
unts+0.066
eping+0.064
Neg logit contributions
cy-0.047
 Of-0.046
 girl-0.045
 up-0.042
 down-0.039
Token patient
Token ID5827
Feature activation+5.88e-01

Pos logit contributions
 Of+0.079
cy+0.079
 girl+0.077
sc+0.074
 down+0.073
Neg logit contributions
 strangers-0.063
 tresp-0.054
vern-0.052
unts-0.048
 supposed-0.047
Token and
Token ID290
Feature activation-2.88e+00

Pos logit contributions
cy+0.029
 Of+0.029
 girl+0.027
sc+0.027
 Sure+0.026
Neg logit contributions
 strangers-0.037
 tresp-0.033
vern-0.032
 cruel-0.031
unts-0.030
Token not
Token ID407
Feature activation-5.01e+00

Pos logit contributions
 strangers+0.137
 tresp+0.120
vern+0.114
unts+0.105
 supposed+0.103
Neg logit contributions
 Of-0.186
cy-0.183
 girl-0.177
sc-0.174
 Sure-0.172
Token trust
Token ID3774
Feature activation-1.73e+00

Pos logit contributions
 strangers+0.289
vern+0.287
 tresp+0.265
isdom+0.250
eping+0.249
Neg logit contributions
 Of-0.248
cy-0.247
 girl-0.239
 down-0.235
sc-0.223
Token strangers
Token ID18981
Feature activation-1.59e+01

Pos logit contributions
vern+0.090
 tresp+0.081
Days+0.079
cod+0.077
 strangers+0.077
Neg logit contributions
 down-0.098
cy-0.097
 up-0.096
 into-0.094
 girl-0.092
Token.
Token ID13
Feature activation-2.27e-01

Pos logit contributions
 strangers+1.106
 tresp+1.042
vern+1.039
unts+0.992
 cruel+0.979
Neg logit contributions
cy-0.639
 Of-0.607
sc-0.594
 girl-0.580
 down-0.560
Token<|endoftext|>
Token ID50256
Feature activation-7.11e+00

Pos logit contributions
 strangers+0.014
 tresp+0.012
vern+0.012
unts+0.011
 hated+0.011
Neg logit contributions
cy-0.012
 Of-0.011
sc-0.011
 girl-0.011
 tin-0.010
TokenOnce
Token ID7454
Feature activation-1.61e-01

Pos logit contributions
 strangers+0.417
 tresp+0.372
vern+0.353
unts+0.345
 supposed+0.337
Neg logit contributions
 Of-0.366
cy-0.359
 girl-0.343
sc-0.338
 mixture-0.337
Token upon
Token ID2402
Feature activation-3.53e-01

Pos logit contributions
 strangers+0.013
 tresp+0.012
cod+0.011
vern+0.011
 cruel+0.011
Neg logit contributions
cy-0.006
 Of-0.006
 girl-0.005
 Sure-0.005
 up-0.005
Token a
Token ID257
Feature activation+1.36e+00

Pos logit contributions
 strangers+0.027
 tresp+0.025
vern+0.024
 cruel+0.023
isdom+0.023
Neg logit contributions
 Of-0.012
cy-0.012
 girl-0.012
sc-0.011
 Sure-0.011
Token shy
Token ID15800
Feature activation-1.60e+00

Pos logit contributions
 strangers+0.060
 tresp+0.053
vern+0.051
isdom+0.048
Days+0.047
Neg logit contributions
cy-0.063
 Of-0.062
 girl-0.061
sc-0.058
 tin-0.057
Token and
Token ID290
Feature activation-3.14e+00

Pos logit contributions
 strangers+0.105
 tresp+0.096
vern+0.093
 cruel+0.088
 supposed+0.087
Neg logit contributions
 Of-0.074
cy-0.074
 girl-0.069
sc-0.069
 Sure-0.066
Token does
Token ID857
Feature activation+7.49e-03

Pos logit contributions
 strangers+0.155
vern+0.139
 tresp+0.138
unts+0.124
 supposed+0.122
Neg logit contributions
 Of-0.191
cy-0.189
 girl-0.184
sc-0.180
 down-0.176
Token not
Token ID407
Feature activation-5.00e+00

Pos logit contributions
 up+0.001
 Of+0.001
 down+0.001
 onto+0.000
 girl+0.000
Neg logit contributions
 strangers-0.000
 tresp-0.000
vern-0.000
unts-0.000
ills-0.000
Token like
Token ID588
Feature activation-6.43e-01

Pos logit contributions
 strangers+0.239
vern+0.224
 tresp+0.222
Days+0.198
isdom+0.195
Neg logit contributions
cy-0.300
 girl-0.298
 Of-0.294
 down-0.281
sc-0.277
Token strangers
Token ID18981
Feature activation-1.59e+01

Pos logit contributions
 strangers+0.038
vern+0.038
 tresp+0.037
unts+0.035
cod+0.034
Neg logit contributions
 Of-0.030
 girl-0.029
cy-0.028
 down-0.027
 up-0.027
Token."
Token ID526
Feature activation-7.24e-01

Pos logit contributions
 strangers+1.086
vern+1.073
 tresp+1.056
Days+1.010
unts+1.000
Neg logit contributions
cy-0.625
 Of-0.589
 down-0.585
 girl-0.583
sc-0.583
Token
Token ID198
Feature activation+3.78e-01

Pos logit contributions
 strangers+0.040
 tresp+0.032
unts+0.032
vern+0.031
 understand+0.031
Neg logit contributions
cy-0.041
sc-0.041
 mixture-0.040
 tin-0.037
umm-0.036
Token
Token ID198
Feature activation+3.79e-01

Pos logit contributions
 Of+0.014
cy+0.013
 girl+0.012
 Sure+0.012
sc+0.012
Neg logit contributions
 strangers-0.029
 tresp-0.028
 supposed-0.026
vern-0.026
 cruel-0.025
Token"
Token ID1
Feature activation-5.91e+00

Pos logit contributions
 Of+0.018
cy+0.018
sc+0.017
 girl+0.017
 Sure+0.016
Neg logit contributions
 strangers-0.025
 tresp-0.022
vern-0.022
 cruel-0.021
 supposed-0.020
TokenThank
Token ID10449
Feature activation+4.77e+00

Pos logit contributions
 strangers+0.376
 cruel+0.333
Days+0.323
vern+0.316
 tresp+0.314
Neg logit contributions
cy-0.280
 onto-0.278
 down-0.277
 up-0.275
 into-0.258
Token.
Token ID13
Feature activation-7.23e-01

Pos logit contributions
cy+0.157
 Of+0.156
 girl+0.146
sc+0.134
 Sure+0.134
Neg logit contributions
 strangers-0.302
 tresp-0.284
vern-0.277
 cruel-0.264
 supposed-0.259
Token They
Token ID1119
Feature activation+2.56e-02

Pos logit contributions
 strangers+0.042
 tresp+0.036
unts+0.035
 hated+0.034
vern+0.033
Neg logit contributions
cy-0.040
sc-0.039
 Of-0.037
 mixture-0.037
 girl-0.036
Token do
Token ID466
Feature activation-2.30e+00

Pos logit contributions
cy+0.001
 girl+0.001
 tin+0.001
 Of+0.001
 up+0.001
Neg logit contributions
 strangers-0.002
vern-0.001
eping-0.001
ills-0.001
 supposed-0.001
Token not
Token ID407
Feature activation-5.09e+00

Pos logit contributions
 strangers+0.089
 tresp+0.079
vern+0.071
cod+0.067
ache+0.065
Neg logit contributions
 up-0.162
 Of-0.160
cy-0.153
 girl-0.151
 with-0.150
Token follow
Token ID1061
Feature activation+2.99e+00

Pos logit contributions
vern+0.274
 strangers+0.268
 tresp+0.260
Days+0.241
cod+0.236
Neg logit contributions
cy-0.286
 girl-0.270
 Of-0.257
 down-0.253
 with-0.240
Token strangers
Token ID18981
Feature activation-1.59e+01

Pos logit contributions
 Of+0.159
cy+0.157
 girl+0.150
sc+0.146
 down+0.142
Neg logit contributions
 strangers-0.168
 tresp-0.158
vern-0.156
 supposed-0.144
 cruel-0.143
Token.
Token ID13
Feature activation-7.18e-01

Pos logit contributions
 strangers+1.075
 tresp+0.997
vern+0.969
 cruel+0.922
unts+0.915
Neg logit contributions
cy-0.695
 Of-0.683
sc-0.644
 girl-0.636
 Sure-0.608
Token They
Token ID1119
Feature activation+5.15e-02

Pos logit contributions
 strangers+0.045
 tresp+0.039
unts+0.037
vern+0.037
 hated+0.036
Neg logit contributions
cy-0.037
sc-0.036
 Of-0.035
 girl-0.034
 mixture-0.033
Token are
Token ID389
Feature activation-4.34e+00

Pos logit contributions
cy+0.003
 girl+0.002
 Of+0.002
 up+0.002
 tin+0.002
Neg logit contributions
 strangers-0.003
vern-0.003
ills-0.003
eping-0.003
 supposed-0.003
Token polite
Token ID23507
Feature activation-2.36e+00

Pos logit contributions
 strangers+0.219
vern+0.213
isdom+0.204
 tresp+0.201
cod+0.198
Neg logit contributions
 up-0.242
 girl-0.238
 down-0.230
 into-0.227
cy-0.220
Token and
Token ID290
Feature activation-3.28e+00

Pos logit contributions
 strangers+0.156
 tresp+0.143
vern+0.140
 cruel+0.132
 supposed+0.131
Neg logit contributions
cy-0.107
 Of-0.107
 girl-0.103
sc-0.098
 Sure-0.094
Token it
Token ID340
Feature activation-5.83e-01

Pos logit contributions
 Of+0.048
cy+0.047
sc+0.044
 girl+0.043
 Sure+0.042
Neg logit contributions
 strangers-0.065
 tresp-0.058
vern-0.053
 cruel-0.052
 never-0.051
Token.
Token ID13
Feature activation-2.43e-02

Pos logit contributions
 strangers+0.041
 tresp+0.037
vern+0.036
 supposed+0.034
 cruel+0.034
Neg logit contributions
 Of-0.026
cy-0.024
 girl-0.022
 Sure-0.022
sc-0.021
Token Finally
Token ID9461
Feature activation+6.34e+00

Pos logit contributions
 strangers+0.001
 tresp+0.001
 hated+0.001
 never+0.001
 shouldn+0.001
Neg logit contributions
cy-0.001
sc-0.001
 girl-0.001
fl-0.001
cer-0.001
Token,
Token ID11
Feature activation+4.94e-01

Pos logit contributions
cy+0.348
 Of+0.342
sc+0.330
 girl+0.315
 Sure+0.311
Neg logit contributions
 strangers-0.378
 tresp-0.341
vern-0.311
 cruel-0.302
 hated-0.291
Token the
Token ID262
Feature activation-1.13e+00

Pos logit contributions
cy+0.028
sc+0.028
 Of+0.027
suit+0.025
 girl+0.025
Neg logit contributions
 strangers-0.028
 tresp-0.024
 never-0.023
 cruel-0.021
 understand-0.020
Token strangers
Token ID18981
Feature activation-1.58e+01

Pos logit contributions
 strangers+0.064
 tresp+0.056
vern+0.052
 cruel+0.051
 supposed+0.049
Neg logit contributions
 Of-0.065
cy-0.065
sc-0.062
 Sure-0.060
 girl-0.058
Token got
Token ID1392
Feature activation-1.18e+00

Pos logit contributions
 strangers+0.909
vern+0.884
 tresp+0.828
isdom+0.795
 supposed+0.787
Neg logit contributions
cy-0.856
sc-0.811
 girl-0.805
 Of-0.801
 onto-0.775
Token angry
Token ID7954
Feature activation-5.42e+00

Pos logit contributions
 strangers+0.086
 tresp+0.078
vern+0.073
 cruel+0.072
 supposed+0.072
Neg logit contributions
 Of-0.050
cy-0.049
sc-0.045
 Sure-0.044
 girl-0.044
Token.
Token ID13
Feature activation+2.15e-02

Pos logit contributions
 strangers+0.325
 tresp+0.291
vern+0.277
 cruel+0.264
 supposed+0.262
Neg logit contributions
 Of-0.287
cy-0.286
sc-0.268
 girl-0.266
 Sure-0.261
Token They
Token ID1119
Feature activation+5.70e-01

Pos logit contributions
cy+0.001
sc+0.001
 girl+0.001
 Of+0.001
 tin+0.001
Neg logit contributions
 strangers-0.001
 tresp-0.001
unts-0.001
 hated-0.001
vern-0.001
Token started
Token ID2067
Feature activation+1.54e+00

Pos logit contributions
cy+0.027
 onto+0.026
 girl+0.025
 down+0.025
 into+0.024
Neg logit contributions
vern-0.037
 strangers-0.035
isdom-0.034
opl-0.033
 supposed-0.032
Token day
Token ID1110
Feature activation+3.74e+00

Pos logit contributions
 strangers+0.105
 tresp+0.094
vern+0.089
 supposed+0.089
 cruel+0.088
Neg logit contributions
cy-0.062
 Of-0.060
sc-0.056
 Sure-0.054
 girl-0.054
Token to
Token ID284
Feature activation-1.10e+00

