TOP ACTIVATIONS
MAX = 25.606

But the ost ric hes did not like that
. One of the ost ric hes looked different from the
. It sees other ost ric hes . It makes new
wanted to touch the ost ric hes . They reached out
ostr ich pen . Ost ric hes are big birds with
ostr ich pen . Ost ric hes are big birds with
. They were called ost ric hes . Lily and Ben
mom and to the ost ric hes . They learned their
did not know what ost ric hes were . They looked
They do not pack ost ric hes anymore . They pack
you count how many ost ric hes there are ?"
that said " O st ric hes ". Sara and Tom
cried . " The ost ric hes are mean ! They
" O st ric hes do not like people
but be careful . Ost ric hes can be gr umpy
Yes , they are ost ric hes ," mom said .
ie . Unlike other ost ric hes , his feathers gl
Look , mom , ost ric hes !" "
should not tease the ost ric hes . They are not
shouted . " The ost ric hes are so funny !"

MIN ACTIVATIONS
MIN = -15.462

At the end of the week , Sus ie said goodbye
and told their mom what happened . Their mom
's mom saw what had happened . She stepped in and
into it , but nothing happened . The
. " What happened , Sam ?" his mom
the journal and understood what happened . She hugged Anna and
told Mom and Dad what happened . Mom and Dad were
them and tell them what happened . Mom and dad are
and didn 't know what happened to her . They missed
her and tell her what happened . " Mom
and came to see what happened . She saw Fl uffy
But then something magical happened . A rainbow appeared and
my and daddy saw what happened and they discuss how to
but didn 't know what happened to the box . James
depend able day of the week . It 's a day
the spring class the next week . <|endoftext|> Once upon a
his favourite day of the week . One Sunday , Jake
could not hop for a week . Ho ppy was sad
felt sad and wondered what happened to the bird . The
disc . He understands what happened . He is not happy

INTERVAL 15.339 - 25.606
CONTAINS 0.020%

put it right on her wrist ! Her Daddy saw it
slapped him again on the neck . This time
louder . It made their ears hurt . It made their
She looked into Emily 's ears , nose and throat .
jewelry on her fingers , wrists , and ears . She

INTERVAL 5.072 - 15.339
CONTAINS 15.849%

watched grow every day . They were very excited to eat
. They were tw irling and jumping , when suddenly ,
to roll the ball to each other and catch it .
She had found Sam with all the plastic pieces , and
Mia said . They leaned over the hole and

INTERVAL -5.195 - 5.072
CONTAINS 66.334%

little girl was scared but brave . She started to shout
tried to fly and even turned it into a pirate ship
her and went inside her house . She knew she 'd
decided he would try . He saw a
Lily with a big smile . Lily was so happy !

INTERVAL -15.462 - -5.195
CONTAINS 17.797%

a good idea . He asked the other animals in the
old bird saw them and said , " Stop fighting !
busy poking around the shelves , his mom my came into
paying the price . Sadly , they were stuck in the
laughed , having a great time . Bob was so happy
Token
Token ID198
Feature activation-3.90e-01

Pos logit contributions
ping+0.089
cks+0.089
opes+0.088
 necks+0.087
aron+0.087
Neg logit contributions
t-0.105
 happened-0.101
 help-0.098
 please-0.097
 day-0.097
Token
Token ID198
Feature activation-3.93e-01

Pos logit contributions
t+0.019
 happened+0.019
 help+0.018
 day+0.018
 reward+0.017
Neg logit contributions
cks-0.021
aron-0.020
uted-0.020
 necks-0.020
opes-0.020
TokenBut
Token ID1537
Feature activation+5.89e+00

Pos logit contributions
 happened+0.019
t+0.019
 help+0.018
 day+0.018
 awaited+0.017
Neg logit contributions
cks-0.021
 necks-0.021
aron-0.021
uted-0.021
 valleys-0.020
Token the
Token ID262
Feature activation+8.86e-01

Pos logit contributions
 necks+0.301
cks+0.293
 valleys+0.290
 ears+0.281
 neck+0.280
Neg logit contributions
t-0.298
 awaited-0.268
 happened-0.265
ha-0.261
va-0.255
Token ost
Token ID23619
Feature activation+3.99e+00

Pos logit contributions
 necks+0.045
cks+0.044
ping+0.043
 valleys+0.043
opes+0.043
Neg logit contributions
t-0.048
 happened-0.045
 awaited-0.043
 please-0.043
 help-0.042
Tokenric
Token ID1173
Feature activation+2.56e+01

Pos logit contributions
rily+0.078
 valleys+0.074
aron+0.071
uted+0.068
 necks+0.066
Neg logit contributions
t-0.338
 happened-0.323
 day-0.317
 help-0.313
 week-0.310
Tokenhes
Token ID956
Feature activation+6.01e+00

Pos logit contributions
 necks+0.861
aters+0.857
 valleys+0.818
opes+0.817
aron+0.816
Neg logit contributions
t-1.841
 happened-1.779
 day-1.697
 help-1.687
 please-1.662
Token did
Token ID750
Feature activation-6.63e+00

Pos logit contributions
rily+0.381
aron+0.379
ping+0.379
cks+0.378
uted+0.378
Neg logit contributions
t-0.215
 happened-0.204
 help-0.203
 awaited-0.202
 week-0.196
Token not
Token ID407
Feature activation+1.36e+00

Pos logit contributions
t+0.202
 happened+0.187
 help+0.181
 please+0.174
 day+0.172
Neg logit contributions
aron-0.487
opes-0.486
 necks-0.485
ping-0.484
 valleys-0.484
Token like
Token ID588
Feature activation+2.67e+00

Pos logit contributions
aron+0.080
cks+0.079
ping+0.078
 necks+0.076
uted+0.074
Neg logit contributions
t-0.060
 happened-0.058
 awaited-0.054
 week-0.053
 day-0.053
Token that
Token ID326
Feature activation-4.17e+00

Pos logit contributions
cks+0.155
 necks+0.154
ping+0.153
 valleys+0.151
opes+0.151
Neg logit contributions
t-0.122
 happened-0.110
 reward-0.108
 awaited-0.106
 please-0.105
Token.
Token ID13
Feature activation+1.83e+00

Pos logit contributions
cks+0.459
ping+0.445
 necks+0.444
uted+0.443
aron+0.441
Neg logit contributions
t-0.419
 week-0.377
 happened-0.377
 please-0.376
 day-0.374
Token One
Token ID1881
Feature activation+1.98e+00

Pos logit contributions
cks+0.099
ping+0.097
 necks+0.096
uted+0.096
opes+0.094
Neg logit contributions
t-0.094
 happened-0.091
 please-0.089
 help-0.087
 day-0.085
Token of
Token ID286
Feature activation-6.86e+00

Pos logit contributions
 valleys+0.118
cks+0.117
ping+0.116
 necks+0.115
opes+0.112
Neg logit contributions
t-0.075
 happened-0.072
 please-0.071
 awaited-0.069
 reward-0.066
Token the
Token ID262
Feature activation+8.37e-01

Pos logit contributions
t+0.244
 help+0.242
 happened+0.240
 day+0.234
 please+0.226
Neg logit contributions
aron-0.461
uted-0.450
opes-0.449
 necks-0.449
ping-0.448
Token ost
Token ID23619
Feature activation+3.95e+00

Pos logit contributions
 necks+0.041
cks+0.040
 valleys+0.039
ping+0.039
aron+0.039
Neg logit contributions
t-0.047
 happened-0.045
 please-0.043
 help-0.042
 awaited-0.042
Tokenric
Token ID1173
Feature activation+2.56e+01

Pos logit contributions
rily+0.081
aron+0.074
uted+0.072
 valleys+0.069
bes+0.067
Neg logit contributions
t-0.332
 happened-0.317
 day-0.315
 help-0.310
 week-0.307
Tokenhes
Token ID956
Feature activation+5.95e+00

Pos logit contributions
 necks+0.832
aters+0.808
aron+0.802
opes+0.799
rily+0.788
Neg logit contributions
t-1.839
 happened-1.787
 day-1.720
 help-1.714
 please-1.686
Token looked
Token ID3114
Feature activation+4.04e+00

Pos logit contributions
ping+0.367
cks+0.366
rily+0.363
uted+0.362
 necks+0.361
Neg logit contributions
t-0.223
 help-0.208
 please-0.205
 reward-0.204
 happened-0.204
Token different
Token ID1180
Feature activation+2.13e+00

Pos logit contributions
aters+0.256
aron+0.255
opes+0.253
cks+0.249
bes+0.248
Neg logit contributions
 happened-0.167
t-0.162
 help-0.159
 day-0.156
 please-0.154
Token from
Token ID422
Feature activation+6.83e-02

Pos logit contributions
bes+0.087
cks+0.085
uted+0.085
rily+0.085
aron+0.084
Neg logit contributions
 day-0.130
 happened-0.130
 help-0.127
t-0.124
 week-0.123
Token the
Token ID262
Feature activation+8.85e-01

Pos logit contributions
aron+0.004
uted+0.004
aters+0.004
opes+0.004
cks+0.004
Neg logit contributions
 help-0.003
 happened-0.003
 day-0.003
t-0.003
 please-0.003
Token.
Token ID13
Feature activation+1.81e+00

Pos logit contributions
t+0.291
 help+0.275
 day+0.272
 happened+0.272
 please+0.262
Neg logit contributions
opes-0.392
cks-0.385
uted-0.383
aters-0.380
 valleys-0.378
Token It
Token ID632
Feature activation+4.91e+00

Pos logit contributions
opes+0.096
ping+0.095
 necks+0.095
cks+0.095
aters+0.092
Neg logit contributions
 thank-0.096
 please-0.093
t-0.092
 help-0.091
 happened-0.090
Token sees
Token ID7224
Feature activation+1.34e+00

Pos logit contributions
ping+0.291
opes+0.290
aron+0.290
uted+0.289
cks+0.289
Neg logit contributions
t-0.209
 happened-0.206
 help-0.202
 day-0.197
 would-0.194
Token other
Token ID584
Feature activation-6.44e+00

Pos logit contributions
aron+0.081
 necks+0.080
aters+0.080
opes+0.080
cks+0.080
Neg logit contributions
 happened-0.057
t-0.057
 help-0.054
 day-0.053
 please-0.052
Token ost
Token ID23619
Feature activation+3.94e+00

Pos logit contributions
t+0.368
 happened+0.363
 help+0.360
 day+0.359
 week+0.346
Neg logit contributions
aron-0.289
cks-0.288
rily-0.288
opes-0.286
uted-0.284
Tokenric
Token ID1173
Feature activation+2.55e+01

Pos logit contributions
rily+0.093
aron+0.087
 valleys+0.085
uted+0.079
 necks+0.077
Neg logit contributions
t-0.321
 happened-0.302
 day-0.297
 help-0.295
 week-0.290
Tokenhes
Token ID956
Feature activation+5.93e+00

Pos logit contributions
 necks+0.896
aters+0.883
aron+0.847
opes+0.843
rily+0.832
Neg logit contributions
t-1.791
 happened-1.744
 day-1.674
 help-1.669
 please-1.635
Token.
Token ID13
Feature activation+1.84e+00

Pos logit contributions
aron+0.351
opes+0.350
 necks+0.350
cks+0.348
uted+0.346
Neg logit contributions
t-0.260
 happened-0.247
 help-0.244
 day-0.240
 please-0.236
Token It
Token ID632
Feature activation+4.94e+00

Pos logit contributions
ping+0.098
opes+0.098
 necks+0.098
cks+0.096
uted+0.093
Neg logit contributions
 please-0.095
 thank-0.094
t-0.094
 help-0.091
 happened-0.091
Token makes
Token ID1838
Feature activation+1.08e-01

Pos logit contributions
aters+0.295
aron+0.292
ping+0.292
uted+0.290
opes+0.290
Neg logit contributions
 happened-0.210
t-0.207
 help-0.206
 would-0.202
 day-0.199
Token new
Token ID649
Feature activation+9.66e-02

Pos logit contributions
aron+0.006
 necks+0.006
opes+0.006
cks+0.006
aters+0.006
Neg logit contributions
t-0.005
 happened-0.005
 help-0.005
 day-0.005
 please-0.005
Token wanted
Token ID2227
Feature activation-1.54e-02

Pos logit contributions
cks+0.590
ping+0.582
opes+0.582
aron+0.582
 necks+0.580
Neg logit contributions
t-0.276
 happened-0.264
 help-0.250
 day-0.242
 please-0.239
Token to
Token ID284
Feature activation-9.13e+00

Pos logit contributions
t+0.001
ha+0.000
 awaited+0.000
 happened+0.000
 reward+0.000
Neg logit contributions
 necks-0.001
ping-0.001
 valleys-0.001
cks-0.001
 piles-0.001
Token touch
Token ID3638
Feature activation+2.69e+00

Pos logit contributions
t+0.396
 happened+0.380
 awaited+0.364
ha+0.349
 week+0.348
Neg logit contributions
cks-0.548
 necks-0.546
aron-0.523
uted-0.520
opes-0.518
Token the
Token ID262
Feature activation+8.06e-01

Pos logit contributions
aron+0.177
opes+0.176
uted+0.175
rily+0.173
ping+0.173
Neg logit contributions
 help-0.098
 happened-0.097
 day-0.096
t-0.096
 please-0.092
Token ost
Token ID23619
Feature activation+3.92e+00

Pos logit contributions
aron+0.038
cks+0.038
uted+0.038
rily+0.038
opes+0.037
Neg logit contributions
t-0.045
 happened-0.044
 help-0.043
 day-0.043
 week-0.041
Tokenric
Token ID1173
Feature activation+2.55e+01

Pos logit contributions
rily+0.094
 valleys+0.088
aron+0.085
efully+0.079
uted+0.078
Neg logit contributions
t-0.315
 day-0.296
 happened-0.293
 help-0.289
 week-0.287
Tokenhes
Token ID956
Feature activation+5.94e+00

Pos logit contributions
 necks+0.783
aron+0.764
opes+0.761
cks+0.754
 valleys+0.750
Neg logit contributions
t-1.867
 happened-1.809
 day-1.757
 help-1.754
 please-1.728
Token.
Token ID13
Feature activation+1.83e+00

Pos logit contributions
cks+0.304
aron+0.304
 necks+0.303
ping+0.302
uted+0.299
Neg logit contributions
t-0.299
 happened-0.290
 help-0.274
 day-0.271
 awaited-0.271
Token They
Token ID1119
Feature activation+8.39e+00

Pos logit contributions
cks+0.084
ping+0.083
opes+0.082
aron+0.082
uted+0.081
Neg logit contributions
t-0.108
 happened-0.104
 help-0.101
 day-0.101
 please-0.100
Token reached
Token ID4251
Feature activation-6.86e-01

Pos logit contributions
 necks+0.564
cks+0.560
aron+0.559
opes+0.556
uted+0.553
Neg logit contributions
t-0.303
 happened-0.283
 day-0.269
 help-0.268
 please-0.261
Token out
Token ID503
Feature activation+1.43e+00

Pos logit contributions
t+0.030
 help+0.030
 happened+0.030
 day+0.029
 please+0.028
Neg logit contributions
aron-0.040
opes-0.040
uted-0.040
 necks-0.039
ping-0.039
Token ostr
Token ID42387
Feature activation+3.05e-01

Pos logit contributions
 necks+0.038
cks+0.038
opes+0.038
 valleys+0.038
aron+0.037
Neg logit contributions
t-0.048
 happened-0.046
 help-0.044
 please-0.044
 day-0.044
Tokenich
Token ID488
Feature activation+7.49e+00

Pos logit contributions
cks+0.011
 necks+0.011
opes+0.011
aron+0.011
ping+0.011
Neg logit contributions
t-0.020
 happened-0.020
 help-0.019
 day-0.019
 please-0.019
Token pen
Token ID3112
Feature activation-2.59e+00

Pos logit contributions
cks+0.377
opes+0.375
aron+0.374
uted+0.371
 necks+0.370
Neg logit contributions
t-0.396
 help-0.376
 day-0.374
 happened-0.374
 please-0.367
Token.
Token ID13
Feature activation+1.75e+00