Pos logit contributions
 Of+0.175
 onto+0.161
cy+0.161
 Sure+0.158
 down+0.156
Neg logit contributions
 strangers-0.236
 tresp-0.221
vern-0.219
cod-0.217
 cruel-0.206
Token be
Token ID307
Feature activation+1.26e+00

Pos logit contributions
 strangers+0.063
 tresp+0.058
vern+0.055
 supposed+0.054
eping+0.054
Neg logit contributions
cy-0.057
 Of-0.056
 girl-0.054
 up-0.051
 tin-0.050
Token careful
Token ID8161
Feature activation-9.81e-01

Pos logit contributions
 girl+0.075
cy+0.074
 Of+0.073
 down+0.070
 up+0.069
Neg logit contributions
 strangers-0.065
 tresp-0.057
vern-0.055
unts-0.052
isdom-0.050
Token with
Token ID351
Feature activation+9.40e+00

Pos logit contributions
 strangers+0.072
 tresp+0.068
vern+0.065
cod+0.063
 cruel+0.062
Neg logit contributions
cy-0.036
 Of-0.036
 up-0.035
 girl-0.034
sc-0.034
Token strangers
Token ID18981
Feature activation-1.58e+01

Pos logit contributions
 Of+0.397
 girl+0.396
 up+0.396
cy+0.373
 down+0.371
Neg logit contributions
vern-0.549
unts-0.543
 strangers-0.535
 tresp-0.529
ache-0.503
Token and
Token ID290
Feature activation-2.87e+00

Pos logit contributions
 strangers+1.052
 tresp+0.978
vern+0.963
unts+0.920
 cruel+0.908
Neg logit contributions
cy-0.713
 Of-0.689
sc-0.663
 girl-0.656
 down-0.619
Token to
Token ID284
Feature activation-1.09e+00

Pos logit contributions
 strangers+0.152
vern+0.145
 tresp+0.143
unts+0.133
eping+0.133
Neg logit contributions
 Of-0.158
 girl-0.154
cy-0.150
 Sure-0.143
 down-0.142
Token not
Token ID407
Feature activation-5.00e+00

Pos logit contributions
 strangers+0.059
vern+0.058
 tresp+0.057
unts+0.053
eping+0.053
Neg logit contributions
 Of-0.055
cy-0.054
 girl-0.053
 up-0.050
 down-0.049
Token trust
Token ID3774
Feature activation-1.77e+00

Pos logit contributions
 strangers+0.297
vern+0.287
 tresp+0.281
eping+0.264
 cruel+0.257
Neg logit contributions
 Of-0.242
cy-0.240
 girl-0.228
 down-0.218
sc-0.214
Token them
Token ID606
Feature activation-7.24e+00

Pos logit contributions
vern+0.090
 tresp+0.085
 strangers+0.082
unts+0.080
eping+0.079
Neg logit contributions
cy-0.099
 down-0.097
 Of-0.096
 girl-0.095
 up-0.095
Token match
Token ID2872
Feature activation+7.32e+00

Pos logit contributions
 strangers+0.157
 tresp+0.137
vern+0.130
 cruel+0.128
 supposed+0.125
Neg logit contributions
 Of-0.133
cy-0.130
sc-0.128
 Sure-0.123
suit-0.116
Token for
Token ID329
Feature activation+1.47e+00

Pos logit contributions
cy+0.329
 Of+0.324
 girl+0.307
sc+0.304
 down+0.288
Neg logit contributions
 strangers-0.483
 tresp-0.441
vern-0.429
unts-0.410
 cruel-0.408
Token the
Token ID262
Feature activation-1.43e+00

Pos logit contributions
 Of+0.062
 girl+0.057
cy+0.055
 Me+0.055
 onto+0.055
Neg logit contributions
 strangers-0.092
 tresp-0.089
vern-0.089
cod-0.088
unts-0.087
Token group
Token ID1448
Feature activation-1.61e+00

Pos logit contributions
 strangers+0.096
 tresp+0.086
 cruel+0.080
vern+0.079
 supposed+0.077
Neg logit contributions
 Of-0.068
cy-0.067
sc-0.065
 Sure-0.063
 onto-0.059
Token of
Token ID286
Feature activation-2.35e+00

Pos logit contributions
 strangers+0.101
 tresp+0.093
vern+0.091
 cruel+0.086
isdom+0.085
Neg logit contributions
 Of-0.077
cy-0.077
sc-0.074
 girl-0.074
 onto-0.068
Token strangers
Token ID18981
Feature activation-1.58e+01

Pos logit contributions
vern+0.133
 strangers+0.131
 tresp+0.128
ache+0.123
 supposed+0.123
Neg logit contributions
 girl-0.114
 Of-0.113
cy-0.104
 up-0.098
 tin-0.098
Token.
Token ID13
Feature activation-2.70e-01

Pos logit contributions
 strangers+1.089
 tresp+1.008
vern+1.002
 cruel+0.944
unts+0.939
Neg logit contributions
cy-0.680
 Of-0.651
sc-0.634
 girl-0.624
 down-0.595
Token She
Token ID1375
Feature activation-3.15e-01

Pos logit contributions
 strangers+0.018
 tresp+0.016
vern+0.015
unts+0.015
 supposed+0.015
Neg logit contributions
cy-0.012
 Of-0.012
sc-0.012
 girl-0.011
 tin-0.011
Token realized
Token ID6939
Feature activation-5.14e+00

Pos logit contributions
 strangers+0.019
vern+0.017
 tresp+0.017
 supposed+0.016
unts+0.015
Neg logit contributions
cy-0.017
 girl-0.016
 Of-0.016
sc-0.015
 onto-0.015
Token that
Token ID326
Feature activation-1.42e+00

Pos logit contributions
 strangers+0.298
 tresp+0.284
vern+0.283
unts+0.282
cod+0.272
Neg logit contributions
 Of-0.256
 girl-0.243
 up-0.233
 onto-0.232
cy-0.230
Token in
Token ID287
Feature activation+2.43e+00

Pos logit contributions
 strangers+0.088
 tresp+0.080
vern+0.077
 cruel+0.073
unts+0.073
Neg logit contributions
 Of-0.072
cy-0.071
 girl-0.067
sc-0.066
 Sure-0.064
Token€
Token ID26391
Feature activation+5.30e-01

Pos logit contributions
 strangers+0.204
 tresp+0.186
vern+0.178
 supposed+0.175
 hated+0.168
Neg logit contributions
 girl-0.159
 Of-0.158
cy-0.155
sc-0.148
 Sure-0.148
Tokenâ„¢
Token ID8151
Feature activation-7.06e+00

Pos logit contributions
 Of+0.030
cy+0.029
 Sure+0.028
sc+0.027
 girl+0.026
Neg logit contributions
 strangers-0.031
 tresp-0.027
vern-0.026
 cruel-0.026
 supposed-0.024
Tokent
Token ID83
Feature activation-1.62e+00

Pos logit contributions
 strangers+0.465
 tresp+0.416
vern+0.391
 cruel+0.387
isdom+0.375
Neg logit contributions
cy-0.342
 Of-0.338
sc-0.323
 Sure-0.305
 girl-0.303
Token scared
Token ID12008
Feature activation-1.77e+00

Pos logit contributions
 strangers+0.090
 tresp+0.080
vern+0.079
 cruel+0.072
isdom+0.072
Neg logit contributions
 Of-0.090
cy-0.089
 girl-0.087
sc-0.084
 down-0.083
Token of
Token ID286
Feature activation-2.20e+00

Pos logit contributions
 strangers+0.113
 tresp+0.102
vern+0.098
 cruel+0.093
 supposed+0.092
Neg logit contributions
 Of-0.087
cy-0.086
sc-0.081
 girl-0.080
 Sure-0.078
Token strangers
Token ID18981
Feature activation-1.58e+01

Pos logit contributions
 strangers+0.132
vern+0.124
 tresp+0.121
unts+0.117
 cruel+0.114
Neg logit contributions
 Of-0.109
cy-0.101
 girl-0.099
sc-0.096
 Me-0.096
Token anymore
Token ID7471
Feature activation-5.30e+00

Pos logit contributions
 strangers+1.044
 tresp+0.950
vern+0.921
 cruel+0.878
unts+0.870
Neg logit contributions
cy-0.730
 Of-0.730
sc-0.681
 girl-0.674
 Sure-0.650
Token -
Token ID532
Feature activation-3.38e+00

Pos logit contributions
 strangers+0.357
 tresp+0.325
vern+0.317
 cruel+0.304
unts+0.299
Neg logit contributions
 Of-0.237
cy-0.232
 girl-0.217
sc-0.217
 Sure-0.209
Token he
Token ID339
Feature activation+1.58e+00

Pos logit contributions
 strangers+0.230
 tresp+0.210
vern+0.206
unts+0.195
 cruel+0.195
Neg logit contributions
 Of-0.150
cy-0.145
 girl-0.137
sc-0.136
 Sure-0.132
Token was
Token ID373
Feature activation+2.65e+00

Pos logit contributions
cy+0.080
 Of+0.077
 girl+0.077
sc+0.073
 Sure+0.071
Neg logit contributions
 strangers-0.095
vern-0.090
 tresp-0.086
unts-0.080
cod-0.079
Token very
Token ID845
Feature activation-8.82e-01

Pos logit contributions
 Of+0.139
 up+0.137
cy+0.135
 girl+0.135
 down+0.134
Neg logit contributions
 strangers-0.143
vern-0.135
 tresp-0.128
isdom-0.124
cod-0.123
Token you
Token ID345
Feature activation-9.36e-02

Pos logit contributions
 strangers+0.238
 tresp+0.226
vern+0.219
unts+0.214
 cruel+0.208
Neg logit contributions
cy-0.175
 Of-0.166
 girl-0.164
sc-0.160
 down-0.158
Token know
Token ID760
Feature activation-4.26e+00

Pos logit contributions
vern+0.005
Days+0.005
 strangers+0.005
 tresp+0.005
eping+0.005
Neg logit contributions
cy-0.004
 down-0.004
 up-0.004
 into-0.004
 girl-0.004
Token and
Token ID290
Feature activation-2.76e+00

Pos logit contributions
 strangers+0.283
 tresp+0.276
unts+0.275
cod+0.268
vern+0.266
Neg logit contributions
 Of-0.154
 up-0.153
 girl-0.151
cy-0.147
sc-0.146
Token not
Token ID407
Feature activation-4.98e+00

Pos logit contributions
 strangers+0.128
 tresp+0.113
vern+0.108
cod+0.099
unts+0.099
Neg logit contributions
 Of-0.180
cy-0.175
 girl-0.172
 Sure-0.165
sc-0.165
Token follow
Token ID1061
Feature activation+2.84e+00

Pos logit contributions
 strangers+0.270
vern+0.255
 tresp+0.247
cod+0.225
unts+0.225
Neg logit contributions
 Of-0.275
cy-0.270
 girl-0.264
 down-0.251
sc-0.249
Token strangers
Token ID18981
Feature activation-1.58e+01

Pos logit contributions
 Of+0.133
 up+0.131
cy+0.130
 girl+0.130
 down+0.128
Neg logit contributions
 strangers-0.159
vern-0.159
 tresp-0.158
cod-0.151
unts-0.149
Token,
Token ID11
Feature activation+2.83e-01

Pos logit contributions
 strangers+1.088
 tresp+1.015
vern+0.994
unts+0.951
 cruel+0.949
Neg logit contributions
cy-0.668
 Of-0.648
sc-0.626
 girl-0.607
 down-0.580
Token even
Token ID772
Feature activation-2.98e+00

Pos logit contributions
 Of+0.013
 girl+0.013
cy+0.012
sc+0.012
 down+0.012
Neg logit contributions
 strangers-0.017
vern-0.017
 tresp-0.016
unts-0.016
eping-0.015
Token if
Token ID611
Feature activation+2.79e+00

Pos logit contributions
 strangers+0.201
 tresp+0.176
vern+0.164
 cruel+0.164
 supposed+0.162
Neg logit contributions
cy-0.143
 Of-0.141
sc-0.132
 Sure-0.129
 girl-0.126
Token it
Token ID340
Feature activation-6.81e-01

Pos logit contributions
 Of+0.111
 girl+0.104
cy+0.103
sc+0.096
 Sure+0.094
Neg logit contributions
 strangers-0.191
 tresp-0.182
vern-0.181
unts-0.175
cod-0.173
Token's
Token ID338
Feature activation+1.16e+00

Pos logit contributions
 strangers+0.048
 tresp+0.044
vern+0.044
unts+0.041
 cruel+0.041
Neg logit contributions
cy-0.028
 Of-0.028
sc-0.026
 girl-0.026
 Sure-0.024
Token.
Token ID13
Feature activation-1.60e-01

Pos logit contributions
 strangers+0.231
 tresp+0.210
vern+0.200
 supposed+0.193
 cruel+0.192
Neg logit contributions
cy-0.155
 Of-0.154
sc-0.145
 girl-0.139
 Sure-0.137
Token Lily
Token ID20037
Feature activation+3.80e+00

Pos logit contributions
 strangers+0.009
 hated+0.007
unts+0.007
 tresp+0.007
lee+0.007
Neg logit contributions
cy-0.009
sc-0.008
 Of-0.008
 girl-0.008
 tin-0.008
Token learned
Token ID4499
Feature activation-6.43e+00

Pos logit contributions
cy+0.173
 girl+0.167
 Of+0.155
 up+0.149
sc+0.149
Neg logit contributions
 strangers-0.270
 tresp-0.239
vern-0.237
 supposed-0.223
 cruel-0.220
Token that
Token ID326
Feature activation-1.46e+00

Pos logit contributions
 strangers+0.380
 tresp+0.348
unts+0.328
cod+0.325
vern+0.323
Neg logit contributions
 Of-0.338
 up-0.309
 girl-0.308
cy-0.301
 onto-0.301
Token sometimes
Token ID3360
Feature activation-7.34e-01

Pos logit contributions
 strangers+0.085
 tresp+0.075
vern+0.071
 cruel+0.068
 supposed+0.068
Neg logit contributions
cy-0.081
 Of-0.080
sc-0.076
 girl-0.075
 Sure-0.074
Token strangers
Token ID18981
Feature activation-1.58e+01

Pos logit contributions
 strangers+0.051
 tresp+0.047
vern+0.046
unts+0.044
 supposed+0.044
Neg logit contributions
 Of-0.031
cy-0.029
 girl-0.029
sc-0.027
 down-0.026
Token can
Token ID460
Feature activation-5.10e+00

Pos logit contributions
 strangers+0.902
vern+0.869
 tresp+0.841
Days+0.797
unts+0.788
Neg logit contributions
cy-0.866
sc-0.805
 Of-0.796
 up-0.781
 girl-0.779
Token be
Token ID307
Feature activation+1.28e+00

Pos logit contributions
 strangers+0.319
 tresp+0.304
eping+0.296
 supposed+0.292
isdom+0.290
Neg logit contributions
cy-0.221
 up-0.216
 Of-0.209
 girl-0.206
 down-0.201
Token nice
Token ID3621
Feature activation-5.83e-01

Pos logit contributions
 girl+0.074
 down+0.072
 up+0.072
cy+0.071
 into+0.069
Neg logit contributions
 strangers-0.064
vern-0.059
 tresp-0.057
avi-0.054
asts-0.054
Token,
Token ID11
Feature activation+2.84e-01

Pos logit contributions
 strangers+0.036
 tresp+0.032
vern+0.031
 cruel+0.029
 supposed+0.029
Neg logit contributions
 Of-0.030
cy-0.030
sc-0.028
 girl-0.027
 Sure-0.027
Token but
Token ID475
Feature activation+4.03e+00

Pos logit contributions
 Of+0.011
cy+0.010
 girl+0.010
sc+0.010
 Sure+0.009
Neg logit contributions
 strangers-0.021
 tresp-0.020
vern-0.019
unts-0.018
 supposed-0.018
Token is
Token ID318
Feature activation+1.24e+00

Pos logit contributions
 Of+0.116
cy+0.115
sc+0.108
 girl+0.108
 Sure+0.101
Neg logit contributions
 strangers-0.188
 tresp-0.173
vern-0.167
 cruel-0.158
 supposed-0.158
Token dangerous
Token ID4923
Feature activation-1.01e+01

Pos logit contributions
 Of+0.072
 girl+0.069
cy+0.066
sc+0.065
 up+0.064
Neg logit contributions
 strangers-0.066
 tresp-0.058
vern-0.057
cod-0.052
unts-0.052
Token.
Token ID13
Feature activation-6.31e-01

Pos logit contributions
 strangers+0.674
 tresp+0.614
vern+0.592
 cruel+0.564
 supposed+0.559
Neg logit contributions
 Of-0.462
cy-0.459
sc-0.432
 girl-0.431
 Sure-0.407
Token You
Token ID921
Feature activation+5.14e+00

Pos logit contributions
 strangers+0.044
 tresp+0.040
vern+0.038
unts+0.037
 cruel+0.037
Neg logit contributions
cy-0.027
 Of-0.025
 girl-0.024
sc-0.024
 mixture-0.023
Token are
Token ID389
Feature activation-4.20e+00

Pos logit contributions
cy+0.280
 girl+0.265
 Of+0.262
 fits+0.257
sc+0.255
Neg logit contributions
 strangers-0.289
vern-0.267
 tresp-0.256
Days-0.249
ules-0.247
Token strangers
Token ID18981
Feature activation-1.58e+01

Pos logit contributions
 strangers+0.223
vern+0.198
 tresp+0.194
unts+0.180
cod+0.177
Neg logit contributions
 Of-0.236
 girl-0.231
cy-0.227
 up-0.217
 tin-0.214
Token.
Token ID13
Feature activation-7.38e-01

Pos logit contributions
 strangers+1.105
vern+1.042
 tresp+1.032
Days+0.983
isdom+0.979
Neg logit contributions
cy-0.637
 girl-0.620
 Of-0.606
sc-0.601
 down-0.572
Token You
Token ID921
Feature activation+5.13e+00

Pos logit contributions
 strangers+0.053
 tresp+0.048
unts+0.044
vern+0.044
 cruel+0.043
Neg logit contributions
cy-0.031
 Of-0.029
sc-0.028
 girl-0.028
 mixture-0.028
Token are
Token ID389
Feature activation-4.20e+00

Pos logit contributions
cy+0.272
 girl+0.251
sc+0.249
 fits+0.249
 Of+0.237
Neg logit contributions
 strangers-0.290
vern-0.278
ules-0.262
Days-0.258
David-0.255
Token big
Token ID1263
Feature activation-4.37e+00

Pos logit contributions
 strangers+0.213
vern+0.196
 tresp+0.182
isdom+0.175
cod+0.174
Neg logit contributions
 girl-0.234
 Of-0.234
 up-0.224
cy-0.223
 tin-0.217
Token and
Token ID290
Feature activation-3.24e+00

Pos logit contributions
 strangers+0.271
vern+0.250
 tresp+0.245
 supposed+0.231
 cruel+0.228
Neg logit contributions
 girl-0.213
cy-0.210
 Of-0.205
sc-0.193
 down-0.186
Token away
Token ID1497
Feature activation+7.46e+00

Pos logit contributions
 strangers+0.267
 tresp+0.243
vern+0.228
 never+0.226
 supposed+0.225
Neg logit contributions
 Of-0.097
cy-0.091
 girl-0.077
 Sure-0.076
sc-0.075
Token.
Token ID13
Feature activation+3.01e-03

Pos logit contributions
cy+0.391
 Of+0.385
sc+0.363
 girl+0.349
 Sure+0.346
Neg logit contributions
 strangers-0.467
 tresp-0.422
vern-0.391
 cruel-0.377
 supposed-0.373
Token
Token ID198
Feature activation+8.93e-01

Pos logit contributions
cy+0.000
sc+0.000
 girl+0.000
 Of+0.000
 tin+0.000
Neg logit contributions
 strangers-0.000
 tresp-0.000
 hated-0.000
unts-0.000
 never-0.000
Token
Token ID198
Feature activation+8.88e-01

Pos logit contributions
 Of+0.025
 Sure+0.023
cy+0.022
sc+0.022
 onto+0.019
Neg logit contributions
 strangers-0.077
 tresp-0.072
 cruel-0.068
isdom-0.067
vern-0.067
TokenThe
Token ID464
Feature activation-2.93e+00

Pos logit contributions
sc+0.036
 Of+0.036
cy+0.034
 girl+0.033
 Sure+0.033
Neg logit contributions
 strangers-0.063
 tresp-0.057
 supposed-0.054
isdom-0.054
vern-0.054
Token strangers
Token ID18981
Feature activation-1.58e+01

Pos logit contributions
 strangers+0.158
 tresp+0.145
vern+0.143
 supposed+0.133
unts+0.133
Neg logit contributions
 girl-0.166
cy-0.166
 Of-0.165
sc-0.152
 Sure-0.149
Token began
Token ID2540
Feature activation+2.87e+00

Pos logit contributions
 strangers+0.956
vern+0.890
 tresp+0.872
 supposed+0.818
isdom+0.807
Neg logit contributions
cy-0.824
 Of-0.790
 girl-0.776
sc-0.768
 onto-0.725
Token to
Token ID284
Feature activation-1.02e+00

Pos logit contributions
 Of+0.113
cy+0.106
 girl+0.102
 onto+0.101
sc+0.100
Neg logit contributions
 strangers-0.203
vern-0.188
 tresp-0.186
cod-0.178
isdom-0.176
Token get
Token ID651
Feature activation+8.15e-01

Pos logit contributions
 strangers+0.056
vern+0.050
 tresp+0.049
isdom+0.047
 supposed+0.046
Neg logit contributions
cy-0.056
 Of-0.055
 girl-0.054
sc-0.051
 down-0.051
Token dangerous
Token ID4923
Feature activation-1.02e+01

Pos logit contributions
 Of+0.046
cy+0.045
sc+0.043
 Sure+0.042
 girl+0.041
Neg logit contributions
 strangers-0.048
 tresp-0.042
 cruel-0.039
vern-0.038
 supposed-0.037
Token.
Token ID13
Feature activation+4.31e-02

Pos logit contributions
 strangers+0.649
 tresp+0.584
vern+0.559
 cruel+0.534
 supposed+0.530
Neg logit contributions
 Of-0.498
cy-0.497
sc-0.464
 girl-0.460
 Sure-0.450
Token them
Token ID606
Feature activation-7.19e+00

Pos logit contributions
vern+0.032
 tresp+0.032
 strangers+0.031
 supposed+0.030
cod+0.029
Neg logit contributions
 Of-0.025
 girl-0.024
 up-0.023
 Me-0.023
cy-0.022
Token to
Token ID284
Feature activation-8.01e-01

Pos logit contributions
 strangers+0.480
 tresp+0.470
cod+0.465
opl+0.462
eping+0.461
Neg logit contributions
 up-0.286
 Of-0.273
 girl-0.268
 down-0.261
 into-0.245
Token stay
Token ID2652
Feature activation-1.03e+00

Pos logit contributions
 strangers+0.045
 tresp+0.043
cod+0.041
vern+0.041
 supposed+0.040
Neg logit contributions
cy-0.040
 girl-0.039
 Of-0.038
 up-0.037
 tin-0.036
Token away
Token ID1497
Feature activation+7.60e+00

Pos logit contributions
 strangers+0.069
 tresp+0.062
vern+0.059
 cruel+0.057
 supposed+0.056
Neg logit contributions
 Of-0.050
cy-0.047
sc-0.046
 Sure-0.044
 girl-0.043
Token from
Token ID422
Feature activation+5.89e+00

Pos logit contributions
 Of+0.271
cy+0.270
sc+0.245
 girl+0.243
 Sure+0.234
Neg logit contributions
 strangers-0.586
 tresp-0.539
vern-0.520
 cruel-0.501
 supposed-0.498
Token strangers
Token ID18981
Feature activation-1.58e+01

Pos logit contributions
cy+0.254
 girl+0.249
 Of+0.244
 up+0.241
 down+0.239
Neg logit contributions
vern-0.373
 strangers-0.365
 tresp-0.357
unts-0.340
ache-0.334
Token.
Token ID13
Feature activation-3.86e-01

Pos logit contributions
 strangers+1.121
 tresp+1.070
vern+1.063
 cruel+1.002
unts+0.998
Neg logit contributions
cy-0.622
sc-0.581
 Of-0.577
 girl-0.571
 down-0.549
Token But
Token ID887
Feature activation+8.88e+00

Pos logit contributions
 strangers+0.028
 tresp+0.026
vern+0.025
 cruel+0.024
 supposed+0.024
Neg logit contributions
 Of-0.016
cy-0.015
 girl-0.014
sc-0.014
 Sure-0.014
Token they
Token ID484
Feature activation-2.49e-01

Pos logit contributions
cy+0.475
 Of+0.475
sc+0.450
 girl+0.440
 Sure+0.432
Neg logit contributions
 strangers-0.531
 tresp-0.474
vern-0.447
 cruel-0.430
 supposed-0.424
Token did
Token ID750
Feature activation-2.31e+00

Pos logit contributions
vern+0.015
opl+0.015
 strangers+0.015
eping+0.014
isdom+0.014
Neg logit contributions
cy-0.012
 girl-0.012
 boy-0.010
 onto-0.010
 into-0.009
Token not
Token ID407
Feature activation-4.93e+00

Pos logit contributions
 strangers+0.087
 tresp+0.074
unts+0.070
vern+0.067
ills+0.066
Neg logit contributions
 up-0.166
 down-0.160
 Of-0.158
 onto-0.156
cy-0.156
Token there
Token ID612
Feature activation+1.07e+00

Pos logit contributions
 Of+0.036
sc+0.035
cy+0.034
 Sure+0.033
 mixture+0.032
Neg logit contributions
 strangers-0.044
 tresp-0.038
 hated-0.036
 cruel-0.036
vern-0.036
Token was
Token ID373
Feature activation+3.07e+00