Pos logit contributions
t+0.134
 happened+0.127
 day+0.127
 help+0.125
 please+0.124
Neg logit contributions
cks-0.133
opes-0.132
 valleys-0.131
 necks-0.130
uted-0.129
Token Ost
Token ID38919
Feature activation+4.02e+00

Pos logit contributions
ping+0.081
opes+0.079
cks+0.077
uted+0.076
 necks+0.076
Neg logit contributions
 please-0.102
t-0.101
 thank-0.099
 help-0.099
 happened-0.099
Tokenric
Token ID1173
Feature activation+2.54e+01

Pos logit contributions
rily+0.131
edly+0.118
aters+0.115
 valleys+0.111
aron+0.111
Neg logit contributions
 day-0.285
t-0.280
 help-0.267
 week-0.265
 done-0.263
Tokenhes
Token ID956
Feature activation+5.79e+00

Pos logit contributions
aters+1.029
 necks+1.001
rily+0.992
ishment+0.946
aron+0.934
Neg logit contributions
t-1.717
 happened-1.649
 day-1.573
 help-1.529
 week-1.511
Token are
Token ID389
Feature activation+2.73e-01

Pos logit contributions
cks+0.373
 necks+0.371
aron+0.370
opes+0.369
ping+0.368
Neg logit contributions
t-0.223
 happened-0.212
 help-0.200
 day-0.199
 please-0.195
Token big
Token ID1263
Feature activation-3.48e+00

Pos logit contributions
uted+0.015
opes+0.015
aron+0.015
rily+0.015
aters+0.015
Neg logit contributions
t-0.012
 happened-0.012
 help-0.012
 day-0.012
 please-0.012
Token birds
Token ID10087
Feature activation+3.90e+00

Pos logit contributions
 help+0.176
 happened+0.174
 day+0.169
 problem+0.168
 thank+0.165
Neg logit contributions
rily-0.180
uted-0.177
cks-0.174
bes-0.174
inning-0.170
Token with
Token ID351
Feature activation+4.49e+00

Pos logit contributions
opes+0.251
 valleys+0.247
rily+0.244
efully+0.243
aters+0.242
Neg logit contributions
t-0.153
 day-0.148
 help-0.147
 please-0.139
 happened-0.135
Token ostr
Token ID42387
Feature activation+2.39e-01

Pos logit contributions
cks+0.037
aron+0.036
opes+0.036
ping+0.036
uted+0.036
Neg logit contributions
t-0.040
 happened-0.039
 help-0.038
 day-0.038
 please-0.037
Tokenich
Token ID488
Feature activation+7.40e+00

Pos logit contributions
cks+0.009
aron+0.009
 necks+0.009
opes+0.009
ping+0.009
Neg logit contributions
t-0.016
 happened-0.015
 help-0.015
 day-0.015
 please-0.014
Token pen
Token ID3112
Feature activation-2.66e+00

Pos logit contributions
cks+0.416
aron+0.413
opes+0.413
 necks+0.410
uted+0.410
Neg logit contributions
t-0.348
 happened-0.330
 help-0.325
 day-0.324
 please-0.317
Token.
Token ID13
Feature activation+1.68e+00

Pos logit contributions
t+0.138
 happened+0.131
 day+0.130
 help+0.127
 please+0.126
Neg logit contributions
cks-0.139
opes-0.136
 valleys-0.135
 necks-0.135
aron-0.134
Token Ost
Token ID38919
Feature activation+3.92e+00

Pos logit contributions
ping+0.086
opes+0.084
 necks+0.083
cks+0.082
uted+0.080
Neg logit contributions
 please-0.090
t-0.088
 thank-0.087
 happened-0.087
 help-0.085
Tokenric
Token ID1173
Feature activation+2.54e+01

Pos logit contributions
rily+0.135
edly+0.125
aters+0.118
 strings+0.118
ksh+0.116
Neg logit contributions
 day-0.269
t-0.262
 done-0.251
 week-0.250
 help-0.246
Tokenhes
Token ID956
Feature activation+5.75e+00

Pos logit contributions
aters+1.047
 necks+1.018
rily+0.989
ishment+0.961
aron+0.939
Neg logit contributions
t-1.720
 happened-1.649
 day-1.561
 help-1.505
 week-1.499
Token are
Token ID389
Feature activation+2.16e-01

Pos logit contributions
cks+0.365
 necks+0.360
ping+0.360
opes+0.358
aron+0.358
Neg logit contributions
t-0.224
 happened-0.212
 help-0.202
 day-0.198
 please-0.197
Token big
Token ID1263
Feature activation-3.53e+00

Pos logit contributions
aron+0.012
opes+0.012
uted+0.012
 valleys+0.012
aters+0.012
Neg logit contributions
t-0.010
 happened-0.010
 help-0.009
 day-0.009
 please-0.009
Token birds
Token ID10087
Feature activation+3.86e+00

Pos logit contributions
 happened+0.170
 help+0.168
 day+0.163
 problem+0.161
t+0.159
Neg logit contributions
rily-0.188
uted-0.187
cks-0.187
bes-0.184
ags-0.181
Token with
Token ID351
Feature activation+4.44e+00

Pos logit contributions
opes+0.247
 valleys+0.245
 necks+0.242
ags+0.241
rily+0.241
Neg logit contributions
t-0.152
 day-0.145
 help-0.144
 happened-0.138
 please-0.138
Token.
Token ID13
Feature activation+1.75e+00

Pos logit contributions
cks+0.640
opes+0.639
 necks+0.634
 valleys+0.630
aron+0.628
Neg logit contributions
t-0.460
 happened-0.433
 day-0.412
 help-0.410
 would-0.394
Token They
Token ID1119
Feature activation+8.27e+00

Pos logit contributions
ping+0.102
cks+0.101
opes+0.096
 necks+0.094
uted+0.094
Neg logit contributions
 please-0.081
t-0.081
 happened-0.078
 thank-0.076
 week-0.075
Token were
Token ID547
Feature activation+5.49e-01

Pos logit contributions
 necks+0.535
cks+0.531
opes+0.527
 valleys+0.526
aron+0.526
Neg logit contributions
t-0.321
 happened-0.300
 day-0.284
 help-0.282
 please-0.276
Token called
Token ID1444
Feature activation+2.45e+00

Pos logit contributions
aron+0.030
opes+0.030
 necks+0.030
aters+0.030
rily+0.030
Neg logit contributions
t-0.025
 happened-0.025
 day-0.025
 help-0.024
 please-0.024
Token ost
Token ID23619
Feature activation+3.76e+00

Pos logit contributions
cks+0.139
 necks+0.138
aron+0.138
opes+0.138
ping+0.137
Neg logit contributions
t-0.113
 happened-0.108
 help-0.103
 day-0.103
 please-0.101
Tokenric
Token ID1173
Feature activation+2.54e+01

Pos logit contributions
rily+0.083
aron+0.082
 valleys+0.075
bes+0.075
uted+0.074
Neg logit contributions
t-0.304
 happened-0.293
 day-0.285
 help-0.284
 would-0.280
Tokenhes
Token ID956
Feature activation+5.75e+00

Pos logit contributions
aters+0.975
 necks+0.953
aron+0.914
rily+0.905
opes+0.888
Neg logit contributions
t-1.737
 happened-1.679
 day-1.598
 help-1.572
 week-1.554
Token.
Token ID13
Feature activation+1.62e+00

Pos logit contributions
cks+0.324
 necks+0.322
aron+0.322
opes+0.320
ping+0.319
Neg logit contributions
t-0.267
 happened-0.255
 help-0.245
 day-0.243
 please-0.239
Token Lily
Token ID20037
Feature activation-5.78e+00

Pos logit contributions
ping+0.091
cks+0.090
opes+0.089
 necks+0.087
uted+0.087
Neg logit contributions
t-0.078
 please-0.075
 happened-0.073
 help-0.072
 day-0.072
Token and
Token ID290
Feature activation+8.56e+00

Pos logit contributions
t+0.242
 happened+0.242
 would+0.231
 day+0.223
 help+0.218
Neg logit contributions
cks-0.358
ags-0.352
rily-0.351
ping-0.346
aters-0.345
Token Ben
Token ID3932
Feature activation-7.58e+00

Pos logit contributions
 necks+0.532
opes+0.523
cks+0.522
 valleys+0.516
ping+0.515
Neg logit contributions
t-0.377
 happened-0.329
 day-0.314
 week-0.313
 please-0.309
Token mom
Token ID1995
Feature activation-9.34e+00

Pos logit contributions
t+0.350
 happened+0.337
 help+0.333
 day+0.325
 please+0.317
Neg logit contributions
aron-0.609
cks-0.604
opes-0.604
 necks-0.603
uted-0.602
Token and
Token ID290
Feature activation+8.54e+00

Pos logit contributions
t+0.551
 happened+0.534
 help+0.508
 day+0.507
 please+0.503
Neg logit contributions
aron-0.414
 necks-0.411
cks-0.409
ping-0.409
uted-0.405
Token to
Token ID284
Feature activation-9.32e+00

Pos logit contributions
 necks+0.492
 neck+0.489
 backs+0.478
 wrists+0.472
 ears+0.468
Neg logit contributions
t-0.367
ha-0.350
 happened-0.291
 awaited-0.291
gh-0.282
Token the
Token ID262
Feature activation+6.12e-01

Pos logit contributions
t+0.464
 happened+0.429
ha+0.403
 awaited+0.400
 day+0.397
Neg logit contributions
cks-0.521
 necks-0.517
ping-0.513
opes-0.507
uted-0.504
Token ost
Token ID23619
Feature activation+3.71e+00

Pos logit contributions
 necks+0.030
cks+0.030
 valleys+0.029
ping+0.029
opes+0.029
Neg logit contributions
t-0.034
 happened-0.032
 please-0.030
 help-0.030
 awaited-0.030
Tokenric
Token ID1173
Feature activation+2.53e+01

Pos logit contributions
rily+0.084
 valleys+0.079
aron+0.078
uted+0.071
bes+0.070
Neg logit contributions
t-0.299
 happened-0.283
 day-0.283
 help-0.279
 week-0.275
Tokenhes
Token ID956
Feature activation+5.72e+00

Pos logit contributions
 necks+0.884
aters+0.879
aron+0.845
opes+0.842
 valleys+0.838
Neg logit contributions
t-1.778
 happened-1.729
 day-1.664
 help-1.656
 week-1.618
Token.
Token ID13
Feature activation+1.63e+00

Pos logit contributions
cks+0.300
aron+0.298
 necks+0.297
ping+0.297
uted+0.294
Neg logit contributions
t-0.284
 happened-0.275
 help-0.259
 day-0.257
 awaited-0.257
Token They
Token ID1119
Feature activation+8.20e+00

Pos logit contributions
ping+0.067
cks+0.067
opes+0.065
uted+0.064
rily+0.063
Neg logit contributions
t-0.104
 happened-0.102
 day-0.100
 help-0.100
 please-0.099
Token learned
Token ID4499
Feature activation-6.70e-01

Pos logit contributions
 necks+0.545
aron+0.543
uted+0.539
cks+0.538
opes+0.536
Neg logit contributions
t-0.301
 happened-0.278
 day-0.266
 week-0.259
 help-0.259
Token their
Token ID511
Feature activation+3.70e+00

Pos logit contributions
t+0.030
 happened+0.029
 help+0.028
 day+0.027
 please+0.027
Neg logit contributions
cks-0.039
 necks-0.039
aron-0.039
opes-0.039
ping-0.039
Token did
Token ID750
Feature activation-6.96e+00

Pos logit contributions
t+0.345
 happened+0.327
 help+0.310
 day+0.308
 please+0.301
Neg logit contributions
cks-0.608
 necks-0.606
aron-0.604
opes-0.602
ping-0.600
Token not
Token ID407
Feature activation+1.04e+00

Pos logit contributions
 help+0.166
t+0.160
 happened+0.153
 please+0.147
 thank+0.144
Neg logit contributions
aters-0.579
aron-0.579
ping-0.570
rily-0.563
opes-0.558
Token know
Token ID760
Feature activation-6.10e+00

Pos logit contributions
aron+0.064
cks+0.061
ping+0.061
 necks+0.060
uted+0.060
Neg logit contributions
t-0.043
 happened-0.042
 awaited-0.039
 day-0.037
 week-0.037
Token what
Token ID644
Feature activation+4.44e+00

Pos logit contributions
t+0.261
 happened+0.252
 help+0.241
 day+0.238
 please+0.234
Neg logit contributions
aron-0.365
 necks-0.364
cks-0.364
opes-0.362
ping-0.361
Token ost
Token ID23619
Feature activation+3.69e+00

Pos logit contributions
cks+0.259
 valleys+0.253
 necks+0.250
aron+0.248
opes+0.245
Neg logit contributions
t-0.190
 reward-0.163
 happened-0.160
ll-0.156
 please-0.155
Tokenric
Token ID1173
Feature activation+2.53e+01

Pos logit contributions
aron+0.064
 necks+0.063
cks+0.063
 valleys+0.061
opes+0.061
Neg logit contributions
t-0.316
 happened-0.308
 help-0.301
 day-0.300
 please-0.297
Tokenhes
Token ID956
Feature activation+5.72e+00

Pos logit contributions
cks+0.869
aron+0.849
opes+0.847
 necks+0.846
ping+0.843
Neg logit contributions
t-1.730
 happened-1.681
 help-1.643
 day-1.631
 please-1.618
Token were
Token ID547
Feature activation+4.58e-01

Pos logit contributions
cks+0.352
ping+0.346
aron+0.343
opes+0.343
uted+0.342
Neg logit contributions
t-0.231
 happened-0.217
 help-0.205
 awaited-0.199
 day-0.199
Token.
Token ID13
Feature activation+1.60e+00

Pos logit contributions
cks+0.026
opes+0.026
 necks+0.026
ping+0.026
aron+0.026
Neg logit contributions
t-0.021
 happened-0.020
 help-0.019
 please-0.019
 day-0.019
Token They
Token ID1119
Feature activation+8.19e+00

Pos logit contributions
ping+0.081
cks+0.080
opes+0.077
inning+0.076
bes+0.076
Neg logit contributions
t-0.088
 please-0.084
 happened-0.084
 week-0.083
 day-0.083
Token looked
Token ID3114
Feature activation+3.81e+00

Pos logit contributions
 necks+0.524
opes+0.516
cks+0.515
aron+0.511
uted+0.511
Neg logit contributions
t-0.323
 happened-0.302
 day-0.289
 help-0.285
 week-0.281
Token They
Token ID1119
Feature activation+8.13e+00

Pos logit contributions
ping+0.081
rily+0.078
opes+0.078
bes+0.077
 necks+0.075
Neg logit contributions
t-0.081
 day-0.080
 thank-0.080
 help-0.079
 happened-0.078
Token do
Token ID466
Feature activation-8.45e+00

Pos logit contributions
 necks+0.539
aron+0.533
cks+0.531
opes+0.528
uted+0.526
Neg logit contributions
t-0.293
 happened-0.279
 day-0.255
 week-0.253
 awaited-0.250
Token not
Token ID407
Feature activation+1.02e+00

Pos logit contributions
t+0.270
 happened+0.251
 help+0.240
 day+0.237
 please+0.227
Neg logit contributions
aron-0.607
 necks-0.607
cks-0.606
opes-0.603
ping-0.602
Token pack
Token ID2353
Feature activation+4.46e+00

Pos logit contributions
aron+0.063
cks+0.063
 necks+0.062
ping+0.062
uted+0.059
Neg logit contributions
t-0.040
 happened-0.039
 awaited-0.037
ha-0.034
 reward-0.034
Token ost
Token ID23619
Feature activation+3.68e+00

Pos logit contributions
cks+0.245
aron+0.244
 necks+0.244
opes+0.244
ping+0.242
Neg logit contributions
t-0.213
 happened-0.205
 help-0.198
 day-0.196
 please-0.193
Tokenric
Token ID1173
Feature activation+2.53e+01

Pos logit contributions
rily+0.101
aron+0.099
 valleys+0.096
uted+0.094
cks+0.090
Neg logit contributions
t-0.282
 happened-0.270
 help-0.265
 day-0.262
 please-0.258
Tokenhes
Token ID956
Feature activation+5.70e+00