Pos logit contributions
 Of+0.042
cy+0.042
sc+0.040
 girl+0.038
 Sure+0.037
Neg logit contributions
 strangers-0.078
 tresp-0.071
vern-0.068
 supposed-0.065
 hated-0.065
Token a
Token ID257
Feature activation+1.90e+00

Pos logit contributions
 Of+0.145
cy+0.144
sc+0.136
 girl+0.133
 Sure+0.131
Neg logit contributions
 strangers-0.200
 tresp-0.180
vern-0.172
 supposed-0.166
 cruel-0.164
Token happy
Token ID3772
Feature activation-2.93e+00

Pos logit contributions
 girl+0.087
cy+0.087
 Of+0.085
 Sure+0.076
sc+0.074
Neg logit contributions
 strangers-0.129
 tresp-0.118
vern-0.116
 supposed-0.110
isdom-0.106
Token little
Token ID1310
Feature activation+7.33e-01

Pos logit contributions
 strangers+0.191
 tresp+0.173
vern+0.165
 cruel+0.158
 supposed+0.157
Neg logit contributions
 Of-0.140
cy-0.139
sc-0.130
 girl-0.128
 Sure-0.125
Token boy
Token ID2933
Feature activation+8.94e+00

Pos logit contributions
sc+0.022
 Of+0.022
antly+0.019
 onto+0.019
 Sure+0.019
Neg logit contributions
 strangers-0.059
 tresp-0.054
 mean-0.052
unts-0.052
 cruel-0.052
Token named
Token ID3706
Feature activation-5.00e+00

Pos logit contributions
cy+0.685
 Of+0.675
 girl+0.648
sc+0.637
 Sure+0.630
Neg logit contributions
 strangers-0.332
 tresp-0.275
vern-0.274
 cruel-0.237
 supposed-0.229
Token Tim
Token ID5045
Feature activation-2.46e+00

Pos logit contributions
 strangers+0.256
 tresp+0.223
vern+0.202
 supposed+0.199
 cruel+0.193
Neg logit contributions
cy-0.303
 Of-0.299
sc-0.293
 girl-0.289
 Sure-0.278
Token.
Token ID13
Feature activation+2.53e-01

Pos logit contributions
 strangers+0.189
 tresp+0.181
vern+0.179
 cruel+0.169
Days+0.165
Neg logit contributions
cy-0.096
 girl-0.085
 down-0.080
 Of-0.078
 up-0.076
Token Tim
Token ID5045
Feature activation-2.43e+00

Pos logit contributions
 Of+0.012
cy+0.012
 Sure+0.011
 girl+0.011
sc+0.011
Neg logit contributions
 strangers-0.017
 tresp-0.016
vern-0.015
 cruel-0.014
 supposed-0.014
Token loved
Token ID6151
Feature activation-5.70e+00

Pos logit contributions
 strangers+0.139
vern+0.128
 tresp+0.124
 cruel+0.113
Days+0.112
Neg logit contributions
cy-0.151
 girl-0.139
 up-0.133
 down-0.130
 Of-0.127
Token the
Token ID262
Feature activation-1.02e+00

Pos logit contributions
 strangers+0.165
 tresp+0.147
vern+0.136
 supposed+0.134
 cruel+0.132
Neg logit contributions
cy-0.132
 Of-0.131
sc-0.124
 Sure-0.119
 girl-0.117
Token table
Token ID3084
Feature activation+4.15e+00

Pos logit contributions
 strangers+0.064
 tresp+0.058
vern+0.055
 cruel+0.053
 supposed+0.053
Neg logit contributions
 Of-0.050
cy-0.050
sc-0.047
 girl-0.046
 Sure-0.045
Token was
Token ID373
Feature activation+2.66e+00

Pos logit contributions
 Of+0.198
cy+0.197
sc+0.184
 girl+0.183
 Sure+0.178
Neg logit contributions
 strangers-0.269
 tresp-0.243
vern-0.233
 cruel-0.223
 supposed-0.221
Token set
Token ID900
Feature activation+5.65e+00

Pos logit contributions
cy+0.125
 Of+0.124
 up+0.123
 down+0.123
 onto+0.122
Neg logit contributions
 strangers-0.171
 tresp-0.149
vern-0.148
cod-0.143
isdom-0.139
Token up
Token ID510
Feature activation+7.49e+00

Pos logit contributions
 Of+0.254
cy+0.253
sc+0.236
 girl+0.233
 Sure+0.227
Neg logit contributions
 strangers-0.383
 tresp-0.347
vern-0.333
 cruel-0.319
 supposed-0.317
Token with
Token ID351
Feature activation+9.48e+00

Pos logit contributions
 Of+0.339
cy+0.334
sc+0.312
 girl+0.308
 Sure+0.302
Neg logit contributions
 strangers-0.507
 tresp-0.462
vern-0.440
 supposed-0.426
 cruel-0.419
Token a
Token ID257
Feature activation+1.41e+00

Pos logit contributions
 Of+0.462
cy+0.458
 girl+0.432
sc+0.421
 Sure+0.412
Neg logit contributions
 strangers-0.599
 tresp-0.544
vern-0.525
 cruel-0.505
 supposed-0.496
Token big
Token ID1263
Feature activation-4.13e+00

Pos logit contributions
 Of+0.075
cy+0.075
 girl+0.071
sc+0.071
 Sure+0.069
Neg logit contributions
 strangers-0.083
 tresp-0.074
vern-0.070
 cruel-0.067
 supposed-0.067
Token,
Token ID11
Feature activation+3.68e-01

Pos logit contributions
 strangers+0.258
 tresp+0.229
vern+0.223
 supposed+0.214
 cruel+0.211
Neg logit contributions
cy-0.210
 Of-0.207
 girl-0.201
sc-0.193
 Sure-0.189
Token red
Token ID2266
Feature activation-1.85e-01

Pos logit contributions
 Of+0.019
cy+0.019
sc+0.018
 girl+0.018
 Sure+0.017
Neg logit contributions
 strangers-0.023
 tresp-0.020
vern-0.019
 cruel-0.018
 supposed-0.018
Token cake
Token ID12187
Feature activation+1.96e+00

Pos logit contributions
 strangers+0.012
 tresp+0.011
vern+0.011
 cruel+0.010
unts+0.010
Neg logit contributions
 Of-0.008
cy-0.008
sc-0.008
 girl-0.008
 Sure-0.008
Token he
Token ID339
Feature activation+1.59e+00

Pos logit contributions
 Of+0.019
cy+0.019
sc+0.017
 girl+0.017
 Sure+0.016
Neg logit contributions
 strangers-0.031
 tresp-0.029
vern-0.027
 cruel-0.026
 supposed-0.026
Token was
Token ID373
Feature activation+2.66e+00

Pos logit contributions
cy+0.085
 girl+0.082
 Of+0.081
sc+0.078
 Sure+0.076
Neg logit contributions
 strangers-0.096
 tresp-0.085
vern-0.084
cod-0.077
unts-0.076
Token climbing
Token ID14281
Feature activation-5.29e+00

Pos logit contributions
 Of+0.134
 up+0.132
cy+0.131
 down+0.131
 girl+0.130
Neg logit contributions
 strangers-0.159
 tresp-0.139
vern-0.137
cod-0.130
unts-0.129
Token all
Token ID477
Feature activation-2.74e+00

Pos logit contributions
 strangers+0.396
 tresp+0.362
vern+0.343
 cruel+0.331
 supposed+0.331
Neg logit contributions
 Of-0.206
cy-0.200
 girl-0.180
sc-0.179
 Sure-0.177
Token the
Token ID262
Feature activation-1.06e+00

Pos logit contributions
 strangers+0.178
 tresp+0.159
 supposed+0.158
 never+0.152
vern+0.147
Neg logit contributions
 Of-0.126
 Sure-0.121
sc-0.116
cy-0.116
 cash-0.113
Token way
Token ID835
Feature activation+8.69e+00

Pos logit contributions
 strangers+0.083
 tresp+0.076
vern+0.073
 cruel+0.070
 supposed+0.070
Neg logit contributions
 Of-0.038
cy-0.038
sc-0.034
 girl-0.033
 Sure-0.033
Token up
Token ID510
Feature activation+7.58e+00

Pos logit contributions
cy+0.352
 Of+0.351
sc+0.323
 girl+0.320
 Sure+0.311
Neg logit contributions
 strangers-0.627
 tresp-0.575
vern-0.551
 cruel-0.532
 supposed-0.525
Token to
Token ID284
Feature activation-9.90e-01

Pos logit contributions
 Of+0.363
cy+0.360
sc+0.335
 girl+0.333
 Sure+0.326
Neg logit contributions
 strangers-0.495
 tresp-0.445
vern-0.424
 cruel-0.407
 supposed-0.405
Token the
Token ID262
Feature activation-1.09e+00

Pos logit contributions
 strangers+0.062
 tresp+0.054
vern+0.051
 supposed+0.049
 cruel+0.049
Neg logit contributions
cy-0.051
 Of-0.051
sc-0.050
 girl-0.047
 Sure-0.046
Token top
Token ID1353
Feature activation+4.93e+00

Pos logit contributions
 strangers+0.071
 tresp+0.064
vern+0.060
 cruel+0.058
 supposed+0.058
Neg logit contributions
 Of-0.053
cy-0.052
sc-0.049
 girl-0.048
 Sure-0.047
Token of
Token ID286
Feature activation-2.29e+00

Pos logit contributions
 Of+0.272
cy+0.269
sc+0.251
 girl+0.249
 Sure+0.248
Neg logit contributions
 strangers-0.284
 tresp-0.249
vern-0.235
unts-0.227
 cruel-0.225
Token envelop
Token ID16441
Feature activation-1.90e+00

Pos logit contributions
 strangers+0.076
 tresp+0.069
vern+0.065
 cruel+0.063
 supposed+0.062
Neg logit contributions
 Of-0.057
cy-0.057
sc-0.054
 girl-0.052
 Sure-0.052
Tokenes
Token ID274
Feature activation-1.23e+00

Pos logit contributions
 strangers+0.125
 tresp+0.112
vern+0.108
 cruel+0.104
 supposed+0.102
Neg logit contributions
cy-0.090
 Of-0.089
sc-0.084
 girl-0.083
 Sure-0.079
Token united
Token ID16503
Feature activation-2.57e+00

Pos logit contributions
 strangers+0.076
 tresp+0.070
vern+0.069
 supposed+0.065
 cruel+0.065
Neg logit contributions
cy-0.060
sc-0.058
 Of-0.057
 girl-0.056
 onto-0.054
Token and
Token ID290
Feature activation-2.31e+00

Pos logit contributions
 strangers+0.164
 tresp+0.149
vern+0.144
 cruel+0.137
 supposed+0.135
Neg logit contributions
cy-0.125
 Of-0.124
sc-0.117
 girl-0.116
 Sure-0.111
Token became
Token ID2627
Feature activation-3.10e+00

Pos logit contributions
 strangers+0.131
 tresp+0.116
vern+0.112
 cruel+0.105
unts+0.104
Neg logit contributions
 Of-0.129
cy-0.128
 girl-0.121
sc-0.121
 Sure-0.117
Token one
Token ID530
Feature activation+8.30e+00

Pos logit contributions
 strangers+0.188
 tresp+0.169
vern+0.161
 cruel+0.153
 supposed+0.152
Neg logit contributions
 Of-0.160
cy-0.160
sc-0.150
 girl-0.149
 Sure-0.145
Token big
Token ID1263
Feature activation-3.71e+00

Pos logit contributions
 Of+0.505
cy+0.499
sc+0.486
 Sure+0.472
 onto+0.454
Neg logit contributions
 strangers-0.420
 tresp-0.370
vern-0.349
 cruel-0.332
unts-0.324
Token,
Token ID11
Feature activation+7.49e-01

Pos logit contributions
 strangers+0.232
 tresp+0.209
vern+0.201
 cruel+0.191
 supposed+0.190
Neg logit contributions
 Of-0.185
cy-0.185
 girl-0.173
sc-0.172
 Sure-0.167
Token happy
Token ID3772
Feature activation-2.78e+00

Pos logit contributions
 Of+0.038
cy+0.038
 girl+0.036
sc+0.036
 Sure+0.035
Neg logit contributions
 strangers-0.046
 tresp-0.042
vern-0.040
 supposed-0.038
 cruel-0.038
Token family
Token ID1641
Feature activation-3.29e+00

Pos logit contributions
 strangers+0.171
 tresp+0.152
vern+0.143
 cruel+0.138
unts+0.137
Neg logit contributions
cy-0.144
 Of-0.143
sc-0.138
 Sure-0.130
 girl-0.130
Token.
Token ID13
Feature activation+8.60e-02

Pos logit contributions
 strangers+0.213
 tresp+0.192
vern+0.184
 cruel+0.176
 supposed+0.174
Neg logit contributions
 Of-0.158
cy-0.158
 girl-0.147
sc-0.146
 Sure-0.142
Token to
Token ID284
Feature activation-7.36e-01

Pos logit contributions
 Of+0.087
cy+0.084
 girl+0.079
sc+0.079
 Sure+0.077
Neg logit contributions
 strangers-0.126
 tresp-0.115
vern-0.113
 cruel-0.105
cod-0.104
Token become
Token ID1716
Feature activation-1.80e+00

Pos logit contributions
 strangers+0.043
 tresp+0.039
vern+0.038
 cruel+0.036
 supposed+0.035
Neg logit contributions
 Of-0.039
cy-0.039
 girl-0.037
sc-0.036
 down-0.035
Token a
Token ID257
Feature activation+1.67e+00

Pos logit contributions
 strangers+0.112
 tresp+0.101
vern+0.096
 cruel+0.092
 supposed+0.091
Neg logit contributions
 Of-0.090
cy-0.090
 girl-0.085
sc-0.084
 Sure-0.081
Token great
Token ID1049
Feature activation-2.70e+00

Pos logit contributions
 Of+0.093
cy+0.091
sc+0.087
 Sure+0.084
 girl+0.083
Neg logit contributions
 strangers-0.095
 tresp-0.086
vern-0.081
 cruel-0.078
unts-0.077
Token basketball
Token ID9669
Feature activation-1.57e+00

Pos logit contributions
 strangers+0.166
 tresp+0.148
vern+0.140
unts+0.136
 supposed+0.135
Neg logit contributions
 Of-0.138
cy-0.136
sc-0.131
 Sure-0.126
 girl-0.122
Token player
Token ID2137
Feature activation+8.33e+00

Pos logit contributions
 strangers+0.100
 tresp+0.091
vern+0.086
 supposed+0.082
 cruel+0.082
Neg logit contributions
 Of-0.076
cy-0.076
sc-0.070
 girl-0.070
 Sure-0.069
Token.
Token ID13
Feature activation+3.21e-01

Pos logit contributions
 Of+0.392
cy+0.391
sc+0.365
 girl+0.362
 Sure+0.352
Neg logit contributions
 strangers-0.544
 tresp-0.491
vern-0.472
 cruel-0.451
 supposed-0.447
Token
Token ID220
Feature activation+3.36e+00

Pos logit contributions
cy+0.014
 Of+0.014
sc+0.013
 girl+0.013
 Sure+0.012
Neg logit contributions
 strangers-0.022
 tresp-0.020
vern-0.020
unts-0.019
 cruel-0.019
Token Thanks
Token ID6930
Feature activation+7.60e+00

Pos logit contributions
 Of+0.136
cy+0.134
sc+0.124
 girl+0.122
 Sure+0.120
Neg logit contributions
 strangers-0.245
 tresp-0.223
vern-0.213
 cruel-0.207
 supposed-0.204
Token to
Token ID284
Feature activation-6.45e-01

Pos logit contributions
cy+0.395
 Of+0.391
sc+0.383
 girl+0.358
 Sure+0.354
Neg logit contributions
 strangers-0.463
 tresp-0.411
vern-0.380
 cruel-0.373
 supposed-0.368
Token the
Token ID262
Feature activation-8.15e-01

Pos logit contributions
 strangers+0.044
vern+0.043
 tresp+0.041
ache+0.040
cod+0.039
Neg logit contributions
 Of-0.028
cy-0.026
 Me-0.024
 down-0.024
 Sure-0.024
Token reached
Token ID4251
Feature activation-1.10e-01

Pos logit contributions
 strangers+0.114
 never+0.114
 hated+0.101
 missed+0.098
 tresp+0.093
Neg logit contributions
umm-0.213
 Of-0.212
sc-0.199
cy-0.187
 mixture-0.186
Token for
Token ID329
Feature activation+1.45e+00

Pos logit contributions
 strangers+0.006
 tresp+0.005
 supposed+0.005
 never+0.005
vern+0.005
Neg logit contributions
 Of-0.006
sc-0.006
cy-0.006
umm-0.006
 girl-0.005
Token the
Token ID262
Feature activation-1.32e+00

Pos logit contributions
 Of+0.055
cy+0.052
 girl+0.051
 onto+0.049
 Sure+0.048
Neg logit contributions
 strangers-0.103
 tresp-0.097
vern-0.095
unts-0.092
 cruel-0.092
Token ball
Token ID2613
Feature activation+2.41e-03

Pos logit contributions
 strangers+0.090
 tresp+0.082
vern+0.079
 cruel+0.076
 supposed+0.075
Neg logit contributions
 Of-0.059
cy-0.059
 girl-0.055
sc-0.054
 Sure-0.053
Token.
Token ID13
Feature activation-4.80e-01

Pos logit contributions
 Of+0.000
cy+0.000
 girl+0.000
sc+0.000
 Sure+0.000
Neg logit contributions
 strangers-0.000
 tresp-0.000
vern-0.000
 supposed-0.000
 cruel-0.000
Token Suddenly
Token ID24975
Feature activation+7.21e+00

Pos logit contributions
 strangers+0.028
 tresp+0.024
unts+0.023
 hated+0.023
isdom+0.022
Neg logit contributions
cy-0.025
sc-0.024
 girl-0.023
 mixture-0.022
cer-0.022
Token,
Token ID11
Feature activation+2.93e-01

Pos logit contributions
 Of+0.359
cy+0.358
sc+0.335
 girl+0.330
 Sure+0.324
Neg logit contributions
 strangers-0.457
 tresp-0.411
vern-0.392
 cruel-0.375
 supposed-0.371
Token she
Token ID673
Feature activation+1.24e+00

Pos logit contributions
sc+0.017
cy+0.017
 Of+0.017
umm+0.016
suit+0.016
Neg logit contributions
 strangers-0.016
 tresp-0.013
 never-0.012
 cruel-0.012
 mean-0.012
Token saw
Token ID2497
Feature activation-2.54e+00

Pos logit contributions
cy+0.061
 girl+0.061
 into+0.057
 down+0.057
 onto+0.056
Neg logit contributions
 strangers-0.078
vern-0.075
 tresp-0.071
isdom-0.067
 supposed-0.065
Token a
Token ID257
Feature activation+1.27e+00

Pos logit contributions
 strangers+0.171
 tresp+0.154
vern+0.148
 cruel+0.142
 supposed+0.141
Neg logit contributions
 Of-0.117
cy-0.117
sc-0.109
 girl-0.107
 Sure-0.105
Token cute
Token ID13779
Feature activation-2.38e+00

Pos logit contributions
 girl+0.066
cy+0.066
 Of+0.065
sc+0.061
 Sure+0.060
Neg logit contributions
 strangers-0.076
 tresp-0.067
vern-0.066
 supposed-0.062
isdom-0.061
Token,
Token ID11
Feature activation+3.32e-01

Pos logit contributions
cy+0.251
 Of+0.237
sc+0.232
 girl+0.225
 mixture+0.223
Neg logit contributions
 strangers-0.214
 tresp-0.194
 hated-0.160
vern-0.159
 cruel-0.157
Token he
Token ID339
Feature activation+1.51e+00

Pos logit contributions
cy+0.019
sc+0.018
 Of+0.018
 fits+0.017
umm+0.017
Neg logit contributions
 strangers-0.019
 tresp-0.016
 never-0.015
 hated-0.014
 enemies-0.014
Token saw
Token ID2497
Feature activation-2.31e+00

Pos logit contributions
cy+0.083
 girl+0.078
sc+0.078
 Of+0.077
 Sure+0.073
Neg logit contributions
 strangers-0.088
vern-0.082
 tresp-0.080
 supposed-0.074
 cruel-0.073
Token a
Token ID257
Feature activation+1.54e+00

Pos logit contributions
 strangers+0.162
 tresp+0.149
vern+0.144
 supposed+0.137
unts+0.137
Neg logit contributions
 Of-0.098
cy-0.096
 girl-0.091
sc-0.089
 Sure-0.087
Token big
Token ID1263
Feature activation-4.10e+00

Pos logit contributions
cy+0.085
 Of+0.085
 girl+0.081
sc+0.080
 Sure+0.077
Neg logit contributions
 strangers-0.088
 tresp-0.078
vern-0.075
 supposed-0.071
 cruel-0.070
Token,
Token ID11
Feature activation+2.89e-01

Pos logit contributions
 strangers+0.265
 tresp+0.240
vern+0.235
 supposed+0.222
 cruel+0.220
Neg logit contributions
cy-0.196
 Of-0.194
 girl-0.185
sc-0.179
 Sure-0.174
Token angry
Token ID7954
Feature activation-5.28e+00

Pos logit contributions
 Of+0.015
cy+0.015
 girl+0.015
sc+0.014
 Sure+0.014
Neg logit contributions
 strangers-0.017
 tresp-0.015
vern-0.015
 supposed-0.014
unts-0.014
Token cat
Token ID3797
Feature activation-3.99e+00

Pos logit contributions
 strangers+0.311
 tresp+0.279
vern+0.275
 supposed+0.257
 cruel+0.254
Neg logit contributions
 Of-0.280
cy-0.278
 girl-0.268
sc-0.255
 Sure-0.254
Token coming
Token ID2406
Feature activation-3.79e+00

Pos logit contributions
 strangers+0.266
vern+0.256
 tresp+0.242
 cruel+0.230
isdom+0.229
Neg logit contributions
cy-0.170
 Of-0.164
sc-0.162
 girl-0.162
 down-0.158
Token towards
Token ID3371
Feature activation+6.79e+00

Pos logit contributions
 strangers+0.310
 tresp+0.285
 supposed+0.265
vern+0.264
 cruel+0.263
Neg logit contributions
 Of-0.124
cy-0.116
sc-0.104
 girl-0.103
 mixture-0.102
Token him
Token ID683
Feature activation-5.18e+00

Pos logit contributions
 Of+0.405
cy+0.397
 girl+0.382
 down+0.376
 onto+0.373
Neg logit contributions
 strangers-0.335
vern-0.330
 tresp-0.320
 cruel-0.294
 supposed-0.291
Token it
Token ID340
Feature activation-6.32e-01

Pos logit contributions
 strangers+0.108
 tresp+0.091
vern+0.086
 cruel+0.082
unts+0.082
Neg logit contributions
cy-0.101
 Of-0.100
sc-0.098
 girl-0.093
 Sure-0.092
Token,
Token ID11
Feature activation+4.48e-01

Pos logit contributions
 strangers+0.034
 never+0.031
 understand+0.030
vern+0.030
 often+0.029
Neg logit contributions
 Of-0.033
cy-0.033
ASH-0.031
 Sure-0.030
sc-0.030
Token before
Token ID878
Feature activation+5.83e+00

Pos logit contributions
 Of+0.024
cy+0.024
 girl+0.023
 Sure+0.022
sc+0.022
Neg logit contributions
 strangers-0.027
 tresp-0.024
vern-0.023
 cruel-0.022
 supposed-0.022
Token putting
Token ID5137
Feature activation+1.18e+00

Pos logit contributions
 Of+0.296
 girl+0.281
cy+0.276
 Sure+0.273
 onto+0.272
Neg logit contributions
 strangers-0.355
 tresp-0.323
vern-0.308
cod-0.307
 cruel-0.296
Token on
Token ID319
Feature activation+3.70e+00

Pos logit contributions
 Of+0.065
cy+0.063
 Sure+0.061
sc+0.060
 girl+0.059
Neg logit contributions
 strangers-0.070
 tresp-0.060
vern-0.057
 cruel-0.053
 supposed-0.053
Token her
Token ID607
Feature activation-1.39e-01

Pos logit contributions
cy+0.166
 Of+0.165
 girl+0.155
sc+0.155
 onto+0.147
Neg logit contributions
 strangers-0.244
 tresp-0.225
vern-0.217
 cruel-0.209
 supposed-0.207
Token shoes
Token ID10012
Feature activation+4.23e-01

Pos logit contributions
 strangers+0.010
 tresp+0.009
vern+0.009
 cruel+0.008
 supposed+0.008
Neg logit contributions
 Of-0.006
cy-0.006
sc-0.005
 girl-0.005
 Sure-0.005
Token.
Token ID13
Feature activation-4.40e-02

Pos logit contributions
 Of+0.021
cy+0.020
 girl+0.019
sc+0.019
 Sure+0.019
Neg logit contributions
 strangers-0.027
 tresp-0.024
vern-0.023
 supposed-0.022
 cruel-0.022
Token She
Token ID1375
Feature activation+7.26e-03

Pos logit contributions
 strangers+0.003
unts+0.002
vern+0.002
 tresp+0.002
isdom+0.002
Neg logit contributions
cy-0.002
sc-0.002
 girl-0.002
 Of-0.002
 tin-0.002
Token waved
Token ID26834
Feature activation+3.21e+00

Pos logit contributions
cy+0.000
 Of+0.000
 girl+0.000
sc+0.000
 Sure+0.000
Neg logit contributions
 strangers-0.000
 tresp-0.000
vern-0.000
 supposed-0.000
 cruel-0.000
Token goodbye
Token ID24829
Feature activation+2.53e-01

Pos logit contributions
cy+0.166
 Of+0.163
sc+0.158
 Sure+0.149
 girl+0.149
Neg logit contributions
 strangers-0.198
 tresp-0.172
vern-0.166
 cruel-0.160
unts-0.156
Token't
Token ID470
Feature activation-3.24e+00

Pos logit contributions
 strangers+0.343
 tresp+0.305
cod+0.296
 cruel+0.286
isdom+0.277
Neg logit contributions
 Of-0.310
 onto-0.293
sc-0.290
cy-0.289
 up-0.288
Token have
Token ID423
Feature activation-3.52e+00