Pos logit contributions
 necks+0.820
aron+0.802
opes+0.789
aters+0.788
rily+0.779
Neg logit contributions
t-1.810
 happened-1.761
 help-1.709
 day-1.705
 please-1.673
Token anymore
Token ID7471
Feature activation-5.25e+00

Pos logit contributions
cks+0.325
aron+0.323
 necks+0.323
opes+0.323
uted+0.321
Neg logit contributions
t-0.261
 happened-0.249
 help-0.242
 day-0.240
 please-0.235
Token.
Token ID13
Feature activation+1.58e+00

Pos logit contributions
t+0.263
 happened+0.250
 help+0.242
 day+0.239
 please+0.238
Neg logit contributions
cks-0.279
 necks-0.279
aron-0.277
opes-0.276
ping-0.274
Token They
Token ID1119
Feature activation+8.16e+00

Pos logit contributions
ping+0.074
rily+0.073
opes+0.072
cks+0.071
 necks+0.071
Neg logit contributions
t-0.094
 happened-0.091
 day-0.089
 help-0.088
 week-0.087
Token pack
Token ID2353
Feature activation+4.51e+00

Pos logit contributions
 necks+0.562
cks+0.558
aron+0.554
opes+0.551
uted+0.547
Neg logit contributions
t-0.277
 happened-0.263
 day-0.239
 week-0.236
 awaited-0.233
Token you
Token ID345
Feature activation-4.68e+00

Pos logit contributions
 necks+0.146
 valleys+0.139
cks+0.137
opes+0.136
 wrists+0.133
Neg logit contributions
 happened-0.056
 awaited-0.047
 week-0.045
t-0.045
 reward-0.044
Token count
Token ID954
Feature activation-1.39e-01

Pos logit contributions
 happened+0.182
t+0.179
 awaited+0.166
 week+0.160
 day+0.160
Neg logit contributions
 necks-0.294
cks-0.293
aron-0.291
opes-0.287
ping-0.286
Token how
Token ID703
Feature activation+1.20e+01

Pos logit contributions
t+0.006
 please+0.005
 help+0.005
 day+0.005
 happened+0.005
Neg logit contributions
aron-0.009
ping-0.009
uted-0.009
rily-0.009
 necks-0.009
Token many
Token ID867
Feature activation+1.76e+00

Pos logit contributions
 valleys+0.754
 necks+0.738
cks+0.734
opes+0.725
uted+0.715
Neg logit contributions
 happened-0.453
t-0.448
 reward-0.418
 awaited-0.409
 help-0.398
Token ost
Token ID23619
Feature activation+3.66e+00

Pos logit contributions
cks+0.083
 necks+0.082
opes+0.080
 valleys+0.080
ping+0.079
Neg logit contributions
t-0.102
 happened-0.097
 help-0.092
 please-0.091
 day-0.091
Tokenric
Token ID1173
Feature activation+2.53e+01

Pos logit contributions
rily+0.068
aron+0.067
uted+0.063
 valleys+0.063
 necks+0.062
Neg logit contributions
t-0.311
 happened-0.301
 day-0.295
 help-0.294
 please-0.289
Tokenhes
Token ID956
Feature activation+5.68e+00

Pos logit contributions
cks+0.943
opes+0.909
aron+0.908
uted+0.906
 necks+0.905
Neg logit contributions
t-1.658
 happened-1.613
 help-1.574
 day-1.558
 please-1.550
Token there
Token ID612
Feature activation-2.04e+00

Pos logit contributions
cks+0.363
 necks+0.351
ping+0.350
opes+0.348
aron+0.346
Neg logit contributions
t-0.217
 happened-0.213
 awaited-0.195
 help-0.191
 reward-0.189
Token are
Token ID389
Feature activation+1.56e-01

Pos logit contributions
t+0.070
 happened+0.067
 help+0.062
 day+0.061
 awaited+0.059
Neg logit contributions
cks-0.138
 necks-0.137
opes-0.137
aron-0.136
ping-0.136
Token?"
Token ID1701
Feature activation-1.29e+00

Pos logit contributions
cks+0.009
 necks+0.009
opes+0.009
aron+0.009
ping+0.009
Neg logit contributions
t-0.007
 happened-0.007
 help-0.007
 day-0.007
 please-0.007
Token
Token ID198
Feature activation-6.76e-01

Pos logit contributions
t+0.057
 happened+0.054
 awaited+0.051
 reward+0.051
 help+0.050
Neg logit contributions
 necks-0.076
cks-0.076
aron-0.075
 valleys-0.074
uted-0.073
Token that
Token ID326
Feature activation-4.57e+00

Pos logit contributions
cks+0.181
 necks+0.179
aron+0.179
uted+0.178
opes+0.177
Neg logit contributions
t-0.124
 happened-0.117
 help-0.113
 day-0.111
 please-0.109
Token said
Token ID531
Feature activation-9.03e+00

Pos logit contributions
t+0.146
 week+0.128
 please+0.126
 help+0.123
 reward+0.123
Neg logit contributions
cks-0.324
 necks-0.319
opes-0.314
uted-0.314
 valleys-0.311
Token "
Token ID366
Feature activation+1.48e+00

Pos logit contributions
t+0.486
 day+0.461
 week+0.460
 happened+0.452
 help+0.440
Neg logit contributions
cks-0.419
opes-0.414
 valleys-0.412
uted-0.412
aron-0.411
TokenO
Token ID46
Feature activation-5.73e-01

Pos logit contributions
cks+0.072
 necks+0.072
aron+0.072
opes+0.071
ping+0.071
Neg logit contributions
t-0.080
 happened-0.077
 help-0.074
 day-0.074
 please-0.073
Tokenst
Token ID301
Feature activation+5.66e+00

Pos logit contributions
t+0.026
 happened+0.026
 help+0.025
 please+0.024
 day+0.024
Neg logit contributions
cks-0.033
 necks-0.032
opes-0.032
aron-0.032
ping-0.032
Tokenric
Token ID1173
Feature activation+2.53e+01

Pos logit contributions
 necks+0.301
aron+0.300
cks+0.298
uted+0.298
 valleys+0.297
Neg logit contributions
t-0.284
 happened-0.267
 help-0.262
 day-0.257
 please-0.257
Tokenhes
Token ID956
Feature activation+5.66e+00

Pos logit contributions
 necks+0.896
cks+0.890
aron+0.887
opes+0.881
ping+0.872
Neg logit contributions
t-1.707
 happened-1.654
 help-1.608
 day-1.601
 please-1.583
Token".
Token ID1911
Feature activation+3.53e+00

Pos logit contributions
cks+0.340
ping+0.332
opes+0.332
uted+0.331
aron+0.330
Neg logit contributions
t-0.231
 happened-0.227
 help-0.211
 awaited-0.210
 day-0.207
Token Sara
Token ID24799
Feature activation-3.24e+00

Pos logit contributions
ping+0.269
cks+0.269
opes+0.267
inning+0.260
 valleys+0.259
Neg logit contributions
t-0.101
 happened-0.097
 please-0.096
 thank-0.089
 day-0.088
Token and
Token ID290
Feature activation+8.52e+00

Pos logit contributions
t+0.143
 happened+0.138
 would+0.130
 help+0.128
 day+0.127
Neg logit contributions
cks-0.197
rily-0.194
ping-0.192
 valleys-0.191
ags-0.191
Token Tom
Token ID4186
Feature activation-9.25e+00

Pos logit contributions
 necks+0.574
opes+0.571
uted+0.570
cks+0.569
aron+0.567
Neg logit contributions
t-0.319
 happened-0.274
 help-0.266
 day-0.260
 awaited-0.258
Token cried
Token ID16896
Feature activation+2.45e+00

Pos logit contributions
t+0.219
 happened+0.207
 help+0.204
 please+0.196
 day+0.190
Neg logit contributions
opes-0.381
cks-0.380
 valleys-0.379
aters-0.378
 necks-0.377
Token.
Token ID13
Feature activation+1.57e+00

Pos logit contributions
cks+0.171
 necks+0.169
opes+0.167
 valleys+0.166
bes+0.166
Neg logit contributions
 help-0.097
t-0.091
 please-0.087
 happened-0.084
 day-0.082
Token "
Token ID366
Feature activation+1.50e+00

Pos logit contributions
cks+0.096
aters+0.096
ping+0.095
rily+0.094
opes+0.092
Neg logit contributions
t-0.075
 happened-0.071
 help-0.067
 please-0.066
 they-0.065
TokenThe
Token ID464
Feature activation+7.27e+00

Pos logit contributions
aters+0.088
aron+0.087
opes+0.086
rily+0.085
 necks+0.083
Neg logit contributions
t-0.079
 happened-0.069
 help-0.066
 day-0.066
 we-0.062
Token ost
Token ID23619
Feature activation+3.66e+00

Pos logit contributions
 necks+0.411
opes+0.408
ping+0.404
cks+0.399
 valleys+0.394
Neg logit contributions
t-0.330
 happened-0.296
 awaited-0.294
 please-0.285
 week-0.277
Tokenric
Token ID1173
Feature activation+2.53e+01

Pos logit contributions
rily+0.064
 valleys+0.064
aron+0.063
uted+0.059
 necks+0.059
Neg logit contributions
t-0.313
 happened-0.303
 help-0.297
 day-0.295
 please-0.292
Tokenhes
Token ID956
Feature activation+5.65e+00

Pos logit contributions
aters+0.970
 necks+0.962
rily+0.913
 valleys+0.907
opes+0.900
Neg logit contributions
t-1.747
 happened-1.686
 day-1.601
 help-1.583
 please-1.552
Token are
Token ID389
Feature activation+1.07e-01

Pos logit contributions
cks+0.342
ping+0.334
aron+0.327
uted+0.327
 necks+0.325
Neg logit contributions
t-0.221
 happened-0.218
 awaited-0.212
 help-0.203
 reward-0.203
Token mean
Token ID1612
Feature activation-9.36e+00

Pos logit contributions
cks+0.006
 necks+0.006
ping+0.006
opes+0.006
aron+0.006
Neg logit contributions
t-0.005
 happened-0.004
 day-0.004
 help-0.004
 awaited-0.004
Token!
Token ID0
Feature activation+4.11e+00

Pos logit contributions
t+0.467
 happened+0.448
 help+0.432
 day+0.429
 please+0.422
Neg logit contributions
cks-0.498
 necks-0.496
aron-0.495
opes-0.493
ping-0.491
Token They
Token ID1119
Feature activation+8.07e+00

Pos logit contributions
 valleys+0.220
 necks+0.218
opes+0.211
ping+0.208
cks+0.207
Neg logit contributions
t-0.220
 please-0.207
 happened-0.203
 help-0.197
 we-0.192
Token
Token ID198
Feature activation-7.31e-01

Pos logit contributions
cks+0.080
 necks+0.080
ping+0.079
opes+0.079
aron+0.079
Neg logit contributions
t-0.076
 happened-0.073
 help-0.070
 day-0.070
 please-0.069
Token
Token ID198
Feature activation-7.36e-01

Pos logit contributions
t+0.035
 happened+0.035
 help+0.033
 day+0.033
 reward+0.033
Neg logit contributions
cks-0.039
aron-0.039
uted-0.038
 necks-0.038
opes-0.038
Token"
Token ID1
Feature activation-2.40e+00

Pos logit contributions
t+0.031
 happened+0.031
 help+0.029
 day+0.029
 please+0.028
Neg logit contributions
cks-0.044
 necks-0.044
aron-0.044
uted-0.044
opes-0.044
TokenO
Token ID46
Feature activation-5.84e-01

Pos logit contributions
t+0.126
 happened+0.118
 help+0.114
 please+0.114
 day+0.113
Neg logit contributions
cks-0.128
opes-0.128
ping-0.128
rily-0.126
aron-0.125
Tokenst
Token ID301
Feature activation+5.61e+00

Pos logit contributions
 help+0.018
 happened+0.018
t+0.018
 please+0.017
 reward+0.017
Neg logit contributions
cks-0.042
aron-0.041
 necks-0.041
opes-0.041
ping-0.040
Tokenric
Token ID1173
Feature activation+2.53e+01

Pos logit contributions
aron+0.322
 necks+0.320
uted+0.319
 valleys+0.319
ping+0.318
Neg logit contributions
t-0.258
 happened-0.243
 help-0.236
 day-0.232
 please-0.231
Tokenhes
Token ID956
Feature activation+5.65e+00

Pos logit contributions
aters+0.961
 necks+0.941
rily+0.910
 valleys+0.887
aron+0.876
Neg logit contributions
t-1.737
 happened-1.695
 help-1.597
 day-1.592
 please-1.571
Token do
Token ID466
Feature activation-8.47e+00

Pos logit contributions
cks+0.326
ping+0.313
uted+0.308
aron+0.306
opes+0.304
Neg logit contributions
t-0.246
 happened-0.238
 awaited-0.234
 week-0.227
 help-0.220
Token not
Token ID407
Feature activation+1.02e+00

Pos logit contributions
t+0.294
 happened+0.284
 day+0.263
 help+0.261
 week+0.257
Neg logit contributions
cks-0.580
 necks-0.572
opes-0.572
aron-0.565
uted-0.564
Token like
Token ID588
Feature activation+2.31e+00

Pos logit contributions
ping+0.065
cks+0.064
aron+0.064
 necks+0.063
uted+0.063
Neg logit contributions
t-0.039
 happened-0.036
 awaited-0.035
 reward-0.032
 day-0.032
Token people
Token ID661
Feature activation-1.70e+00

Pos logit contributions
cks+0.145
opes+0.145
 necks+0.144
ping+0.143
uted+0.142
Neg logit contributions
t-0.093
 happened-0.080
 awaited-0.080
 reward-0.079
ha-0.077
Token but
Token ID475
Feature activation+6.11e+00

Pos logit contributions
 happened+0.240
t+0.239
 week+0.212
 day+0.211
 awaited+0.205
Neg logit contributions
 necks-0.476
rily-0.464
cks-0.463
aron-0.463
uted-0.457
Token be
Token ID307
Feature activation+1.41e+00

Pos logit contributions
 necks+0.370
 neck+0.359
cks+0.328
opes+0.327
 ears+0.321
Neg logit contributions
t-0.275
ha-0.254
 awaited-0.239
 happened-0.238
 week-0.217
Token careful
Token ID8161
Feature activation-2.69e+00

Pos logit contributions
opes+0.104
aters+0.102
rily+0.102
 valleys+0.101
uted+0.100
Neg logit contributions
 help-0.042
 please-0.041
 day-0.039
t-0.037
 week-0.036
Token.
Token ID13
Feature activation+1.52e+00

Pos logit contributions
t+0.120
 help+0.109
 day+0.108
 please+0.106
 happened+0.106
Neg logit contributions
 valleys-0.164
cks-0.160
 necks-0.160
opes-0.160
uted-0.159
Token Ost
Token ID38919
Feature activation+3.77e+00

Pos logit contributions
ping+0.083
uted+0.083
opes+0.082
 valleys+0.082
cks+0.082
Neg logit contributions
t-0.073
 please-0.073
 help-0.071
 thank-0.068
 day-0.066
Tokenric
Token ID1173
Feature activation+2.52e+01

Pos logit contributions
rily+0.117
 valleys+0.104
aron+0.104
edly+0.103
aters+0.102
Neg logit contributions
 day-0.275
t-0.271
 help-0.269
 week-0.257
 done-0.252
Tokenhes
Token ID956
Feature activation+5.61e+00

Pos logit contributions
aters+0.942
 necks+0.930
rily+0.910
aron+0.882
opes+0.878
Neg logit contributions
t-1.732
 happened-1.676
 day-1.617
 help-1.601
 please-1.566
Token can
Token ID460
Feature activation-8.65e+00

Pos logit contributions
cks+0.358
 necks+0.353
ping+0.351
aron+0.351
opes+0.349
Neg logit contributions
t-0.217
 happened-0.211
 help-0.194
 day-0.192
 awaited-0.192
Token be
Token ID307
Feature activation+1.40e+00

Pos logit contributions
t+0.321
 happened+0.309
 day+0.287
 help+0.286
 please+0.278
Neg logit contributions
cks-0.569
 necks-0.566
aron-0.563
opes-0.562
ping-0.559
Token gr
Token ID1036
Feature activation+3.06e+00