Pos logit contributions
 strangers+0.153
 tresp+0.140
vern+0.139
 cruel+0.123
isdom+0.123
Neg logit contributions
cy-0.207
 girl-0.202
 Of-0.198
 down-0.189
sc-0.188
Token any
Token ID597
Feature activation-6.60e-01

Pos logit contributions
 strangers+0.227
 tresp+0.213
vern+0.211
cod+0.201
unts+0.199
Neg logit contributions
 Of-0.154
cy-0.150
 girl-0.148
 down-0.139
sc-0.138
Token time
Token ID640
Feature activation-1.94e+00

Pos logit contributions
 strangers+0.040
 tresp+0.034
vern+0.033
 supposed+0.032
 cruel+0.031
Neg logit contributions
cy-0.037
 Of-0.036
sc-0.034
 Sure-0.034
 girl-0.032
Token to
Token ID284
Feature activation-8.53e-01

Pos logit contributions
 strangers+0.132
 tresp+0.122
vern+0.120
unts+0.113
 cruel+0.113
Neg logit contributions
 Of-0.084
cy-0.083
 girl-0.078
sc-0.076
 Sure-0.074
Token get
Token ID651
Feature activation+9.87e-01

Pos logit contributions
 strangers+0.050
 tresp+0.047
vern+0.045
 cruel+0.044
unts+0.043
Neg logit contributions
cy-0.043
 Of-0.043
 girl-0.041
 onto-0.039
 up-0.039
Token a
Token ID257
Feature activation+1.62e+00

Pos logit contributions
 Of+0.050
cy+0.049
sc+0.048
 Sure+0.047
 girl+0.044
Neg logit contributions
 strangers-0.064
 tresp-0.055
 supposed-0.053
vern-0.053
 cruel-0.052
Token massage
Token ID26900
Feature activation+3.02e+00

Pos logit contributions
cy+0.084
 Of+0.081
sc+0.078
 Sure+0.074
ASH+0.073
Neg logit contributions
 strangers-0.103
 tresp-0.088
vern-0.087
 cruel-0.084
ache-0.082
Token.
Token ID13
Feature activation+5.85e-03

Pos logit contributions
 Of+0.172
cy+0.163
 Sure+0.161
sc+0.154
Wow+0.142
Neg logit contributions
 strangers-0.177
 tresp-0.147
ache-0.132
vern-0.131
 supposed-0.128
Token She
Token ID1375
Feature activation+8.72e-02

Pos logit contributions
cy+0.000
sc+0.000
 Of+0.000
 girl+0.000
 tin+0.000
Neg logit contributions
 strangers-0.000
 tresp-0.000
 hated-0.000
vern-0.000
 supposed-0.000
Token started
Token ID2067
Feature activation+1.80e+00

Pos logit contributions
cy+0.004
 girl+0.004
 Of+0.004
sc+0.004
 tin+0.004
Neg logit contributions
 strangers-0.005
vern-0.005
 tresp-0.005
 supposed-0.005
unts-0.005
Token and
Token ID290
Feature activation-2.60e+00

Pos logit contributions
 Of+0.050
cy+0.049
sc+0.046
 girl+0.046
 Sure+0.045
Neg logit contributions
 strangers-0.058
 tresp-0.052
vern-0.049
 cruel-0.047
 supposed-0.047
Token started
Token ID2067
Feature activation+1.70e+00

Pos logit contributions
 strangers+0.146
 tresp+0.131
 never+0.118
 cruel+0.117
unts+0.115
Neg logit contributions
 Of-0.144
cy-0.142
sc-0.139
 Sure-0.133
 girl-0.130
Token applaud
Token ID22517
Feature activation-1.24e+00

Pos logit contributions
 Of+0.093
cy+0.092
sc+0.086
 girl+0.086
 Sure+0.084
Neg logit contributions
 strangers-0.099
 tresp-0.088
vern-0.085
 cruel-0.080
 supposed-0.078
Tokening
Token ID278
Feature activation+4.22e+00

Pos logit contributions
 strangers+0.088
 tresp+0.078
vern+0.075
 cruel+0.073
unts+0.073
Neg logit contributions
cy-0.051
 Of-0.050
sc-0.048
 Sure-0.047
 girl-0.046
Token louder
Token ID27089
Feature activation+3.62e+00

Pos logit contributions
cy+0.202
 Of+0.198
 Sure+0.188
sc+0.185
 girl+0.182
Neg logit contributions
 strangers-0.276
 tresp-0.244
vern-0.225
 cruel-0.224
unts-0.222
Token.
Token ID13
Feature activation+9.47e-02

Pos logit contributions
cy+0.181
 Of+0.180
sc+0.169
 girl+0.166
 Sure+0.164
Neg logit contributions
 strangers-0.228
 tresp-0.204
vern-0.194
 cruel-0.187
unts-0.185
Token The
Token ID383
Feature activation-9.03e-01

Pos logit contributions
cy+0.004
 girl+0.004
sc+0.004
 Of+0.004
 tin+0.004
Neg logit contributions
 strangers-0.006
 tresp-0.006
unts-0.005
vern-0.005
 hated-0.005
Token performer
Token ID26960
Feature activation+6.69e+00

Pos logit contributions
 strangers+0.048
vern+0.048
 tresp+0.044
 supposed+0.042
unts+0.041
Neg logit contributions
 girl-0.053
cy-0.049
 Of-0.048
sc-0.044
 boy-0.044
Token was
Token ID373
Feature activation+2.82e+00

Pos logit contributions
cy+0.342
 Of+0.340
 girl+0.321
sc+0.319
 Sure+0.307
Neg logit contributions
 strangers-0.412
 tresp-0.369
vern-0.357
 supposed-0.336
 cruel-0.336
Token so
Token ID523
Feature activation+2.35e+00

Pos logit contributions
 Of+0.136
cy+0.133
 girl+0.128
 up+0.127
 onto+0.125
Neg logit contributions
 strangers-0.181
 tresp-0.160
vern-0.155
isdom-0.148
cod-0.148
Token embarrassed
Token ID21100
Feature activation-2.99e+00

Pos logit contributions
 Of+0.146
cy+0.143
 girl+0.138
sc+0.132
 down+0.130
Neg logit contributions
 strangers-0.125
 tresp-0.108
vern-0.099
cod-0.093
isdom-0.093
Token sun
Token ID4252
Feature activation+2.18e+00

Pos logit contributions
 strangers+0.154
 tresp+0.128
vern+0.120
 cruel+0.119
 enemies+0.114
Neg logit contributions
 Of-0.150
cy-0.147
 Sure-0.142
sc-0.141
 girl-0.135
Tokenfl
Token ID2704
Feature activation+4.78e+00

Pos logit contributions
 Of+0.083
sc+0.081
 Sure+0.076
cy+0.071
 girl+0.067
Neg logit contributions
 strangers-0.158
 tresp-0.139
ache-0.135
eping-0.132
vern-0.131
Tokenowers
Token ID3618
Feature activation-5.13e+00

Pos logit contributions
 Of+0.289
 girl+0.277
sc+0.274
 Sure+0.272
cy+0.271
Neg logit contributions
 strangers-0.234
 tresp-0.206
vern-0.199
 supposed-0.185
unts-0.183
Token again
Token ID757
Feature activation+4.56e+00

Pos logit contributions
 strangers+0.407
 tresp+0.380
vern+0.368
unts+0.354
 cruel+0.353
Neg logit contributions
cy-0.169
 Of-0.165
sc-0.151
 girl-0.150
 Sure-0.138
Token.
Token ID13
Feature activation-1.92e-01

Pos logit contributions
cy+0.184
 Of+0.179
 girl+0.168
sc+0.166
 Sure+0.156
Neg logit contributions
 strangers-0.324
 tresp-0.304
vern-0.296
 cruel-0.281
 supposed-0.279
Token<|endoftext|>
Token ID50256
Feature activation-6.75e+00

Pos logit contributions
 strangers+0.011
 tresp+0.010
unts+0.009
 hated+0.009
vern+0.009
Neg logit contributions
cy-0.010
sc-0.010
 mixture-0.010
 tin-0.010
 Of-0.009
TokenL
Token ID43
Feature activation+3.75e+00

Pos logit contributions
 strangers+0.468
 tresp+0.422
unts+0.395
vern+0.393
 supposed+0.379
Neg logit contributions
 Of-0.276
cy-0.257
 Sure-0.250
 mixture-0.244
sc-0.244
Tokenily
Token ID813
Feature activation-1.83e+00

Pos logit contributions
cy+0.206
 Of+0.202
 girl+0.194
sc+0.190
 Sure+0.185
Neg logit contributions
 strangers-0.216
 tresp-0.196
vern-0.186
 cruel-0.183
cod-0.175
Token and
Token ID290
Feature activation-2.50e+00

Pos logit contributions
 strangers+0.125
vern+0.116
 tresp+0.113
 cruel+0.108
 supposed+0.104
Neg logit contributions
cy-0.089
 girl-0.080
 Of-0.077
sc-0.074
 Sure-0.073
Token Ben
Token ID3932
Feature activation+2.55e+00

Pos logit contributions
 strangers+0.161
vern+0.152
 tresp+0.152
cod+0.142
 cruel+0.140
Neg logit contributions
 Of-0.120
cy-0.118
 girl-0.112
 Sure-0.104
 down-0.103
Token were
Token ID547
Feature activation-3.91e+00

Pos logit contributions
cy+0.139
 girl+0.120
 Of+0.108
 tin+0.107
ed+0.107
Neg logit contributions
 strangers-0.163
vern-0.156
 tresp-0.146
 cruel-0.146
Days-0.138
Token."
Token ID526
Feature activation-3.12e-01

Pos logit contributions
 strangers+0.380
 tresp+0.340
vern+0.317
 supposed+0.310
 cruel+0.302
Neg logit contributions
cy-0.314
 Of-0.305
 girl-0.286
sc-0.283
 Sure-0.280
Token
Token ID220
Feature activation+3.10e+00

Pos logit contributions
 strangers+0.020
 tresp+0.017
vern+0.017
unts+0.017
 hated+0.017
Neg logit contributions
cy-0.015
sc-0.015
 tin-0.014
 Of-0.013
 girl-0.013
Token
Token ID198
Feature activation+9.60e-01

Pos logit contributions
 Of+0.126
cy+0.125
sc+0.115
 girl+0.114
 Sure+0.112
Neg logit contributions
 strangers-0.224
 tresp-0.205
vern-0.196
 cruel-0.190
 supposed-0.188
Token
Token ID198
Feature activation+9.64e-01

Pos logit contributions
cy+0.041
 Of+0.041
sc+0.038
 girl+0.037
 Sure+0.036
Neg logit contributions
 strangers-0.067
 tresp-0.061
vern-0.059
 cruel-0.057
 supposed-0.056
TokenHer
Token ID9360
Feature activation-9.28e-01

Pos logit contributions
 Of+0.055
cy+0.053
 girl+0.050
sc+0.050
 Sure+0.050
Neg logit contributions
 strangers-0.055
 tresp-0.050
vern-0.046
 supposed-0.044
 cruel-0.044
Token mom
Token ID1995
Feature activation-1.22e+00

Pos logit contributions
 strangers+0.057
 tresp+0.051
vern+0.049
 cruel+0.047
 supposed+0.046
Neg logit contributions
 Of-0.048
cy-0.048
 girl-0.045
sc-0.045
 Sure-0.044
Token smiled
Token ID13541
Feature activation+1.35e+00

Pos logit contributions
 strangers+0.083
 tresp+0.075
vern+0.073
 supposed+0.069
 cruel+0.069
Neg logit contributions
cy-0.056
 Of-0.055
 girl-0.052
sc-0.051
 Sure-0.049
Token and
Token ID290
Feature activation-2.59e+00

Pos logit contributions
sc+0.085
cy+0.085
 Of+0.085
 Sure+0.080
 Me+0.076
Neg logit contributions
 strangers-0.065
 tresp-0.052
vern-0.052
unts-0.050
 cruel-0.050
Token said
Token ID531
Feature activation+3.92e+00

Pos logit contributions
 strangers+0.132
 tresp+0.115
 cruel+0.111
 hated+0.110
 never+0.110
Neg logit contributions
cy-0.150
sc-0.149
 Of-0.142
suit-0.136
umm-0.133
Token,
Token ID11
Feature activation+5.07e-01

Pos logit contributions
cy+0.218
 Of+0.209
sc+0.201
 girl+0.196
 Sure+0.193
Neg logit contributions
 strangers-0.226
 tresp-0.204
vern-0.195
 cruel-0.185
unts-0.178
Token "
Token ID366
Feature activation-2.90e+00

Pos logit contributions
cy+0.026
 Of+0.025
sc+0.024
 girl+0.023
 Sure+0.023
Neg logit contributions
 strangers-0.031
 tresp-0.028
vern-0.027
 cruel-0.026
 supposed-0.026
Token,
Token ID11
Feature activation+4.45e-01

Pos logit contributions
 Of+0.512
cy+0.508
 girl+0.480
sc+0.465
 Sure+0.454
Neg logit contributions
 strangers-0.769
 tresp-0.702
vern-0.673
 supposed-0.656
 cruel-0.649
Token but
Token ID475
Feature activation+4.23e+00

Pos logit contributions
 Of+0.019
 girl+0.018
cy+0.017
sc+0.017
 Sure+0.016
Neg logit contributions
 strangers-0.031
 tresp-0.029
vern-0.028
 supposed-0.027
unts-0.027
Token be
Token ID307
Feature activation+1.51e+00

Pos logit contributions
cy+0.227
 Of+0.226
sc+0.215
 girl+0.210
 Sure+0.207
Neg logit contributions
 strangers-0.252
 tresp-0.224
vern-0.211
 cruel-0.203
 supposed-0.200
Token careful
Token ID8161
Feature activation-6.50e-01

Pos logit contributions
 Of+0.096
cy+0.095
 girl+0.092
sc+0.091
 Sure+0.089
Neg logit contributions
 strangers-0.074
 tresp-0.064
vern-0.060
 cruel-0.056
unts-0.055
Token and
Token ID290
Feature activation-2.63e+00

Pos logit contributions
 strangers+0.046
 tresp+0.043
vern+0.041
 cruel+0.040
unts+0.039
Neg logit contributions
 Of-0.025
cy-0.025
 up-0.024
 girl-0.024
 down-0.024
Token don
Token ID836
Feature activation-3.97e+00

Pos logit contributions
 strangers+0.143
 tresp+0.128
vern+0.125
unts+0.118
 cruel+0.113
Neg logit contributions
 Of-0.149
cy-0.146
 girl-0.142
 down-0.142
 Sure-0.138
Token't
Token ID470
Feature activation-3.18e+00

Pos logit contributions
 strangers+0.257
 tresp+0.231
cod+0.219
 liar+0.219
 cruel+0.219
Neg logit contributions
 Of-0.185
 onto-0.184
 up-0.178
sc-0.177
cy-0.175
Token lean
Token ID10904
Feature activation-3.41e+00

Pos logit contributions
 strangers+0.189
 tresp+0.177
vern+0.176
unts+0.161
 cruel+0.160
Neg logit contributions
cy-0.165
 Of-0.159
 down-0.154
 girl-0.154
 onto-0.145
Token too
Token ID1165
Feature activation+2.40e-02

Pos logit contributions
 strangers+0.278
 tresp+0.260
vern+0.256
unts+0.244
 cruel+0.241
Neg logit contributions
cy-0.105
 Of-0.099
sc-0.095
 down-0.094
 onto-0.090
Token far
Token ID1290
Feature activation-3.43e+00

Pos logit contributions
cy+0.001
 down+0.001
 girl+0.001
 Of+0.001
sc+0.001
Neg logit contributions
 strangers-0.001
 tresp-0.001
vern-0.001
isdom-0.001
cod-0.001
Token,"
Token ID553
Feature activation-5.02e-01

Pos logit contributions
 strangers+0.208
 tresp+0.176
vern+0.166
 cruel+0.162
 supposed+0.159
Neg logit contributions
 Of-0.189
cy-0.183
 Sure-0.174
 Me-0.165
sc-0.165
Token great
Token ID1049
Feature activation-3.01e+00

Pos logit contributions
cy+0.071
 girl+0.069
 Of+0.069
sc+0.066
 Sure+0.065
Neg logit contributions
 strangers-0.073
 tresp-0.062
vern-0.059
isdom-0.057
 cruel-0.057
Token time
Token ID640
Feature activation-2.12e+00

Pos logit contributions
 strangers+0.160
 tresp+0.140
vern+0.133
 cruel+0.127
 supposed+0.123
Neg logit contributions
cy-0.183
 Of-0.182
 girl-0.173
sc-0.172
 Sure-0.168
Token at
Token ID379
Feature activation-4.09e-01

Pos logit contributions
 strangers+0.153
 tresp+0.135
vern+0.133
 cruel+0.131
isdom+0.125
Neg logit contributions
 Of-0.086
cy-0.084
sc-0.079
 girl-0.078
 Sure-0.077
Token the
Token ID262
Feature activation-1.37e+00

Pos logit contributions
 strangers+0.026
 tresp+0.023
vern+0.022
 supposed+0.021
 cruel+0.021
Neg logit contributions
 Of-0.021
cy-0.020
sc-0.020
 girl-0.019
 Sure-0.019
Token event
Token ID1785
Feature activation-1.46e+00

Pos logit contributions
 strangers+0.087
 tresp+0.079
vern+0.075
 cruel+0.072
 supposed+0.071
Neg logit contributions
 Of-0.069
cy-0.068
sc-0.064
 girl-0.063
 Sure-0.062
Token.
Token ID13
Feature activation-4.33e-01

Pos logit contributions
 strangers+0.098
 tresp+0.089
vern+0.085
 cruel+0.082
 supposed+0.081
Neg logit contributions
 Of-0.067
cy-0.067
sc-0.062
 girl-0.061
 Sure-0.060
Token<|endoftext|>
Token ID50256
Feature activation-7.15e+00

Pos logit contributions
 strangers+0.028
 tresp+0.025
vern+0.024
 supposed+0.023
unts+0.023
Neg logit contributions
cy-0.021
 Of-0.021
sc-0.020
 girl-0.020
 Sure-0.019
TokenOnce
Token ID7454
Feature activation-9.96e-02

Pos logit contributions
 strangers+0.423
 tresp+0.377
vern+0.356
unts+0.353
 supposed+0.343
Neg logit contributions
 Of-0.364
cy-0.354
 girl-0.337
sc-0.336
 mixture-0.335
Token upon
Token ID2402
Feature activation-2.51e-01

Pos logit contributions
 strangers+0.008
 tresp+0.007
vern+0.007
cod+0.007
 cruel+0.007
Neg logit contributions
cy-0.004
 Of-0.004
 girl-0.003
 down-0.003
 Sure-0.003
Token a
Token ID257
Feature activation+1.36e+00

Pos logit contributions
 strangers+0.019
 tresp+0.018
vern+0.017
 cruel+0.017
isdom+0.016
Neg logit contributions
 Of-0.009
cy-0.009
 girl-0.008
sc-0.008
 Sure-0.008
Token time
Token ID640
Feature activation-2.11e+00

Pos logit contributions
cy+0.071
 Of+0.066
sc+0.064
 Sure+0.063
 girl+0.063
Neg logit contributions
 strangers-0.085
 tresp-0.077
 cruel-0.071
vern-0.070
 reckless-0.068
TokenAll
Token ID3237
Feature activation-8.04e-03

Pos logit contributions
 Of+0.077
cy+0.075
sc+0.072
 girl+0.071
 Sure+0.071
Neg logit contributions
 strangers-0.088
 tresp-0.079
vern-0.072
 cruel-0.071
 supposed-0.071
Token of
Token ID286
Feature activation-1.95e+00

Pos logit contributions
 strangers+0.000
 tresp+0.000
vern+0.000
 cruel+0.000
unts+0.000
Neg logit contributions
 Of-0.000
cy-0.000
sc-0.000
 Sure-0.000
 tin-0.000
Token Bella
Token ID39304
Feature activation+1.21e+00

Pos logit contributions
 strangers+0.135
 tresp+0.125
vern+0.124
 supposed+0.117
 cruel+0.116
Neg logit contributions
 Of-0.082
cy-0.081
 girl-0.078
 Sure-0.073
sc-0.072
Token's
Token ID338
Feature activation+1.63e+00

Pos logit contributions
cy+0.059
 Of+0.055
 girl+0.054
sc+0.053
 Sure+0.051
Neg logit contributions
 strangers-0.079
vern-0.072
 tresp-0.072
 cruel-0.067
 supposed-0.066
Token friends
Token ID2460
Feature activation-2.94e-01

Pos logit contributions
 Of+0.082
cy+0.081
 girl+0.081
 Sure+0.074
 mixture+0.073
Neg logit contributions
 strangers-0.098
 tresp-0.091
vern-0.087
cod-0.085
 supposed-0.084
Token wanted
Token ID2227
Feature activation-2.58e+00

Pos logit contributions
 strangers+0.017
vern+0.016
 tresp+0.016
 cruel+0.014
cod+0.014
Neg logit contributions
cy-0.016
 Of-0.016
 girl-0.015
sc-0.014
 down-0.014
Token to
Token ID284
Feature activation-7.54e-01

Pos logit contributions
 strangers+0.173
 tresp+0.159
vern+0.154
 cruel+0.147
unts+0.146
Neg logit contributions
 Of-0.116
cy-0.113
 girl-0.106
sc-0.105
 Sure-0.103
Token see
Token ID766
Feature activation-3.48e+00

Pos logit contributions
 strangers+0.045
 tresp+0.041
 cruel+0.040
cod+0.040
vern+0.039
Neg logit contributions
 Of-0.038
cy-0.037
 girl-0.035
 onto-0.034
 up-0.034
Token the
Token ID262
Feature activation-8.93e-01

Pos logit contributions
 strangers+0.206
 tresp+0.192
vern+0.187
unts+0.178
 supposed+0.176
Neg logit contributions
 Of-0.180
cy-0.177
 girl-0.170
sc-0.164
 down-0.159
Token triangle
Token ID22950
Feature activation+5.00e+00

Pos logit contributions
 strangers+0.054
 tresp+0.049
vern+0.047
 supposed+0.045
 cruel+0.044
Neg logit contributions
cy-0.046
 Of-0.046
 girl-0.044
sc-0.043
 Sure-0.041
Token in
Token ID287
Feature activation+2.63e+00

Pos logit contributions
 Of+0.235
cy+0.234
sc+0.218
 girl+0.214
 Sure+0.211
Neg logit contributions
 strangers-0.329
 tresp-0.296
vern-0.283
 cruel-0.272
 supposed-0.269
TokenThen
Token ID6423
Feature activation+2.74e+00

Pos logit contributions
 Of+0.040
cy+0.039
sc+0.038
 girl+0.037
 Sure+0.037
Neg logit contributions
 strangers-0.059
 tresp-0.053
vern-0.050
 supposed-0.049
 cruel-0.048
Token,
Token ID11
Feature activation+5.51e-01

Pos logit contributions
sc+0.164
cy+0.160
 Of+0.155
 Sure+0.143
suit+0.142
Neg logit contributions
 strangers-0.152
 tresp-0.133
 never-0.120
 cruel-0.114
 enemies-0.111
Token it
Token ID340
Feature activation-5.16e-01

Pos logit contributions
sc+0.032
cy+0.032
 Of+0.030
suit+0.029
umm+0.029
Neg logit contributions
 strangers-0.031
 tresp-0.027
 never-0.024
 cruel-0.024
 enemies-0.023
Token started
Token ID2067
Feature activation+1.55e+00

Pos logit contributions
 strangers+0.032
 tresp+0.029
vern+0.027
 cruel+0.027
 hated+0.027
Neg logit contributions
 Of-0.026
cy-0.026
sc-0.024
 Sure-0.024
 girl-0.023
Token to
Token ID284
Feature activation-1.01e+00

Pos logit contributions
 Of+0.069
cy+0.068
sc+0.063
 girl+0.063
 Sure+0.062
Neg logit contributions
 strangers-0.106
 tresp-0.096
vern-0.093
 cruel-0.088
unts-0.087
Token rain
Token ID6290
Feature activation-8.20e+00

Pos logit contributions
 strangers+0.059
 tresp+0.054
vern+0.052
 supposed+0.049
unts+0.049
Neg logit contributions
cy-0.053
 Of-0.052
 girl-0.051
sc-0.049
 tin-0.049
Token.
Token ID13
Feature activation+1.52e-02

Pos logit contributions
 strangers+0.525
 tresp+0.473
vern+0.451
 supposed+0.432
 cruel+0.430
Neg logit contributions
 Of-0.403
cy-0.396
sc-0.368
 girl-0.367
 Sure-0.362
Token The
Token ID383
Feature activation-6.60e-01

Pos logit contributions
cy+0.001
 Of+0.001
sc+0.001
 girl+0.001
 tin+0.001
Neg logit contributions
 strangers-0.001
 tresp-0.001
 hated-0.001
 cruel-0.001
unts-0.001
Token bunny
Token ID44915
Feature activation+2.42e+00

Pos logit contributions
 strangers+0.042
 tresp+0.037
 cruel+0.035
vern+0.034
 enemies+0.033
Neg logit contributions
 Of-0.034
cy-0.032
sc-0.032
 Sure-0.031
 onto-0.028
Token looked
Token ID3114
Feature activation+3.84e+00

Pos logit contributions
cy+0.112
 girl+0.107
 Of+0.106
sc+0.104
 Sure+0.097
Neg logit contributions
 strangers-0.163
 tresp-0.149
vern-0.149
 supposed-0.139
 cruel-0.135
Token up
Token ID510
Feature activation+7.49e+00

Pos logit contributions
cy+0.117
 Of+0.116
sc+0.104
 girl+0.104
 Sure+0.098
Neg logit contributions
 strangers-0.316
 tresp-0.293
vern-0.285
 cruel-0.273
 supposed-0.272
Token the
Token ID262
Feature activation-7.39e-01