Pos logit contributions
opes+0.076
aron+0.076
cks+0.076
 necks+0.075
uted+0.075
Neg logit contributions
t-0.068
 happened-0.065
 help-0.063
 day-0.062
 please-0.061
Tokenumpy
Token ID32152
Feature activation+3.80e-01

Pos logit contributions
rily+0.146
 valleys+0.141
 necks+0.138
opes+0.133
bes+0.133
Neg logit contributions
t-0.185
 day-0.164
 week-0.161
 happened-0.160
 help-0.156
TokenYes
Token ID5297
Feature activation+8.42e-01

Pos logit contributions
t+0.137
 day+0.131
 happened+0.130
 help+0.128
 week+0.126
Neg logit contributions
opes-0.120
rily-0.118
aron-0.117
ping-0.117
cks-0.116
Token,
Token ID11
Feature activation-7.10e+00

Pos logit contributions
rily+0.055
cks+0.052
opes+0.052
 necks+0.052
ping+0.051
Neg logit contributions
 happened-0.032
t-0.032
 awaited-0.032
 week-0.029
 day-0.028
Token they
Token ID484
Feature activation-3.94e+00

Pos logit contributions
t+0.279
 happened+0.260
 day+0.241
 awaited+0.240
 week+0.239
Neg logit contributions
 necks-0.454
cks-0.454
opes-0.447
rily-0.446
ping-0.445
Token are
Token ID389
Feature activation+9.11e-02

Pos logit contributions
t+0.153
 happened+0.139
 day+0.132
 please+0.131
 week+0.130
Neg logit contributions
cks-0.258
 necks-0.255
opes-0.254
 valleys-0.251
ping-0.251
Token ost
Token ID23619
Feature activation+3.61e+00

Pos logit contributions
cks+0.006
 necks+0.006
aron+0.006
opes+0.006
ping+0.006
Neg logit contributions
t-0.004
 happened-0.004
 help-0.003
 day-0.003
 please-0.003
Tokenric
Token ID1173
Feature activation+2.52e+01

Pos logit contributions
aron+0.072
 valleys+0.069
 necks+0.069
rily+0.069
cks+0.069
Neg logit contributions
t-0.300
 happened-0.291
 help-0.285
 day-0.284
 please-0.280
Tokenhes
Token ID956
Feature activation+5.62e+00

Pos logit contributions
 necks+0.828
aters+0.808
aron+0.806
opes+0.796
rily+0.789
Neg logit contributions
t-1.786
 happened-1.744
 help-1.684
 day-1.683
 please-1.651
Token,"
Token ID553
Feature activation-5.96e+00

Pos logit contributions
cks+0.345
 necks+0.341
aron+0.340
ping+0.339
opes+0.338
Neg logit contributions
t-0.233
 happened-0.223
 help-0.208
 day-0.207
 awaited-0.204
Token mom
Token ID1995
Feature activation-9.41e+00

Pos logit contributions
t+0.290
 happened+0.246
 awaited+0.244
ha+0.235
 week+0.232
Neg logit contributions
 necks-0.356
cks-0.350
efully-0.339
 valleys-0.335
aron-0.330
Token said
Token ID531
Feature activation-9.04e+00

Pos logit contributions
t+0.261
 happened+0.241
 help+0.231
 day+0.226
 reward+0.223
Neg logit contributions
aron-0.727
uted-0.713
ping-0.700
cks-0.699
 necks-0.698
Token.
Token ID13
Feature activation+1.53e+00

Pos logit contributions
t+0.442
 happened+0.420
 day+0.406
 awaited+0.402
 week+0.399
Neg logit contributions
aron-0.491
ping-0.486
rily-0.485
cks-0.481
 necks-0.480
Tokenie
Token ID494
Feature activation-3.85e+00

Pos logit contributions
t+0.029
 happened+0.027
 help+0.026
 day+0.026
 please+0.026
Neg logit contributions
cks-0.040
 necks-0.040
aron-0.040
opes-0.040
uted-0.039
Token.
Token ID13
Feature activation+1.53e+00

Pos logit contributions
 day+0.142
t+0.136
 would+0.135
 help+0.134
 please+0.126
Neg logit contributions
 valleys-0.261
cks-0.258
ags-0.251
uted-0.251
opes-0.250
Token Unlike
Token ID12101
Feature activation+7.95e+00

Pos logit contributions
cks+0.102
uted+0.102
opes+0.100
 necks+0.100
aron+0.100
Neg logit contributions
t-0.060
 day-0.057
 please-0.055
 help-0.054
 week-0.052
Token other
Token ID584
Feature activation-6.77e+00

Pos logit contributions
cks+0.475
ping+0.473
 necks+0.465
opes+0.463
 valleys+0.462
Neg logit contributions
t-0.348
 happened-0.340
 help-0.313
 please-0.311
 reward-0.310
Token ost
Token ID23619
Feature activation+3.62e+00

Pos logit contributions
t+0.393
 happened+0.377
 help+0.361
 day+0.359
 please+0.357
Neg logit contributions
 necks-0.310
cks-0.308
ping-0.304
opes-0.304
aron-0.302
Tokenric
Token ID1173
Feature activation+2.52e+01

Pos logit contributions
rily+0.065
aron+0.063
 valleys+0.060
uted+0.058
 necks+0.056
Neg logit contributions
t-0.308
 happened-0.299
 day-0.293
 help-0.290
 week-0.287
Tokenhes
Token ID956
Feature activation+5.60e+00

Pos logit contributions
 necks+0.917
aters+0.900
aron+0.879
opes+0.865
rily+0.865
Neg logit contributions
t-1.742
 happened-1.688
 day-1.630
 help-1.603
 week-1.587
Token,
Token ID11
Feature activation-7.10e+00

Pos logit contributions
cks+0.347
ping+0.346
opes+0.343
 necks+0.342
aron+0.339
Neg logit contributions
t-0.219
 happened-0.208
 help-0.198
 please-0.197
 reward-0.195
Token his
Token ID465
Feature activation+2.79e+00

Pos logit contributions
t+0.250
 happened+0.235
 day+0.229
 help+0.227
 please+0.223
Neg logit contributions
aron-0.491
cks-0.490
 necks-0.485
uted-0.484
aters-0.483
Token feathers
Token ID27400
Feature activation+1.32e+01

Pos logit contributions
 necks+0.158
opes+0.154
cks+0.154
ping+0.153
aron+0.152
Neg logit contributions
t-0.136
 happened-0.128
 help-0.120
 please-0.120
 awaited-0.119
Token gl
Token ID1278
Feature activation+6.60e+00

Pos logit contributions
ping+0.850
cks+0.850
 necks+0.849
opes+0.845
aron+0.841
Neg logit contributions
t-0.495
 happened-0.466
 help-0.449
 please-0.445
 day-0.436
TokenLook
Token ID8567
Feature activation+2.84e+00

Pos logit contributions
rily+0.078
cks+0.077
bes+0.077
ags+0.076
opes+0.075
Neg logit contributions
t-0.071
 day-0.067
 would-0.065
 week-0.064
ha-0.064
Token,
Token ID11
Feature activation-7.13e+00

Pos logit contributions
cks+0.186
uted+0.180
opes+0.179
rily+0.179
 necks+0.175
Neg logit contributions
t-0.121
 week-0.102
 happened-0.102
 awaited-0.098
 day-0.096
Token mom
Token ID1995
Feature activation-9.46e+00

Pos logit contributions
t+0.346
 happened+0.298
 awaited+0.280
 week+0.277
 day+0.268
Neg logit contributions
 necks-0.408
 valleys-0.404
cks-0.399
 neck-0.397
opes-0.397
Token,
Token ID11
Feature activation-7.13e+00

Pos logit contributions
t+0.341
 help+0.307
 happened+0.305
 reward+0.292
 please+0.275
Neg logit contributions
aters-0.647
aron-0.645
ping-0.637
uted-0.633
cks-0.628
Token ost
Token ID23619
Feature activation+3.58e+00

Pos logit contributions
t+0.367
 happened+0.315
 week+0.298
 awaited+0.294
 day+0.293
Neg logit contributions
 valleys-0.387
 necks-0.386
cks-0.378
 neck-0.377
opes-0.369
Tokenric
Token ID1173
Feature activation+2.52e+01

Pos logit contributions
rily+0.059
aron+0.059
 valleys+0.057
uted+0.055
 necks+0.055
Neg logit contributions
t-0.308
 happened-0.299
 help-0.292
 day-0.292
 please-0.288
Tokenhes
Token ID956
Feature activation+5.59e+00

Pos logit contributions
aters+0.935
 necks+0.921
rily+0.891
aron+0.884
opes+0.866
Neg logit contributions
t-1.708
 happened-1.676
 day-1.604
 help-1.596
 please-1.563
Token!"
Token ID2474
Feature activation+1.40e+00

Pos logit contributions
cks+0.358
ping+0.351
 necks+0.350
opes+0.349
uted+0.348
Neg logit contributions
t-0.219
 happened-0.209
 help-0.194
 day-0.192
 awaited-0.191
Token
Token ID198
Feature activation-7.54e-01

Pos logit contributions
cks+0.075
aron+0.074
ping+0.074
opes+0.074
 necks+0.073
Neg logit contributions
t-0.071
 happened-0.068
 help-0.067
 day-0.066
 please-0.065
Token
Token ID198
Feature activation-7.65e-01

Pos logit contributions
t+0.039
 happened+0.039
 reward+0.037
 help+0.037
 awaited+0.036
Neg logit contributions
cks-0.037
uted-0.037
aron-0.037
 necks-0.036
opes-0.036
Token"
Token ID1
Feature activation-2.43e+00

Pos logit contributions
t+0.045
 happened+0.044
 help+0.042
 day+0.042
 please+0.041
Neg logit contributions
cks-0.034
 necks-0.034
aron-0.034
opes-0.033
uted-0.033
Token should
Token ID815
Feature activation-8.26e+00

Pos logit contributions
cks+0.396
opes+0.396
 necks+0.395
aron+0.394
uted+0.394
Neg logit contributions
t-0.211
 happened-0.197
 day-0.195
 week-0.193
 awaited-0.184
Token not
Token ID407
Feature activation+9.19e-01

Pos logit contributions
t+0.295
 happened+0.286
 awaited+0.263
 week+0.251
 day+0.250
Neg logit contributions
 necks-0.553
aron-0.552
cks-0.549
opes-0.545
ping-0.536
Token tease
Token ID34691
Feature activation-4.05e+00

Pos logit contributions
cks+0.057
 necks+0.057
aron+0.057
ping+0.056
opes+0.056
Neg logit contributions
t-0.035
 happened-0.034
 awaited-0.032
 day-0.031
 week-0.031
Token the
Token ID262
Feature activation+4.69e-01

Pos logit contributions
t+0.153
 happened+0.149
 help+0.146
 day+0.141
 please+0.140
Neg logit contributions
aron-0.261
rily-0.260
 valleys-0.258
 necks-0.258
opes-0.257
Token ost
Token ID23619
Feature activation+3.58e+00

Pos logit contributions
cks+0.023
 necks+0.023
aron+0.023
opes+0.023
uted+0.023
Neg logit contributions
t-0.025
 happened-0.024
 help-0.023
 day-0.023
 please-0.023
Tokenric
Token ID1173
Feature activation+2.52e+01

Pos logit contributions
rily+0.064
 valleys+0.063
aron+0.062
uted+0.058
 necks+0.057
Neg logit contributions
t-0.306
 happened-0.294
 help-0.289
 day-0.289
 please-0.283
Tokenhes
Token ID956
Feature activation+5.59e+00

Pos logit contributions
 necks+0.767
cks+0.765
aron+0.761
opes+0.756
ping+0.747
Neg logit contributions
t-1.822
 happened-1.770
 help-1.724
 day-1.718
 please-1.698
Token.
Token ID13
Feature activation+1.47e+00

Pos logit contributions
cks+0.286
ping+0.284
aron+0.284
 necks+0.281
uted+0.280
Neg logit contributions
t-0.276
 happened-0.274
 awaited-0.257
 help-0.250
 reward-0.248
Token They
Token ID1119
Feature activation+8.05e+00

Pos logit contributions
ping+0.075
rily+0.075
 valleys+0.073
 necks+0.073
opes+0.073
Neg logit contributions
 please-0.076
t-0.076
 help-0.074
 we-0.071
 thank-0.070
Token are
Token ID389
Feature activation+7.75e-02

Pos logit contributions
 necks+0.513
cks+0.509
opes+0.505
uted+0.495
ping+0.494
Neg logit contributions
t-0.296
 happened-0.283
 week-0.279
 day-0.270
 please-0.265
Token not
Token ID407
Feature activation+9.44e-01

Pos logit contributions
cks+0.005
aron+0.005
 necks+0.005
opes+0.005
uted+0.005
Neg logit contributions
t-0.003
 happened-0.003
 help-0.003
 day-0.003
 please-0.003
Token shouted
Token ID17293
Feature activation-6.73e-01

Pos logit contributions
t+0.382
 happened+0.365
 help+0.352
 please+0.342
 day+0.330
Neg logit contributions
rily-0.591
opes-0.590
 valleys-0.587
cks-0.587
aters-0.581
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
t+0.030
 happened+0.029
 day+0.027
 help+0.027
 week+0.026
Neg logit contributions
aron-0.039
cks-0.039
 necks-0.039
ping-0.039
uted-0.039
Token "
Token ID366
Feature activation+1.36e+00

Pos logit contributions
aron+0.076
cks+0.076
 necks+0.076
opes+0.075
uted+0.075
Neg logit contributions
t-0.072
 happened-0.069
 help-0.067
 day-0.067
 week-0.065
TokenThe
Token ID464
Feature activation+7.16e+00

Pos logit contributions
opes+0.090
aters+0.086
aron+0.086
ping+0.085
rily+0.085
Neg logit contributions
t-0.066
 we-0.055
 they-0.055
 please-0.054
 day-0.053
Token ost
Token ID23619
Feature activation+3.56e+00

Pos logit contributions
 necks+0.370
cks+0.366
opes+0.365
ping+0.363
aron+0.362
Neg logit contributions
t-0.378
 happened-0.360
 help-0.346
 please-0.341
 day-0.340
Tokenric
Token ID1173
Feature activation+2.52e+01

Pos logit contributions
rily+0.081
 valleys+0.075
aron+0.073
uted+0.068
bes+0.067
Neg logit contributions
t-0.292
 happened-0.276
 day-0.271
 help-0.269
 please-0.264
Tokenhes
Token ID956
Feature activation+5.56e+00

Pos logit contributions
 necks+0.892
aters+0.883
rily+0.843
aron+0.837
opes+0.836
Neg logit contributions
t-1.785
 happened-1.719
 day-1.649
 help-1.628
 please-1.606
Token are
Token ID389
Feature activation+4.75e-02

Pos logit contributions
cks+0.350
ping+0.341
uted+0.337
 necks+0.336
opes+0.336
Neg logit contributions
t-0.214
 happened-0.208
 help-0.196
 awaited-0.194
 week-0.190
Token so
Token ID523
Feature activation+6.68e+00

Pos logit contributions
aron+0.003
 necks+0.003
uted+0.003
opes+0.003
cks+0.003
Neg logit contributions
t-0.002
 happened-0.002
 help-0.002
 day-0.002
 please-0.002
Token funny
Token ID8258
Feature activation-1.79e+00

Pos logit contributions
cks+0.375
 necks+0.370
aron+0.366
opes+0.365
uted+0.365
Neg logit contributions
t-0.315
 happened-0.305
 help-0.291
 day-0.286
 please-0.285
Token!"
Token ID2474
Feature activation+1.38e+00

Pos logit contributions
t+0.068
 happened+0.065
 day+0.064
 help+0.062
 please+0.062
Neg logit contributions
rily-0.114
 valleys-0.113
 necks-0.113
ags-0.113
cks-0.112
TokenAt
Token ID2953
Feature activation+2.63e+00

Pos logit contributions
t+0.045
 day+0.041
 week+0.041
 happened+0.040
 please+0.040
Neg logit contributions
cks-0.044
ping-0.043
 necks-0.043
opes-0.042
aron-0.042
Token the
Token ID262
Feature activation+4.35e-01

Pos logit contributions
 valleys+0.137
cks+0.127
ags+0.123
 rivers+0.122
ping+0.121
Neg logit contributions
t-0.143
 happened-0.129
 please-0.121
ha-0.119
 awaited-0.117
Token end
Token ID886
Feature activation-4.47e+00

Pos logit contributions
 valleys+0.029
 necks+0.028
ping+0.027
opes+0.027
cks+0.027
Neg logit contributions
t-0.016
 happened-0.016
 please-0.014
 awaited-0.013
 help-0.013
Token of
Token ID286
Feature activation-7.24e+00

Pos logit contributions
 happened+0.180
t+0.166
 reward+0.160
 would+0.160
 help+0.156
Neg logit contributions
 valleys-0.249
aters-0.247
 piles-0.241
aron-0.237
ady-0.233
Token the
Token ID262
Feature activation+4.48e-01

Pos logit contributions
t+0.352
 happened+0.321
 please+0.311
 would+0.300
 help+0.297
Neg logit contributions
cks-0.401
 valleys-0.392
 necks-0.390
aron-0.389
ping-0.387
Token week
Token ID1285
Feature activation-1.55e+01

Pos logit contributions
 valleys+0.033
 necks+0.033
 strings+0.032
ping+0.032
opes+0.031
Neg logit contributions
 happened-0.012
t-0.011
 please-0.011
ha-0.008
 would-0.008
Token,
Token ID11
Feature activation-7.15e+00

Pos logit contributions
t+0.470
 happened+0.411
 help+0.401
 please+0.394
ha+0.370
Neg logit contributions
aron-1.075
 valleys-1.072
aters-1.061
uted-1.046
 necks-1.045
Token Sus
Token ID8932
Feature activation-1.25e-02

Pos logit contributions
t+0.252
 happened+0.238
 help+0.222
 day+0.217
 please+0.214
Neg logit contributions
aron-0.474
 valleys-0.473
uted-0.472
rily-0.472
 necks-0.472
Tokenie
Token ID494
Feature activation-3.91e+00

Pos logit contributions
t+0.000
 happened+0.000
 help+0.000
 day+0.000
 please+0.000
Neg logit contributions
cks-0.001
 necks-0.001
aron-0.001
opes-0.001
ping-0.001
Token said
Token ID531
Feature activation-9.11e+00

Pos logit contributions
t+0.159
 happened+0.148
 help+0.141
 day+0.139
 please+0.139
Neg logit contributions
 necks-0.242
aron-0.242
opes-0.239
cks-0.239
uted-0.239
Token goodbye
Token ID24829
Feature activation-3.72e+00

Pos logit contributions
t+0.386
 awaited+0.373
 happened+0.363
 day+0.351
ll+0.351
Neg logit contributions
rily-0.519
edly-0.493
uted-0.486
aron-0.475
efully-0.469
Token and
Token ID290
Feature activation+8.41e+00

Pos logit contributions
opes+0.034
cks+0.034
uted+0.034
aters+0.033
 necks+0.033
Neg logit contributions
t-0.040
 help-0.037
 happened-0.037
 day-0.037
 week-0.036
Token told
Token ID1297
Feature activation-7.41e+00

Pos logit contributions
 necks+0.480
 valleys+0.462
cks+0.456
aron+0.441
 neck+0.440
Neg logit contributions
t-0.413
ha-0.362
 happened-0.355
 problem-0.343
 week-0.340
Token their
Token ID511
Feature activation+3.54e+00

Pos logit contributions
t+0.402
 happened+0.365
 awaited+0.348
ha+0.343
 week+0.341
Neg logit contributions
cks-0.381
 necks-0.378
uted-0.376
ping-0.376
opes-0.373
Token mom
Token ID1995
Feature activation-9.49e+00

Pos logit contributions
 piles+0.204
opes+0.202
 necks+0.202
 ears+0.200
 backs+0.196
Neg logit contributions
t-0.160
 awaited-0.143
ha-0.133
 happened-0.131
 please-0.130
Token what
Token ID644
Feature activation+4.31e+00

Pos logit contributions
t+0.445
 happened+0.423
 help+0.405
 day+0.401
 please+0.396
Neg logit contributions
cks-0.532
aron-0.531
 necks-0.530
ping-0.527
opes-0.526
Token happened
Token ID3022
Feature activation-1.55e+01

Pos logit contributions
 valleys+0.269
cks+0.266
bes+0.258
uted+0.257
 spots+0.257
Neg logit contributions
 reward-0.118
 please-0.117
use-0.104
t-0.104
ipop-0.102
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
t+0.737
 happened+0.706
 help+0.680
 day+0.676
 please+0.661
Neg logit contributions
cks-0.862
 necks-0.860
opes-0.859
aron-0.858
uted-0.850
Token
Token ID198
Feature activation-8.09e-01

Pos logit contributions
cks+0.086
ping+0.086
 necks+0.085
opes+0.085
aron+0.084
Neg logit contributions
t-0.066
 happened-0.063
 help-0.060
 day-0.060
 please-0.060
Token
Token ID198
Feature activation-8.00e-01

Pos logit contributions
t+0.037
 happened+0.036
 help+0.035
 day+0.034
 please+0.034
Neg logit contributions
cks-0.046
aron-0.045
 necks-0.045
opes-0.045
uted-0.045
TokenTheir
Token ID14574
Feature activation+6.40e+00

Pos logit contributions
t+0.035
 happened+0.033
 help+0.032
 day+0.032
 please+0.032
Neg logit contributions
cks-0.048
opes-0.048
 necks-0.048
ping-0.048
aron-0.047
Token mom
Token ID1995
Feature activation-9.47e+00

Pos logit contributions
 necks+0.423
opes+0.402
 ears+0.397
 piles+0.393
 backs+0.388
Neg logit contributions
t-0.255
 awaited-0.239
ha-0.235
 please-0.217
 happened-0.216
Token's
Token ID338
Feature activation-4.93e-01

Pos logit contributions
t+0.279
 day+0.251
 happened+0.249
 help+0.249
 week+0.247
Neg logit contributions
 necks-0.447
aron-0.442
ping-0.439
 valleys-0.438
opes-0.437
Token mom
Token ID1995
Feature activation-9.49e+00

Pos logit contributions
t+0.019
 awaited+0.017
 happened+0.017
ha+0.016
 week+0.015
Neg logit contributions
 necks-0.032
opes-0.031
 neck-0.031
ping-0.031
 valleys-0.030
Token saw
Token ID2497
Feature activation-5.11e+00

Pos logit contributions
t+0.338
 reward+0.306
 day+0.301
 week+0.290
 help+0.282
Neg logit contributions
ping-0.648
aron-0.642
uted-0.632
cks-0.625
opes-0.625
Token what
Token ID644
Feature activation+4.29e+00

Pos logit contributions
 happened+0.198
t+0.196
 help+0.189
 day+0.181
 please+0.180
Neg logit contributions
 necks-0.331
aron-0.329
cks-0.326
aters-0.323
opes-0.323
Token had
Token ID550
Feature activation-4.45e+00

Pos logit contributions
opes+0.281
uted+0.280
 strings+0.279
bes+0.278
 valleys+0.275
Neg logit contributions
 reward-0.118
 inconvenience-0.112
bye-0.107
t-0.104
 please-0.103
Token happened
Token ID3022
Feature activation-1.55e+01

Pos logit contributions
t+0.071
 please+0.066
 day+0.060
 week+0.057
 reward+0.057
Neg logit contributions
ping-0.367
uted-0.361
cks-0.356
opes-0.350
ps-0.345
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
t+0.736
 happened+0.716
 day+0.705
 help+0.684
 week+0.664
Neg logit contributions
cks-0.888
 valleys-0.874
opes-0.873
 necks-0.868
aters-0.867
Token She
Token ID1375
Feature activation+3.43e+00

Pos logit contributions
cks+0.070
 necks+0.070
aron+0.069
opes+0.069
ping+0.069
Neg logit contributions
t-0.081
 happened-0.078
 help-0.075
 day-0.075
 please-0.074
Token stepped
Token ID10764
Feature activation+5.08e+00

Pos logit contributions
aron+0.218
uted+0.215
 necks+0.213
ping+0.212
cks+0.212
Neg logit contributions
t-0.134
 day-0.123
 week-0.121
 happened-0.121
 awaited-0.116
Token in
Token ID287
Feature activation+1.49e+00

Pos logit contributions
opes+0.306
cks+0.302
 necks+0.301
aters+0.293
aron+0.292
Neg logit contributions
t-0.236
 help-0.236
 please-0.225
 happened-0.217
 day-0.216
Token and
Token ID290
Feature activation+8.41e+00

Pos logit contributions
opes+0.081
cks+0.080
uted+0.078
 necks+0.077
aters+0.077
Neg logit contributions
 help-0.079
t-0.076
 happened-0.074
 day-0.073
 please-0.072
Token into
Token ID656
Feature activation+7.49e+00

Pos logit contributions
cks+0.086
opes+0.084
uted+0.083
aron+0.083
 necks+0.082
Neg logit contributions
 help-0.044
 day-0.043
t-0.042
 happened-0.041
 thank-0.040
Token it
Token ID340
Feature activation-2.23e+00

Pos logit contributions
aron+0.559
uted+0.544
cks+0.537
ping+0.534
ksh+0.532
Neg logit contributions
 help-0.265
 day-0.237
 happened-0.219
 week-0.215
t-0.207
Token,
Token ID11
Feature activation-7.16e+00

Pos logit contributions
t+0.117
 day+0.114
 help+0.114
 happened+0.109
 please+0.108
Neg logit contributions
cks-0.120
 necks-0.115
uted-0.115
opes-0.115
aron-0.115
Token but
Token ID475
Feature activation+6.01e+00

Pos logit contributions
 help+0.336
t+0.331
 day+0.326
 happened+0.325
 would+0.319
Neg logit contributions
aters-0.416
cks-0.409
opes-0.401
efully-0.391
uted-0.390
Token nothing
Token ID2147
Feature activation+3.46e+00

Pos logit contributions
 valleys+0.371
 necks+0.358
uted+0.348
ping+0.347
opes+0.346
Neg logit contributions
t-0.231
 happened-0.218
 reward-0.209
 help-0.208
 week-0.205
Token happened
Token ID3022
Feature activation-1.55e+01

Pos logit contributions
ping+0.223
aron+0.221
 valleys+0.214
cks+0.212
uted+0.211
Neg logit contributions
 please-0.103
 reward-0.092
t-0.090
 thank-0.087
 Sorry-0.086
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
t+0.714
 happened+0.676
 help+0.654
 day+0.649
 please+0.632
Neg logit contributions
cks-0.892
opes-0.886
aron-0.885
 necks-0.884
uted-0.877
Token
Token ID220
Feature activation+3.08e+00

Pos logit contributions
cks+0.079
 necks+0.076
ping+0.076
opes+0.075
uted+0.074
Neg logit contributions
t-0.078
 happened-0.072
 help-0.071
 day-0.071
 please-0.070
Token
Token ID198
Feature activation-8.00e-01

Pos logit contributions
 necks+0.189
cks+0.187
ping+0.187
opes+0.186
aron+0.186
Neg logit contributions
t-0.133
 happened-0.124
 help-0.119
 day-0.118
 please-0.116
Token
Token ID198
Feature activation-8.05e-01

Pos logit contributions
t+0.037
 happened+0.036
 help+0.035
 day+0.034
 please+0.034
Neg logit contributions
cks-0.044
aron-0.044
 necks-0.044
uted-0.044
opes-0.043
TokenThe
Token ID464
Feature activation+7.16e+00

Pos logit contributions
t+0.049
 week+0.043
 day+0.043
 please+0.043
 help+0.043
Neg logit contributions
cks-0.039
rily-0.039
ping-0.038
opes-0.038
aters-0.038
Token.
Token ID13
Feature activation+1.44e+00

Pos logit contributions
cks+0.410
 necks+0.408
 valleys+0.398
uted+0.391
bes+0.391
Neg logit contributions
t-0.249
 happened-0.234
 help-0.226
 day-0.224
 please-0.221
Token
Token ID198
Feature activation-8.18e-01

Pos logit contributions
aron+0.070
cks+0.070
opes+0.069
 necks+0.069
uted+0.069
Neg logit contributions
t-0.075
 happened-0.072
 day-0.071
 help-0.070
 week-0.070
Token
Token ID198
Feature activation-8.04e-01

Pos logit contributions
 happened+0.045
t+0.044
 reward+0.044
 problem+0.043
 day+0.042
Neg logit contributions
cks-0.037
aron-0.036
uted-0.036
 valleys-0.034
opes-0.034
Token"
Token ID1
Feature activation-2.48e+00

Pos logit contributions
 happened+0.039
t+0.037
 awaited+0.035
 day+0.035
 week+0.035
Neg logit contributions
cks-0.044
 necks-0.043
aron-0.042
opes-0.042
uted-0.042
TokenWhat
Token ID2061
Feature activation+9.61e+00

Pos logit contributions
t+0.126
 happened+0.121
 help+0.117
 day+0.115
 please+0.115
Neg logit contributions
cks-0.132
opes-0.132
 necks-0.131
aron-0.131
ping-0.131
Token happened
Token ID3022
Feature activation-1.55e+01

Pos logit contributions
uted+0.647
cks+0.638
opes+0.618
aron+0.601
ping+0.589
Neg logit contributions
t-0.293
 week-0.264
 reward-0.258
ha-0.246
 day-0.245
Token,
Token ID11
Feature activation-7.15e+00

Pos logit contributions
t+0.630
ha+0.549
 reward+0.545
 awaited+0.524
 happened+0.523
Neg logit contributions
aron-0.921
ping-0.920
uted-0.907
rily-0.897
cks-0.895
Token Sam
Token ID3409
Feature activation-7.80e+00

Pos logit contributions
t+0.247
 happened+0.224
 day+0.209
 week+0.207
 help+0.204
Neg logit contributions
cks-0.500
opes-0.497
 necks-0.495
aron-0.494
uted-0.494
Token?"
Token ID1701
Feature activation-1.41e+00

Pos logit contributions
t+0.323
 reward+0.273
 help+0.271
 please+0.249
 thank+0.249
Neg logit contributions
aron-0.512
ping-0.497
cks-0.489
uted-0.486
opes-0.479
Token his
Token ID465
Feature activation+2.76e+00

Pos logit contributions
t+0.068
ha+0.063
 awaited+0.061
 week+0.059
 reward+0.059
Neg logit contributions
cks-0.075
 necks-0.074
 neck-0.071
uted-0.070
 valleys-0.070
Token mom
Token ID1995
Feature activation-9.47e+00

Pos logit contributions
 necks+0.218
cks+0.216
opes+0.216
aron+0.215
uted+0.214
Neg logit contributions
t-0.068
 happened-0.061
 awaited-0.056
 help-0.054
 day-0.053
Token the
Token ID262
Feature activation+4.44e-01

Pos logit contributions
t+0.194
 happened+0.186
 help+0.178
 day+0.174
 please+0.171
Neg logit contributions
 necks-0.335
aron-0.333
cks-0.333
opes-0.332
ping-0.331
Token journal
Token ID3989
Feature activation-7.81e-01

Pos logit contributions
cks+0.024
 necks+0.024
aron+0.024
opes+0.024
ping+0.024
Neg logit contributions
t-0.021
 happened-0.021
 help-0.020
 day-0.020
 please-0.019
Token and
Token ID290
Feature activation+8.41e+00

Pos logit contributions
t+0.046
 happened+0.045
 help+0.043
 day+0.043
 please+0.042
Neg logit contributions
cks-0.035
aron-0.035
 necks-0.035
opes-0.035
ping-0.034
Token understood
Token ID7247
Feature activation-4.23e+00

Pos logit contributions
 necks+0.516
cks+0.513
uted+0.512
aron+0.510
ping+0.509
Neg logit contributions
t-0.357
 happened-0.315
 day-0.314
 week-0.309
 please-0.304
Token what
Token ID644
Feature activation+4.31e+00

Pos logit contributions
t+0.218
 happened+0.195
 day+0.194
 week+0.192
ha+0.189
Neg logit contributions
aron-0.222
cks-0.219
uted-0.218
 necks-0.214
opes-0.214
Token happened
Token ID3022
Feature activation-1.55e+01