Pos logit contributions
 Of+0.129
cy+0.126
 girl+0.125
 Sure+0.115
 Me+0.112
Neg logit contributions
 strangers-0.242
 tresp-0.228
vern-0.224
 supposed-0.215
cod-0.210
Token lion
Token ID18744
Feature activation-2.75e+00

Pos logit contributions
 strangers+0.039
vern+0.035
 tresp+0.035
 supposed+0.032
unts+0.031
Neg logit contributions
 Of-0.043
 girl-0.042
cy-0.042
sc-0.040
 Sure-0.039
Token flex
Token ID7059
Feature activation+4.99e+00

Pos logit contributions
 strangers+0.164
 tresp+0.147
vern+0.144
 supposed+0.136
 cruel+0.133
Neg logit contributions
cy-0.145
 Of-0.143
sc-0.137
 girl-0.136
 Sure-0.131
Tokened
Token ID276
Feature activation+6.93e+00

Pos logit contributions
cy+0.122
 Of+0.119
sc+0.105
 girl+0.101
 Sure+0.093
Neg logit contributions
 strangers-0.443
 tresp-0.413
vern-0.401
 supposed-0.388
 cruel-0.388
Token his
Token ID465
Feature activation+1.32e+00

Pos logit contributions
cy+0.371
 Of+0.361
sc+0.346
 girl+0.341
 Sure+0.333
Neg logit contributions
 strangers-0.420
 tresp-0.365
vern-0.335
 cruel-0.332
 enemies-0.326
Token muscles
Token ID12749
Feature activation-9.16e+00

Pos logit contributions
 Of+0.054
 girl+0.053
 onto+0.053
 down+0.052
 mixture+0.050
Neg logit contributions
 strangers-0.086
 tresp-0.080
 supposed-0.077
unts-0.076
cod-0.076
Token and
Token ID290
Feature activation-2.29e+00

Pos logit contributions
 strangers+0.632
 tresp+0.573
vern+0.549
 cruel+0.530
 supposed+0.522
Neg logit contributions
 Of-0.396
cy-0.396
sc-0.378
 girl-0.365
 Sure-0.353
Token roared
Token ID45615
Feature activation-8.39e-01

Pos logit contributions
 strangers+0.120
 tresp+0.106
 never+0.104
 cruel+0.100
 hated+0.098
Neg logit contributions
cy-0.139
 Of-0.136
sc-0.134
 Sure-0.122
 girl-0.122
Token.
Token ID13
Feature activation+2.66e-01

Pos logit contributions
 strangers+0.052
 tresp+0.046
vern+0.044
 cruel+0.043
 enemies+0.042
Neg logit contributions
cy-0.043
 Of-0.042
sc-0.040
 girl-0.039
 Sure-0.039
Token
Token ID198
Feature activation+1.09e+00

Pos logit contributions
cy+0.013
sc+0.012
 Of+0.012
 girl+0.012
 tin+0.011
Neg logit contributions
 strangers-0.016
 tresp-0.015
unts-0.014
vern-0.014
 hated-0.014
Token
Token ID198
Feature activation+1.11e+00

Pos logit contributions
 Of+0.031
 Sure+0.029
sc+0.028
cy+0.027
 up+0.024
Neg logit contributions
 strangers-0.095
 tresp-0.088
 cruel-0.084
 liar-0.081
 supposed-0.081
TokenSo
Token ID2396
Feature activation+3.09e+00

Pos logit contributions
 Of+0.044
cy+0.044
sc+0.042
 girl+0.041
 Sure+0.040
Neg logit contributions
 strangers-0.057
 tresp-0.052
vern-0.048
 supposed-0.048
 cruel-0.047
Token,
Token ID11
Feature activation+5.45e-01

Pos logit contributions
sc+0.188
cy+0.176
 Of+0.174
 Sure+0.171
 mixture+0.168
Neg logit contributions
 strangers-0.164
 tresp-0.136
 never-0.133
 cruel-0.116
 mean-0.115
Token one
Token ID530
Feature activation+8.05e+00

Pos logit contributions
sc+0.029
cy+0.029
 Of+0.028
suit+0.027
umm+0.027
Neg logit contributions
 strangers-0.032
 tresp-0.026
 never-0.025
 enemies-0.023
 understand-0.023
Token of
Token ID286
Feature activation-2.21e+00

Pos logit contributions
sc+0.448
 Of+0.439
cy+0.439
 Sure+0.419
ASH+0.408
Neg logit contributions
 strangers-0.461
 tresp-0.395
 cruel-0.394
 mean-0.385
unts-0.365
Token the
Token ID262
Feature activation-9.45e-01

Pos logit contributions
 strangers+0.140
 tresp+0.126
vern+0.121
 cruel+0.116
 supposed+0.115
Neg logit contributions
 Of-0.110
cy-0.109
sc-0.102
 girl-0.102
 Sure-0.099
Token cows
Token ID22575
Feature activation-1.10e+01

Pos logit contributions
 strangers+0.054
 tresp+0.047
vern+0.044
 cruel+0.043
unts+0.041
Neg logit contributions
 Of-0.055
cy-0.054
sc-0.052
 Sure-0.051
 onto-0.048
Token offered
Token ID4438
Feature activation+2.08e+00

Pos logit contributions
 strangers+0.681
vern+0.654
 tresp+0.635
 supposed+0.597
unts+0.582
Neg logit contributions
cy-0.549
 girl-0.528
 Of-0.510
 down-0.486
sc-0.481
Token to
Token ID284
Feature activation-9.07e-01

Pos logit contributions
 Of+0.096
cy+0.095
 girl+0.089
sc+0.089
 Sure+0.086
Neg logit contributions
 strangers-0.136
 tresp-0.125
vern-0.121
 cruel-0.115
 supposed-0.114
Token carry
Token ID3283
Feature activation+2.81e+00

Pos logit contributions
 strangers+0.052
 tresp+0.048
vern+0.048
 supposed+0.045
unts+0.045
Neg logit contributions
 Of-0.048
cy-0.047
 girl-0.045
sc-0.043
 Sure-0.043
Token her
Token ID607
Feature activation-1.38e-01

Pos logit contributions
 Of+0.149
cy+0.146
 Sure+0.139
 girl+0.135
sc+0.134
Neg logit contributions
 strangers-0.174
 tresp-0.149
vern-0.139
 cruel-0.132
 supposed-0.130
Token out
Token ID503
Feature activation+4.65e+00

Pos logit contributions
 strangers+0.010
 tresp+0.009
vern+0.008
 cruel+0.008
 supposed+0.008
Neg logit contributions
 Of-0.006
cy-0.006
sc-0.006
 girl-0.005
 Sure-0.005
Token ride
Token ID6594
Feature activation-1.85e+00

Pos logit contributions
 strangers+0.015
 tresp+0.013
vern+0.012
 cruel+0.011
 supposed+0.011
Neg logit contributions
 Of-0.022
cy-0.022
sc-0.021
 girl-0.021
 Sure-0.021
Token together
Token ID1978
Feature activation+7.04e+00

Pos logit contributions
 strangers+0.126
 tresp+0.112
vern+0.106
 supposed+0.102
 cruel+0.101
Neg logit contributions
 Of-0.083
cy-0.081
 Sure-0.075
 girl-0.075
sc-0.074
Token.
Token ID13
Feature activation-2.51e-02

Pos logit contributions
 Of+0.317
cy+0.316
sc+0.294
 girl+0.291
 Sure+0.282
Neg logit contributions
 strangers-0.476
 tresp-0.433
vern-0.416
 cruel-0.399
 supposed-0.395
Token The
Token ID383
Feature activation-7.74e-01

Pos logit contributions
 strangers+0.001
 tresp+0.001
 hated+0.001
 shouldn+0.001
 supposed+0.001
Neg logit contributions
cy-0.001
 tin-0.001
 mixture-0.001
sc-0.001
 Of-0.001
Token two
Token ID734
Feature activation+5.47e+00

Pos logit contributions
 strangers+0.050
 tresp+0.046
vern+0.044
unts+0.042
 supposed+0.042
Neg logit contributions
 Of-0.037
 girl-0.036
cy-0.036
sc-0.034
 Sure-0.032
Token ponies
Token ID46370
Feature activation-9.77e+00

Pos logit contributions
 girl+0.318
cy+0.285
 Of+0.283
 down+0.265
sc+0.259
Neg logit contributions
vern-0.293
 tresp-0.291
 strangers-0.289
isdom-0.281
 supposed-0.279
Token ran
Token ID4966
Feature activation-2.98e+00

Pos logit contributions
 strangers+0.544
vern+0.499
 tresp+0.489
 cruel+0.458
 supposed+0.453
Neg logit contributions
cy-0.582
 Of-0.543
 girl-0.542
sc-0.533
 onto-0.510
Token through
Token ID832
Feature activation+5.36e+00

Pos logit contributions
 strangers+0.199
 tresp+0.180
vern+0.167
 supposed+0.163
unts+0.162
Neg logit contributions
 Of-0.136
cy-0.133
 girl-0.121
 Sure-0.119
 mixture-0.118
Token the
Token ID262
Feature activation-1.09e+00

Pos logit contributions
 Of+0.211
cy+0.209
 girl+0.200
sc+0.191
 onto+0.186
Neg logit contributions
 strangers-0.378
vern-0.367
 tresp-0.354
 cruel-0.343
 supposed-0.341
Token me
Token ID502
Feature activation-2.55e+00

Pos logit contributions
 strangers+0.068
 tresp+0.061
vern+0.059
 cruel+0.056
 supposed+0.056
Neg logit contributions
cy-0.055
 Of-0.055
 girl-0.052
sc-0.051
 Sure-0.050
Tokenadow
Token ID4584
Feature activation-6.87e+00

Pos logit contributions
 strangers+0.150
 cruel+0.136
 tresp+0.135
 liar+0.126
 bullies+0.122
Neg logit contributions
cy-0.141
 down-0.126
 Of-0.123
 up-0.122
 Sure-0.120
Token so
Token ID523
Feature activation+4.35e+00

Pos logit contributions
 Of+0.079
 girl+0.068
cy+0.065
 Sure+0.063
 down+0.063
Neg logit contributions
 strangers-0.228
 tresp-0.222
vern-0.216
 supposed-0.212
unts-0.210
Token happy
Token ID3772
Feature activation-1.29e+00

Pos logit contributions
 Of+0.241
cy+0.236
 girl+0.227
sc+0.221
 Sure+0.218
Neg logit contributions
 strangers-0.249
 tresp-0.225
vern-0.213
 cruel-0.198
cod-0.198
Token and
Token ID290
Feature activation-1.22e+00

Pos logit contributions
 strangers+0.078
 tresp+0.069
vern+0.064
 supposed+0.062
 cruel+0.062
Neg logit contributions
cy-0.069
 Of-0.068
sc-0.065
 Sure-0.062
 girl-0.062
Token smiled
Token ID13541
Feature activation+2.51e+00

Pos logit contributions
 strangers+0.067
 tresp+0.059
vern+0.056
 cruel+0.054
 supposed+0.054
Neg logit contributions
cy-0.070
 Of-0.069
sc-0.066
 girl-0.064
 Sure-0.064
Token at
Token ID379
Feature activation+6.41e-01

Pos logit contributions
sc+0.130
cy+0.130
 Of+0.128
 Sure+0.120
 tin+0.113
Neg logit contributions
 strangers-0.150
 tresp-0.131
vern-0.127
 cruel-0.121
unts-0.121
Token Billy
Token ID15890
Feature activation-8.99e+00

Pos logit contributions
 Of+0.031
cy+0.030
 girl+0.028
 Sure+0.027
sc+0.026
Neg logit contributions
 strangers-0.041
 tresp-0.038
vern-0.037
cod-0.035
 cruel-0.035
Token.
Token ID13
Feature activation+7.89e-01

Pos logit contributions
 strangers+0.507
 tresp+0.427
vern+0.405
 supposed+0.400
 understand+0.398
Neg logit contributions
 Of-0.491
cy-0.483
sc-0.472
 Sure-0.461
 girl-0.436
Token His
Token ID2399
Feature activation+2.44e+00

Pos logit contributions
 Of+0.033
cy+0.032
sc+0.029
 girl+0.029
 Sure+0.029
Neg logit contributions
 strangers-0.057
 tresp-0.052
vern-0.050
 cruel-0.049
 supposed-0.048
Token mother
Token ID2802
Feature activation-9.12e-01

Pos logit contributions
 Of+0.123
cy+0.121
 girl+0.117
 Sure+0.111
sc+0.106
Neg logit contributions
 strangers-0.153
 tresp-0.138
vern-0.133
 supposed-0.127
cod-0.125
Token hugged
Token ID41130
Feature activation-1.21e+00

Pos logit contributions
 strangers+0.066
 tresp+0.061
vern+0.060
 supposed+0.056
 cruel+0.055
Neg logit contributions
cy-0.039
 girl-0.037
 Of-0.037
sc-0.032
 Sure-0.032
Token him
Token ID683
Feature activation-4.73e+00

Pos logit contributions
 strangers+0.060
 tresp+0.056
vern+0.054
 supposed+0.050
 cruel+0.049
Neg logit contributions
 Of-0.077
cy-0.075
 girl-0.073
 down-0.070
sc-0.069