Pos logit contributions
 spots+0.198
 circles+0.195
 shapes+0.194
bes+0.192
 piles+0.185
Neg logit contributions
bye-0.166
 reward-0.164
 inconvenience-0.161
ye-0.160
use-0.154
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
t+0.736
 happened+0.703
 help+0.676
 day+0.671
 please+0.656
Neg logit contributions
cks-0.867
 necks-0.863
opes-0.861
aron-0.860
 valleys-0.854
Token She
Token ID1375
Feature activation+3.43e+00

Pos logit contributions
cks+0.070
ping+0.069
 necks+0.069
opes+0.068
aron+0.067
Neg logit contributions
t-0.082
 happened-0.080
 help-0.077
 please-0.076
 day-0.076
Token hugged
Token ID41130
Feature activation+1.33e+00

Pos logit contributions
aron+0.223
uted+0.220
 necks+0.218
cks+0.217
ping+0.215
Neg logit contributions
t-0.130
 day-0.120
 week-0.118
 happened-0.117
 help-0.112
Token Anna
Token ID11735
Feature activation-5.03e+00

Pos logit contributions
cks+0.086
 necks+0.085
opes+0.085
aron+0.085
ping+0.085
Neg logit contributions
t-0.052
 happened-0.049
 help-0.047
 day-0.046
 please-0.046
Token and
Token ID290
Feature activation+8.41e+00

Pos logit contributions
 help+0.247
t+0.246
 day+0.246
 would+0.232
 thank+0.230
Neg logit contributions
cks-0.294
opes-0.287
 valleys-0.284
aters-0.264
 necks-0.263
Token told
Token ID1297
Feature activation-7.40e+00

Pos logit contributions
 necks+0.497
aron+0.485
 valleys+0.479
cks+0.478
uted+0.474
Neg logit contributions
t-0.338
 happened-0.317
 day-0.299
 week-0.294
 please-0.293
Token Mom
Token ID11254
Feature activation-6.52e+00

Pos logit contributions
t+0.374
 happened+0.338
 awaited+0.322
ha+0.316
 week+0.310
Neg logit contributions
 necks-0.412
opes-0.408
ping-0.405
cks-0.404
uted-0.404
Token and
Token ID290
Feature activation+8.41e+00

Pos logit contributions
t+0.330
 happened+0.317
 help+0.298
 day+0.295
 reward+0.294
Neg logit contributions
 necks-0.341
ping-0.339
aron-0.339
opes-0.337
uted-0.336
Token Dad
Token ID17415
Feature activation-4.71e+00

Pos logit contributions
 necks+0.415
uted+0.392
 wrists+0.391
aron+0.381
ksh+0.379
Neg logit contributions
t-0.456
ha-0.427
 awaited-0.395
 problem-0.391
 reward-0.381
Token what
Token ID644
Feature activation+4.31e+00

Pos logit contributions
t+0.231
 happened+0.215
ha+0.208
 reward+0.202
 please+0.201
Neg logit contributions
 necks-0.252
ping-0.251
uted-0.250
aron-0.247
cks-0.245
Token happened
Token ID3022
Feature activation-1.55e+01

Pos logit contributions
uted+0.283
 spots+0.268
cks+0.265
 stripes+0.264
 strings+0.259
Neg logit contributions
use-0.118
t-0.112
ha-0.108
 reward-0.106
 please-0.100
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
t+0.728
 happened+0.697
 help+0.673
 day+0.669
 please+0.652
Neg logit contributions
cks-0.880
opes-0.876
 necks-0.875
aron-0.874
 valleys-0.867
Token Mom
Token ID11254
Feature activation-6.51e+00

Pos logit contributions
cks+0.081
ping+0.080
 necks+0.077
opes+0.077
uted+0.077
Neg logit contributions
t-0.073
 happened-0.072
 day-0.070
 please-0.070
 week-0.069
Token and
Token ID290
Feature activation+8.42e+00

Pos logit contributions
t+0.425
 happened+0.412
 help+0.401
 day+0.399
 please+0.394
Neg logit contributions
cks-0.248
 necks-0.245
opes-0.244
aron-0.243
ping-0.241
Token Dad
Token ID17415
Feature activation-4.70e+00

Pos logit contributions
 necks+0.513
uted+0.490
rily+0.490
aron+0.488
ping+0.486
Neg logit contributions
t-0.372
 happened-0.331
ha-0.323
 awaited-0.320
 day-0.312
Token were
Token ID547
Feature activation+3.18e-01

Pos logit contributions
t+0.193
 happened+0.173
 week+0.172
 day+0.171
 please+0.166
Neg logit contributions
uted-0.291
aron-0.291
 necks-0.288
ping-0.283
cks-0.283
Token them
Token ID606
Feature activation+1.47e+00

Pos logit contributions
 help+0.116
 please+0.110
 day+0.108
t+0.108
 happened+0.108
Neg logit contributions
cks-0.187
opes-0.185
aters-0.183
aron-0.183
 valleys-0.182
Token and
Token ID290
Feature activation+8.40e+00

Pos logit contributions
 valleys+0.088
cks+0.088
opes+0.084
 necks+0.080
rily+0.080
Neg logit contributions
 help-0.072
 day-0.070
t-0.069
 thank-0.067
 to-0.065
Token tell
Token ID1560
Feature activation-4.00e+00

Pos logit contributions
 necks+0.608
cks+0.608
aron+0.603
opes+0.598
uted+0.596
Neg logit contributions
t-0.266
 happened-0.240
 day-0.221
 week-0.213
 please-0.212
Token them
Token ID606
Feature activation+1.47e+00

Pos logit contributions
t+0.240
 happened+0.217
ha+0.211
 awaited+0.210
 reward+0.209
Neg logit contributions
cks-0.178
ping-0.177
 necks-0.177
uted-0.176
opes-0.175
Token what
Token ID644
Feature activation+4.31e+00

Pos logit contributions
uted+0.083
opes+0.083
 necks+0.083
cks+0.083
ping+0.082
Neg logit contributions
t-0.064
 happened-0.060
 day-0.058
 reward-0.058
 awaited-0.057
Token happened
Token ID3022
Feature activation-1.55e+01

Pos logit contributions
cks+0.253
 spots+0.250
 necks+0.243
 valleys+0.242
 circles+0.239
Neg logit contributions
 reward-0.123
t-0.118
 please-0.118
ha-0.117
ipop-0.109
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
t+0.733
 happened+0.702
 help+0.676
 day+0.672
 please+0.657
Neg logit contributions
cks-0.866
 necks-0.865
aron-0.864
opes-0.863
 valleys-0.854
Token Mom
Token ID11254
Feature activation-6.51e+00

Pos logit contributions
ping+0.067
cks+0.066
opes+0.065
rily+0.065
uted+0.064
Neg logit contributions
t-0.086
 happened-0.085
 day-0.081
 help-0.081
 please-0.081
Token and
Token ID290
Feature activation+8.42e+00

Pos logit contributions
t+0.346
 happened+0.344
 help+0.338
 would+0.337
 day+0.329
Neg logit contributions
rily-0.321
 valleys-0.315
opes-0.307
cks-0.304
ping-0.303
Token dad
Token ID9955
Feature activation-4.68e+00

Pos logit contributions
 necks+0.544
 valleys+0.517
opes+0.511
cks+0.511
ping+0.510
Neg logit contributions
t-0.363
 happened-0.311
ha-0.299
 awaited-0.298
 reward-0.297
Token are
Token ID389
Feature activation+4.75e-02

Pos logit contributions
t+0.157
 happened+0.147
 day+0.138
 help+0.137
 please+0.134
Neg logit contributions
cks-0.326
 necks-0.324
aron-0.324
opes-0.322
uted-0.321
Token and
Token ID290
Feature activation+8.41e+00

Pos logit contributions
aron+0.199
ping+0.199
 necks+0.197
opes+0.196
uted+0.196
Neg logit contributions
t-0.275
 happened-0.263
 help-0.255
 day-0.251
 reward-0.251
Token didn
Token ID1422
Feature activation-2.04e+00

Pos logit contributions
ping+0.478
 necks+0.475
 valleys+0.472
cks+0.463
opes+0.460
Neg logit contributions
t-0.384
 reward-0.340
ha-0.337
 happened-0.335
 awaited-0.322
Token't
Token ID470
Feature activation-7.16e+00

Pos logit contributions
t+0.043
 happened+0.042
 day+0.038
 help+0.037
 week+0.036
Neg logit contributions
cks-0.162
uted-0.161
opes-0.161
aron-0.160
ping-0.159
Token know
Token ID760
Feature activation-6.25e+00

Pos logit contributions
t+0.276
 happened+0.251
 awaited+0.243
 day+0.227
 reward+0.226
Neg logit contributions
ping-0.460
aron-0.459
cks-0.442
 necks-0.436
uted-0.433
Token what
Token ID644
Feature activation+4.31e+00

Pos logit contributions
t+0.307
 happened+0.281
 day+0.272
 week+0.268
 please+0.265
Neg logit contributions
cks-0.344
 necks-0.339
opes-0.339
uted-0.339
 valleys-0.337
Token happened
Token ID3022
Feature activation-1.55e+01

Pos logit contributions
 necks+0.223
 valleys+0.217
 neck+0.214
bes+0.214
 spots+0.212
Neg logit contributions
t-0.157
 reward-0.151
ll-0.148
ipop-0.144
 inconvenience-0.141
Token to
Token ID284
Feature activation-9.46e+00

Pos logit contributions
t+0.666
 happened+0.647
 reward+0.631
 help+0.616
 awaited+0.612
Neg logit contributions
 necks-0.871
ping-0.870
cks-0.870
uted-0.865
aron-0.863
Token her
Token ID607
Feature activation+1.24e-01

Pos logit contributions
t+0.482
 happened+0.432
ha+0.417
 week+0.406
 day+0.405
Neg logit contributions
cks-0.514
opes-0.501
ping-0.501
 necks-0.496
uted-0.496
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
 necks+0.007
opes+0.007
aron+0.007
cks+0.007
ping+0.007
Neg logit contributions
t-0.006
 happened-0.006
 please-0.005
 help-0.005
 day-0.005
Token They
Token ID1119
Feature activation+8.02e+00

Pos logit contributions
cks+0.080
 necks+0.078
ping+0.078
opes+0.078
aron+0.077
Neg logit contributions
t-0.073
 happened-0.069
 day-0.067
 help-0.066
 please-0.065
Token missed
Token ID6825
Feature activation-3.79e+00

Pos logit contributions
 necks+0.428
efully+0.426
 valleys+0.426
uted+0.417
ping+0.412
Neg logit contributions
t-0.394
 happened-0.356
 week-0.343
 day-0.340
 awaited-0.332
Token her
Token ID607
Feature activation+1.24e-01

Pos logit contributions
 help+0.114
 please+0.109
 day+0.108
 happened+0.106
t+0.106
Neg logit contributions
cks-0.192
 valleys-0.188
opes-0.187
aron-0.186
bes-0.186
Token and
Token ID290
Feature activation+8.40e+00

Pos logit contributions
 valleys+0.008
cks+0.008
opes+0.008
aters+0.007
 necks+0.007
Neg logit contributions
 help-0.005
 thank-0.005
 day-0.005
,-0.005
 please-0.005
Token tell
Token ID1560
Feature activation-4.00e+00

Pos logit contributions
 necks+0.601
cks+0.601
aron+0.596
opes+0.592
uted+0.590
Neg logit contributions
t-0.274
 happened-0.247
 day-0.228
 week-0.222
 please-0.222
Token her
Token ID607
Feature activation+1.16e-01

Pos logit contributions
t+0.246
ha+0.216
 happened+0.214
 awaited+0.213
 reward+0.208
Neg logit contributions
ping-0.176
uted-0.174
cks-0.173
opes-0.170
ags-0.169
Token what
Token ID644
Feature activation+4.31e+00

Pos logit contributions
cks+0.007
uted+0.007
rily+0.007
opes+0.007
 necks+0.007
Neg logit contributions
t-0.005
 happened-0.004
ha-0.004
 awaited-0.004
 day-0.004
Token happened
Token ID3022
Feature activation-1.55e+01

Pos logit contributions
 valleys+0.241
cks+0.240
 spots+0.239
bes+0.239
 necks+0.236
Neg logit contributions
 reward-0.136
 please-0.122
ipop-0.115
ha-0.110
t-0.110
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
t+0.739
 happened+0.707
 help+0.680
 day+0.676
 please+0.663
Neg logit contributions
cks-0.859
 necks-0.858
aron-0.857
opes-0.855
ping-0.847
Token
Token ID198
Feature activation-8.09e-01

Pos logit contributions
cks+0.078
 necks+0.077
opes+0.077
ping+0.077
aron+0.077
Neg logit contributions
t-0.073
 happened-0.070
 help-0.067
 day-0.067
 please-0.066
Token
Token ID198
Feature activation-8.00e-01

Pos logit contributions
t+0.036
 happened+0.035
 help+0.033
 day+0.033
 please+0.033
Neg logit contributions
cks-0.047
 necks-0.047
aron-0.047
opes-0.047
ping-0.046
Token"
Token ID1
Feature activation-2.47e+00

Pos logit contributions
t+0.044
 happened+0.042
 help+0.041
 day+0.041
 please+0.041
Neg logit contributions
opes-0.039
ping-0.039
cks-0.039
 necks-0.039
aron-0.039
TokenMom
Token ID29252
Feature activation-3.02e+00

Pos logit contributions
t+0.126
 happened+0.123
 day+0.115
 help+0.115
 please+0.112
Neg logit contributions
cks-0.133
opes-0.132
rily-0.130
 necks-0.130
ping-0.130
Token and
Token ID290
Feature activation+8.41e+00

Pos logit contributions
cks+0.132
 valleys+0.128
 necks+0.128
opes+0.126
bes+0.125
Neg logit contributions
t-0.126
 help-0.121
 day-0.120
 please-0.119
 happened-0.117
Token came
Token ID1625
Feature activation-8.34e+00

Pos logit contributions
cks+0.591
ping+0.585
 valleys+0.581
aron+0.576
 necks+0.571
Neg logit contributions
t-0.288
 week-0.252
 day-0.252
 reward-0.245
 happened-0.230
Token to
Token ID284
Feature activation-9.46e+00

Pos logit contributions
t+0.236
 help+0.232
 happened+0.217
 day+0.213
 please+0.206
Neg logit contributions
opes-0.624
aron-0.624
 necks-0.619
cks-0.619
rily-0.617
Token see
Token ID766
Feature activation-2.98e+00

Pos logit contributions
t+0.380
 happened+0.333
 day+0.319
 week+0.307
 problem+0.302
Neg logit contributions
 valleys-0.611
cks-0.609
 necks-0.606
aron-0.599
ping-0.597
Token what
Token ID644
Feature activation+4.31e+00

Pos logit contributions
t+0.122
 happened+0.117
 help+0.114
 day+0.110
 please+0.109
Neg logit contributions
 necks-0.186
aron-0.186
cks-0.185
opes-0.185
ping-0.184
Token happened
Token ID3022
Feature activation-1.55e+01

Pos logit contributions
cks+0.159
 valleys+0.156
bes+0.144
 spots+0.142
 circles+0.138
Neg logit contributions
 reward-0.246
 inconvenience-0.227
 wait-0.223
 exam-0.219
 please-0.218
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
t+0.724
 happened+0.691
 help+0.666
 day+0.661
 please+0.647
Neg logit contributions
cks-0.882
opes-0.879
 necks-0.877
aron-0.873
uted-0.869
Token She
Token ID1375
Feature activation+3.43e+00

Pos logit contributions
cks+0.067
aron+0.066
ping+0.066
uted+0.066
rily+0.065
Neg logit contributions
t-0.084
 happened-0.082
 help-0.080
 please-0.079
 day-0.079
Token saw
Token ID2497
Feature activation-5.11e+00

Pos logit contributions
aron+0.222
 necks+0.221
cks+0.218
uted+0.216
 valleys+0.215
Neg logit contributions
t-0.132
 day-0.119
 week-0.117
 happened-0.115
 reward-0.110
Token Fl
Token ID1610
Feature activation-4.06e-02

Pos logit contributions
t+0.175
 happened+0.171
 help+0.164
 day+0.157
 please+0.154
Neg logit contributions
aron-0.353
 necks-0.351
opes-0.347
cks-0.346
ping-0.345
Tokenuffy
Token ID15352
Feature activation-4.68e+00

Pos logit contributions
t+0.001
 happened+0.001
 help+0.001
 please+0.001
 day+0.001
Neg logit contributions
aron-0.003
 valleys-0.003
cks-0.003
 necks-0.003
ping-0.003
Token
Token ID198
Feature activation-8.09e-01

Pos logit contributions
t+0.038
 happened+0.037
 help+0.035
 day+0.035
 please+0.034
Neg logit contributions
cks-0.045
aron-0.045
 necks-0.045
uted-0.045
opes-0.045
TokenBut
Token ID1537
Feature activation+5.44e+00

Pos logit contributions
t+0.051
 help+0.047
 happened+0.046
 please+0.046
 day+0.046
Neg logit contributions
cks-0.035
ping-0.035
 necks-0.035
opes-0.035
rily-0.034
Token then
Token ID788
Feature activation+2.32e+00

Pos logit contributions
 necks+0.248
 valleys+0.246
ping+0.239
uted+0.234
rily+0.234
Neg logit contributions
t-0.318
 happened-0.291
 awaited-0.278
 help-0.275
 week-0.270
Token something
Token ID1223
Feature activation+8.16e+00

Pos logit contributions
 valleys+0.154
 necks+0.147
opes+0.143
 neck+0.140
 rivers+0.140
Neg logit contributions
t-0.094
 week-0.074
 happened-0.071
ll-0.070
 day-0.070
Token magical
Token ID10883
Feature activation-1.41e+00

Pos logit contributions
ping+0.407
 valleys+0.392
cks+0.391
uted+0.390
aron+0.376
Neg logit contributions
t-0.396
 please-0.362
 week-0.357
 we-0.344
 reward-0.339
Token happened
Token ID3022
Feature activation-1.55e+01

Pos logit contributions
t+0.023
 please+0.020
 week+0.019
 help+0.019
 thank+0.016
Neg logit contributions
ping-0.119
uted-0.117
aron-0.115
opes-0.115
edly-0.114
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
t+0.677
 happened+0.661
 help+0.624
 day+0.615
 please+0.608
Neg logit contributions
aron-0.930
cks-0.928
 necks-0.928
opes-0.924
aters-0.917
Token A
Token ID317
Feature activation+4.61e+00

Pos logit contributions
cks+0.086
 necks+0.083
ping+0.080
opes+0.079
uted+0.078
Neg logit contributions
t-0.072
 happened-0.069
 please-0.068
 help-0.066
 week-0.066
Token rainbow
Token ID27223
Feature activation+2.55e+00

Pos logit contributions
 valleys+0.210
aron+0.196
 unison+0.194
 strings+0.193
 neck+0.192
Neg logit contributions
t-0.260
 happened-0.231
 awaited-0.223
ll-0.219
 help-0.214
Token appeared
Token ID4120
Feature activation-4.97e+00

Pos logit contributions
ping+0.157
cks+0.155
uted+0.154
 valleys+0.154
opes+0.153
Neg logit contributions
t-0.103
 help-0.096
 please-0.095
 week-0.092
 day-0.090
Token and
Token ID290
Feature activation+8.41e+00

Pos logit contributions
t+0.214
 happened+0.210
 help+0.197
 day+0.194
 please+0.194
Neg logit contributions
 necks-0.323
cks-0.319
bes-0.312
opes-0.307
aron-0.305
Tokenmy
Token ID1820
Feature activation-2.00e+00

Pos logit contributions
t+0.420
 happened+0.402
 help+0.382
 day+0.378
 please+0.373
Neg logit contributions
cks-0.555
aron-0.554
 necks-0.554
ping-0.554
opes-0.550
Token and
Token ID290
Feature activation+8.40e+00

Pos logit contributions
t+0.109
 happened+0.103
 day+0.101
 reward+0.101
 week+0.100
Neg logit contributions
aron-0.096
ping-0.096
uted-0.094
 necks-0.094
opes-0.093
Token daddy
Token ID35822
Feature activation-4.68e+00

Pos logit contributions
opes+0.533
 necks+0.532
ping+0.528
uted+0.519
 piles+0.509
Neg logit contributions
t-0.363
ha-0.298
 reward-0.296
 contest-0.270
 happened-0.268
Token saw
Token ID2497
Feature activation-5.13e+00

Pos logit contributions
t+0.166
 reward+0.157
 day+0.149
 week+0.148
 happened+0.146
Neg logit contributions
ping-0.303
uted-0.303
aron-0.298
 necks-0.290
opes-0.286
Token what
Token ID644
Feature activation+4.31e+00

Pos logit contributions
t+0.230
 happened+0.212
 day+0.205
 help+0.203
 reward+0.200
Neg logit contributions
cks-0.305
ping-0.301
opes-0.301
uted-0.301
 necks-0.298
Token happened
Token ID3022
Feature activation-1.55e+01

Pos logit contributions
bes+0.231
uted+0.227
 strings+0.224
 spots+0.223
cks+0.219
Neg logit contributions
 reward-0.159
 please-0.144
 thank-0.135
ye-0.134
 inconvenience-0.133
Token and
Token ID290
Feature activation+8.42e+00

Pos logit contributions
t+0.874
 happened+0.822
 day+0.815
 help+0.805
 week+0.782
Neg logit contributions
cks-0.780
 valleys-0.777
aters-0.762
opes-0.756
 necks-0.755
Token they
Token ID484
Feature activation-4.01e+00

Pos logit contributions
ping+0.532
uted+0.517
aron+0.502
 valleys+0.501
cks+0.496
Neg logit contributions
t-0.342
 reward-0.302
 week-0.280
 day-0.277
 please-0.274
Token discuss
Token ID2112
Feature activation-2.04e+00

Pos logit contributions
t+0.168
 happened+0.154
 day+0.149
 week+0.146
 help+0.145
Neg logit contributions
uted-0.246
ping-0.245
cks-0.245
 necks-0.244
opes-0.243
Token how
Token ID703
Feature activation+1.18e+01

Pos logit contributions
t+0.084
 happened+0.083
 help+0.080
 day+0.079
 please+0.077
Neg logit contributions
aron-0.125
cks-0.125
 necks-0.124
opes-0.124
ping-0.124
Token to
Token ID284
Feature activation-9.46e+00

Pos logit contributions
ping+0.705
uted+0.671
cks+0.667
 valleys+0.661
 necks+0.645
Neg logit contributions
 reward-0.469
 awaited-0.414
 please-0.406
ha-0.406
 happened-0.400
Token but
Token ID475
Feature activation+6.02e+00

Pos logit contributions
t+0.357
 help+0.354
 please+0.348
 happened+0.344
 day+0.343
Neg logit contributions
cks-0.389
aters-0.374
rily-0.374
opes-0.373
uted-0.371
Token didn
Token ID1422
Feature activation-2.04e+00

Pos logit contributions
 necks+0.341
uted+0.340
 valleys+0.337
rily+0.332
opes+0.328
Neg logit contributions
t-0.260
ha-0.232
 happened-0.232
 help-0.218
 awaited-0.217
Token't
Token ID470
Feature activation-7.16e+00

Pos logit contributions
t+0.044
 happened+0.039
 help+0.036
 day+0.035
 please+0.034
Neg logit contributions
 necks-0.168
cks-0.167
aron-0.167
opes-0.166
ping-0.166
Token know
Token ID760
Feature activation-6.25e+00

Pos logit contributions
t+0.282
 happened+0.276
ha+0.267
 awaited+0.258
 day+0.241
Neg logit contributions
aron-0.433
ping-0.427
cks-0.410
uted-0.408
rily-0.408
Token what
Token ID644
Feature activation+4.31e+00

Pos logit contributions
t+0.305
 happened+0.284
 help+0.274
 day+0.274
 please+0.270
Neg logit contributions
cks-0.342
opes-0.339
 necks-0.338
uted-0.337
aron-0.336
Token happened
Token ID3022
Feature activation-1.55e+01

Pos logit contributions
 valleys+0.272
cks+0.267
opes+0.266
 necks+0.266
aron+0.258
Neg logit contributions
t-0.158
 reward-0.135
 please-0.126
ha-0.125
 thank-0.122
Token to
Token ID284
Feature activation-9.46e+00

Pos logit contributions
t+0.677
 happened+0.644
 help+0.617
 reward+0.607
 day+0.606
Neg logit contributions
cks-0.897
 necks-0.886
ping-0.886
aron-0.883
uted-0.883
Token the
Token ID262
Feature activation+4.43e-01

Pos logit contributions
t+0.425
 happened+0.394
 day+0.369
 help+0.362
 week+0.361
Neg logit contributions
cks-0.565
opes-0.552
ping-0.550
uted-0.550
 necks-0.549
Token box
Token ID3091
Feature activation-2.46e+00

Pos logit contributions
 necks+0.023
cks+0.023
aron+0.023
opes+0.023
ping+0.023
Neg logit contributions
t-0.022
 happened-0.021
 help-0.020
 day-0.020
 please-0.020
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
t+0.116
 happened+0.112
 help+0.106
ha+0.105
 day+0.104
Neg logit contributions
ping-0.129
cks-0.129
rily-0.129
uted-0.127
aron-0.127
Token James
Token ID3700
Feature activation-4.37e+00

Pos logit contributions
cks+0.074
ping+0.072
 necks+0.072
aron+0.071
opes+0.071
Neg logit contributions
t-0.080
 happened-0.075
 day-0.073
 help-0.072
 please-0.072
Token depend
Token ID4745
Feature activation+1.51e+00

Pos logit contributions
aron+0.291
uted+0.283
rily+0.280
ping+0.279
 valleys+0.279
Neg logit contributions
t-0.232
 happened-0.214
 help-0.205
 please-0.200
 awaited-0.199
Tokenable
Token ID540
Feature activation-5.37e+00

Pos logit contributions
aron+0.060
cks+0.057
inning+0.057
ping+0.054
rily+0.053
Neg logit contributions
 help-0.089
 thank-0.088
 please-0.087
t-0.086
 reward-0.086
Token day
Token ID1110
Feature activation-1.48e+01

Pos logit contributions
t+0.227
 happened+0.207
 help+0.192
 awaited+0.190
 please+0.188
Neg logit contributions
aron-0.325
rily-0.315
ping-0.311
aters-0.310
 necks-0.309
Token of
Token ID286
Feature activation-7.23e+00

Pos logit contributions
t+0.681
 happened+0.671
 help+0.634
 reward+0.622
 awaited+0.613
Neg logit contributions
aron-0.818
ping-0.802
 necks-0.798
cks-0.794
uted-0.791
Token the
Token ID262
Feature activation+4.39e-01

Pos logit contributions
t+0.302
 happened+0.281
 help+0.265
 day+0.262
 please+0.259
Neg logit contributions
cks-0.449
opes-0.445
 necks-0.445
ping-0.443
aron-0.442
Token week
Token ID1285
Feature activation-1.55e+01

Pos logit contributions
 valleys+0.026
opes+0.026
ping+0.026
 necks+0.025
aron+0.025
Neg logit contributions
t-0.019
 happened-0.017
 please-0.016
 help-0.016
 awaited-0.015
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
t+0.772
 happened+0.740
 help+0.712
 please+0.695
 day+0.689
Neg logit contributions
aron-0.812
 necks-0.805
cks-0.801
ping-0.799
opes-0.797
Token It
Token ID632
Feature activation+4.55e+00

Pos logit contributions
cks+0.089
 necks+0.088
ping+0.088
opes+0.087
uted+0.086
Neg logit contributions
t-0.063
 please-0.059
 help-0.058
 happened-0.057
 day-0.057
Token's
Token ID338
Feature activation-4.86e-01

Pos logit contributions
aron+0.263
cks+0.262
opes+0.261
 valleys+0.261
ping+0.260
Neg logit contributions
t-0.196
 happened-0.184
 help-0.178
 please-0.176
 day-0.174
Token a
Token ID257
Feature activation+5.02e+00

Pos logit contributions
t+0.018
 happened+0.018
 day+0.018
 help+0.017
 please+0.017
Neg logit contributions
 necks-0.032
cks-0.032
opes-0.032
uted-0.032
ping-0.031
Token day
Token ID1110
Feature activation-1.48e+01

Pos logit contributions
aron+0.261
 valleys+0.260
 unison+0.259
 necks+0.256
opes+0.246
Neg logit contributions
t-0.238
 happened-0.225
 awaited-0.206
 help-0.196
ha-0.192
Token the
Token ID262
Feature activation+4.44e-01

Pos logit contributions
t+0.380
 happened+0.349
 help+0.324
 day+0.322
 please+0.321
Neg logit contributions
cks-0.604
 necks-0.600
opes-0.597
ping-0.597
 valleys-0.596
Token spring
Token ID6076
Feature activation+3.58e+00

Pos logit contributions
 necks+0.028
 valleys+0.027
uted+0.027
opes+0.027
ping+0.027
Neg logit contributions
t-0.018
 happened-0.017
 please-0.016
 help-0.015
 awaited-0.015
Token class
Token ID1398
Feature activation-2.68e+00

Pos logit contributions
aron+0.226
 valleys+0.225
 necks+0.225
ping+0.224
aters+0.223
Neg logit contributions
t-0.133
 happened-0.132
 help-0.121
 please-0.116
 thank-0.114
Token the
Token ID262
Feature activation+4.50e-01

Pos logit contributions
t+0.132
 happened+0.130
 help+0.123
 please+0.120
 day+0.118
Neg logit contributions
aron-0.140
 necks-0.139
 valleys-0.136
ping-0.135
uted-0.135
Token next
Token ID1306
Feature activation-5.03e+00

Pos logit contributions
 necks+0.027
 valleys+0.027
ping+0.026
opes+0.026
cks+0.026
Neg logit contributions
t-0.019
 happened-0.019
 please-0.017
 help-0.017
 awaited-0.017
Token week
Token ID1285
Feature activation-1.55e+01

Pos logit contributions
t+0.131
 happened+0.129
 please+0.103
 awaited+0.100
 thank+0.096
Neg logit contributions
 valleys-0.371
 necks-0.368
aron-0.363
efully-0.362
 unison-0.362
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
t+0.786
 happened+0.754
 help+0.726
 please+0.711
 day+0.703
Neg logit contributions
aron-0.794
 necks-0.792
 valleys-0.783
ping-0.782
opes-0.776
Token<|endoftext|>
Token ID50256
Feature activation+1.48e+00

Pos logit contributions
cks+0.081
aron+0.081
 necks+0.081
opes+0.080
uted+0.080
Neg logit contributions
t-0.068
 happened-0.065
 help-0.063
 day-0.062
 please-0.061
TokenOnce
Token ID7454
Feature activation-3.20e+00

Pos logit contributions
 necks+0.089
cks+0.089
opes+0.089
ping+0.088
aron+0.087
Neg logit contributions
t-0.065
 happened-0.062
 day-0.060
 help-0.058
 week-0.058
Token upon
Token ID2402
Feature activation+6.29e+00

Pos logit contributions
 reward+0.217
 help+0.203
 inconvenience+0.200
 wait+0.196
 ha+0.194
Neg logit contributions
rily-0.095
cks-0.089
 valleys-0.085
uted-0.082
 piles-0.077
Token a
Token ID257
Feature activation+5.02e+00

Pos logit contributions
opes+0.434
aters+0.432
 necks+0.431
cks+0.427
rily+0.420
Neg logit contributions
 happened-0.253
t-0.249
 day-0.244
 help-0.243
 please-0.225
Token his
Token ID465
Feature activation+2.76e+00

Pos logit contributions
t+0.035
 happened+0.034
 day+0.033
 help+0.033
 please+0.032
Neg logit contributions
cks-0.046
 necks-0.046
aron-0.046
opes-0.046
uted-0.046
Token favourite
Token ID12507
Feature activation+2.34e+00

Pos logit contributions
 necks+0.170
opes+0.169
cks+0.169
aron+0.169
ping+0.168
Neg logit contributions
t-0.113
 happened-0.108
 help-0.102
 day-0.100
 please-0.099
Token day
Token ID1110
Feature activation-1.48e+01

Pos logit contributions
cks+0.148
 necks+0.145
aron+0.145
uted+0.144
 valleys+0.144
Neg logit contributions
t-0.096
 happened-0.092
 day-0.091
 help-0.089
 week-0.087
Token of
Token ID286
Feature activation-7.24e+00

Pos logit contributions
t+0.679
 happened+0.652
 help+0.624
 please+0.611
 day+0.608
Neg logit contributions
cks-0.828
opes-0.827
 necks-0.827
ping-0.826
aron-0.823
Token the
Token ID262
Feature activation+4.44e-01

Pos logit contributions
 happened+0.292
 day+0.292
t+0.287
 help+0.286
 week+0.278
Neg logit contributions
aron-0.449
cks-0.449
 necks-0.444
uted-0.442
rily-0.442
Token week
Token ID1285
Feature activation-1.55e+01

Pos logit contributions
 necks+0.024
opes+0.024
aron+0.024
ping+0.024
cks+0.023
Neg logit contributions
t-0.022
 happened-0.021
 help-0.020
 please-0.020
 day-0.019
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
t+0.722
 happened+0.695
 day+0.677
 help+0.668
 week+0.655
Neg logit contributions
cks-0.878
 necks-0.867
opes-0.863
aron-0.863
uted-0.860
Token One
Token ID1881
Feature activation+1.59e+00

Pos logit contributions
cks+0.081
ping+0.080
uted+0.080
 necks+0.080
rily+0.079
Neg logit contributions
t-0.070
 happened-0.067
 day-0.066
 help-0.065
 please-0.064
Token Sunday
Token ID3502
Feature activation-4.76e+00

Pos logit contributions
ping+0.127
aron+0.127
inning+0.125
aters+0.123
ady+0.123
Neg logit contributions
t-0.029
 happened-0.026
 help-0.022
 reward-0.022
 please-0.021
Token,
Token ID11
Feature activation-7.17e+00

Pos logit contributions
t+0.171
 help+0.165
 please+0.165
 thank+0.151
 reward+0.146
Neg logit contributions
aron-0.292
 valleys-0.291
aters-0.284
 fields-0.275
ping-0.273
Token Jake
Token ID14757
Feature activation-5.15e+00

Pos logit contributions
t+0.297
 happened+0.282
 help+0.263
 reward+0.259
ha+0.258
Neg logit contributions
opes-0.432
 necks-0.431
cks-0.430
 valleys-0.429
uted-0.425
Token could
Token ID714
Feature activation-7.97e+00

Pos logit contributions
 necks+0.231
opes+0.227
cks+0.226
ping+0.226
aron+0.224
Neg logit contributions
t-0.131
 happened-0.118
 help-0.116
 please-0.114
 day-0.114
Token not
Token ID407
Feature activation+8.97e-01

Pos logit contributions
t+0.284
 happened+0.275
 day+0.257
 week+0.253
 awaited+0.250
Neg logit contributions
cks-0.530
 necks-0.526
ping-0.523
opes-0.522
aron-0.521
Token hop
Token ID1725
Feature activation+4.13e+00

Pos logit contributions
cks+0.055
 necks+0.055
aron+0.055
ping+0.055
opes+0.054
Neg logit contributions
t-0.036
 happened-0.036
 day-0.033
 week-0.032
 help-0.032
Token for
Token ID329
Feature activation-4.64e+00

Pos logit contributions
cks+0.226
 necks+0.225
aron+0.224
opes+0.224
uted+0.222
Neg logit contributions
t-0.202
 happened-0.192
 help-0.186
 day-0.185
 please-0.182
Token a
Token ID257
Feature activation+5.03e+00

Pos logit contributions
t+0.240
 happened+0.228
 day+0.214
 please+0.213
 awaited+0.213
Neg logit contributions
 necks-0.240
cks-0.238
ping-0.237
opes-0.236
 valleys-0.234
Token week
Token ID1285
Feature activation-1.55e+01

Pos logit contributions
 neck+0.239
 valleys+0.224
 moss+0.223
 necks+0.222
 tail+0.222
Neg logit contributions
 happened-0.242
 awaited-0.237
 done-0.214
 happens-0.214
t-0.210
Token.
Token ID13
Feature activation+1.44e+00

Pos logit contributions
t+0.729
 happened+0.698
 help+0.673
 day+0.668
 please+0.656
Neg logit contributions
cks-0.863
 necks-0.858
aron-0.856
opes-0.854
uted-0.849
Token Ho
Token ID9544
Feature activation-6.20e-01

Pos logit contributions
cks+0.083
uted+0.080
aron+0.078
 necks+0.077
 valleys+0.077
Neg logit contributions
t-0.071
 help-0.068
 please-0.067
 day-0.065
 happened-0.065
Tokenppy
Token ID14097
Feature activation-2.27e+00

Pos logit contributions
t+0.029
 happened+0.027
 help+0.026
 please+0.025
 day+0.025
Neg logit contributions
cks-0.035
 valleys-0.035
uted-0.035
 necks-0.035
aron-0.035
Token was
Token ID373
Feature activation-7.85e-01

Pos logit contributions
t+0.089
 happened+0.082
 help+0.080
 please+0.078
 day+0.078
Neg logit contributions
 necks-0.146
opes-0.143
ping-0.143
aron-0.142
 valleys-0.142
Token sad
Token ID6507
Feature activation+7.39e-01

Pos logit contributions
t+0.036
 happened+0.034
 help+0.033
 day+0.033
 please+0.032
Neg logit contributions
cks-0.045
 necks-0.045
aron-0.045
opes-0.045
uted-0.044
Token felt
Token ID2936
Feature activation+5.64e+00

Pos logit contributions
cks+0.246
aters+0.244
aron+0.243
opes+0.242
ping+0.241
Neg logit contributions
t-0.115
 happened-0.111
 help-0.103
 day-0.101
 please-0.100
Token sad
Token ID6507
Feature activation+7.53e-01

Pos logit contributions
aters+0.373
opes+0.369
 necks+0.365
aron+0.362
cks+0.353
Neg logit contributions
 help-0.237
 happened-0.227
t-0.223
 please-0.219
 thank-0.218
Token and
Token ID290
Feature activation+8.40e+00

Pos logit contributions
cks+0.039
 necks+0.039
opes+0.038
aron+0.038
uted+0.038
Neg logit contributions
t-0.039
 happened-0.038
 help-0.037
 day-0.036
 please-0.036
Token wondered
Token ID14028
Feature activation+6.59e+00

Pos logit contributions
ping+0.474
cks+0.469
 necks+0.466
 valleys+0.465
uted+0.458
Neg logit contributions
t-0.404
 happened-0.359
 reward-0.349
 help-0.348
ha-0.344
Token what
Token ID644
Feature activation+4.30e+00

Pos logit contributions
cks+0.370
aron+0.370
ping+0.369
uted+0.369
opes+0.368
Neg logit contributions
t-0.310
 happened-0.285
 day-0.271
 week-0.269
 reward-0.263
Token happened
Token ID3022
Feature activation-1.55e+01

Pos logit contributions
 valleys+0.191
 rivers+0.172
 necks+0.170
cks+0.168
 fields+0.168
Neg logit contributions
t-0.225
ipop-0.209
ll-0.208
olly-0.203
 reward-0.202
Token to
Token ID284
Feature activation-9.46e+00

Pos logit contributions
t+0.649
 happened+0.621
 help+0.592
 day+0.586
 please+0.576
Neg logit contributions
cks-0.935
 necks-0.931
aron-0.929
ping-0.924
opes-0.924
Token the
Token ID262
Feature activation+4.48e-01

Pos logit contributions
t+0.438
 happened+0.393
 week+0.371
 day+0.370
ha+0.370
Neg logit contributions
cks-0.563
ping-0.553
opes-0.543
 necks-0.542
uted-0.541
Token bird
Token ID6512
Feature activation-6.22e+00

Pos logit contributions
cks+0.029
 necks+0.029
aron+0.029
opes+0.029
ping+0.029
Neg logit contributions
t-0.017
 happened-0.016
 help-0.015
 day-0.015
 please-0.015
Token.
Token ID13
Feature activation+1.44e+00

Pos logit contributions
t+0.319
 happened+0.303
 help+0.287
 reward+0.282
 day+0.282
Neg logit contributions
cks-0.323
ping-0.323
 necks-0.317
aron-0.315
uted-0.314
Token The
Token ID383
Feature activation+3.55e+00

Pos logit contributions
cks+0.079
opes+0.078
 necks+0.077
ping+0.077
uted+0.077
Neg logit contributions
t-0.072
 happened-0.067
 help-0.066
 day-0.065
 please-0.065
Token disc
Token ID1221
Feature activation+9.10e+00

Pos logit contributions
cks+0.024
aron+0.023
opes+0.023
uted+0.023
 necks+0.023
Neg logit contributions
t-0.022
 happened-0.021
 help-0.021
 day-0.021
 week-0.020
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
aron+0.506
 necks+0.503
opes+0.502
cks+0.498
ping+0.497
Neg logit contributions
t-0.433
 happened-0.415
 help-0.400
 day-0.395
 please-0.388
Token He
Token ID679
Feature activation+3.48e+00

Pos logit contributions
opes+0.082
ping+0.080
cks+0.077
uted+0.077
 necks+0.076
Neg logit contributions
t-0.074
 happened-0.072
 please-0.069
 day-0.068
 help-0.068
Token understands
Token ID14759
Feature activation-1.33e+00

Pos logit contributions
rily+0.263
aters+0.260
ping+0.259
aron+0.258
edly+0.253
Neg logit contributions
 happened-0.109
 help-0.105
 thank-0.105
 problem-0.101
 would-0.099
Token what
Token ID644
Feature activation+4.30e+00

Pos logit contributions
t+0.060
 happened+0.055
 day+0.053
 help+0.053
 week+0.052
Neg logit contributions
cks-0.079
aron-0.079
 necks-0.078
uted-0.077
ping-0.077
Token happened
Token ID3022
Feature activation-1.55e+01

Pos logit contributions
cks+0.187
 valleys+0.178
 spots+0.177
 corners+0.173
 yourselves+0.171
Neg logit contributions
t-0.179
ha-0.177
 reward-0.167
 please-0.163
ll-0.161
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
t+0.719
 happened+0.682
 help+0.657
 day+0.655
 please+0.637
Neg logit contributions
opes-0.889
 necks-0.887
cks-0.884
aron-0.880
 valleys-0.879
Token He
Token ID679
Feature activation+3.49e+00

Pos logit contributions
opes+0.080
ping+0.079
cks+0.078
 necks+0.078
uted+0.077
Neg logit contributions
t-0.073
 happened-0.070
 please-0.067
 day-0.067
 help-0.066
Token is
Token ID318
Feature activation+3.81e-01

Pos logit contributions
ping+0.251
aters+0.249
rily+0.249
aron+0.243
 valleys+0.241
Neg logit contributions
 happened-0.118
 thank-0.114
 help-0.112
 would-0.108
 problem-0.107
Token not
Token ID407
Feature activation+8.97e-01

Pos logit contributions
opes+0.024
 necks+0.024
aters+0.023
 valleys+0.023
aron+0.023
Neg logit contributions
t-0.016
 happened-0.015
 help-0.015
 day-0.014
 please-0.014
Token happy
Token ID3772
Feature activation-9.54e-01

Pos logit contributions
cks+0.050
 necks+0.049
aron+0.049
opes+0.049
ping+0.049
Neg logit contributions
t-0.043
 happened-0.041
 help-0.040
 day-0.039
 please-0.039
Token put
Token ID1234
Feature activation+1.82e+00

Pos logit contributions
t+0.222
 happened+0.208
 help+0.199
 day+0.199
 week+0.194
Neg logit contributions
aron-0.362
 necks-0.361
cks-0.359
uted-0.358
opes-0.358
Token it
Token ID340
Feature activation-1.94e+00

Pos logit contributions
cks+0.129
 necks+0.128
aron+0.127
ping+0.127
 valleys+0.127
Neg logit contributions
t-0.059
 happened-0.054
 help-0.050
 please-0.049
 day-0.049
Token right
Token ID826
Feature activation-2.92e+00

Pos logit contributions
t+0.097
 happened+0.094
 help+0.090
 day+0.089
 please+0.088
Neg logit contributions
cks-0.101
 necks-0.101
ping-0.100
aron-0.100
opes-0.100
Token on
Token ID319
Feature activation-2.79e+00

Pos logit contributions
t+0.142
 happened+0.136
 help+0.131
 day+0.131
 please+0.128
Neg logit contributions
cks-0.159
 necks-0.158
aron-0.158
opes-0.157
ping-0.157
Token her
Token ID607
Feature activation+4.39e-01

Pos logit contributions
t+0.121
 day+0.116
 happened+0.116
 help+0.114
 week+0.112
Neg logit contributions
cks-0.173
 necks-0.168
opes-0.168
uted-0.166
ping-0.166
Token wrist
Token ID15980
Feature activation+1.54e+01

Pos logit contributions
 necks+0.019
cks+0.019
aron+0.018
opes+0.018
ping+0.018
Neg logit contributions
t-0.027
 happened-0.026
 help-0.025
 day-0.025
 please-0.025
Token!
Token ID0
Feature activation+4.37e+00

Pos logit contributions
cks+0.890
opes+0.869
 necks+0.868
uted+0.862
 valleys+0.861
Neg logit contributions
t-0.730
 happened-0.683
 day-0.669
 help-0.665
 please-0.651
Token Her
Token ID2332
Feature activation+1.35e+00

Pos logit contributions
cks+0.186
 necks+0.186
aron+0.185
opes+0.185
ping+0.183
Neg logit contributions
t-0.263
 happened-0.254
 help-0.246
 day-0.245
 please-0.242
Token Daddy
Token ID26926
Feature activation-3.45e+00

Pos logit contributions
 necks+0.073
opes+0.072
aters+0.072
rily+0.071
ping+0.070
Neg logit contributions
t-0.066
 happened-0.061
 please-0.058
 awaited-0.058
ha-0.058
Token saw
Token ID2497
Feature activation-4.77e+00

Pos logit contributions
t+0.132
 happened+0.120
 week+0.117
 help+0.116
 day+0.116
Neg logit contributions
aron-0.222
uted-0.219
 necks-0.216
ping-0.214
opes-0.212
Token it
Token ID340
Feature activation-1.89e+00

Pos logit contributions
t+0.213
 happened+0.198
 help+0.191
 day+0.190
 please+0.188
Neg logit contributions
cks-0.281
ping-0.280
opes-0.280
uted-0.279
 necks-0.278
Token slapped
Token ID31213
Feature activation-3.12e-01

Pos logit contributions
uted+0.476
cks+0.469
ping+0.467
 necks+0.465
efully+0.458
Neg logit contributions
t-0.341
 week-0.305
 awaited-0.303
 day-0.292
 reward-0.289
Token him
Token ID683
Feature activation-4.74e+00

Pos logit contributions
t+0.012
 happened+0.012
 help+0.011
 day+0.011
 please+0.011
Neg logit contributions
aron-0.020
cks-0.020
opes-0.020
 necks-0.020
aters-0.020
Token again
Token ID757
Feature activation-1.44e+00

Pos logit contributions
 help+0.193
t+0.192
 day+0.188
 happened+0.181
 please+0.177
Neg logit contributions
 valleys-0.295
aron-0.294
opes-0.290
 necks-0.289
aters-0.289
Token on
Token ID319
Feature activation-3.09e+00

Pos logit contributions
t+0.068
 happened+0.065
 help+0.063
 day+0.063
 please+0.061
Neg logit contributions
cks-0.081
 necks-0.080
opes-0.080
aron-0.080
uted-0.079
Token the
Token ID262
Feature activation+4.68e-01

Pos logit contributions
t+0.115
 happened+0.112
 help+0.111
 day+0.110
 week+0.105
Neg logit contributions
cks-0.202
 necks-0.201
aron-0.201
uted-0.200
opes-0.199
Token neck
Token ID7393
Feature activation+1.67e+01

Pos logit contributions
cks+0.019
aron+0.019
uted+0.019
opes+0.018
aters+0.018
Neg logit contributions
t-0.029
 help-0.029
 day-0.028
 happened-0.028
 week-0.027
Token.
Token ID13
Feature activation+1.46e+00

Pos logit contributions
cks+0.910
 necks+0.906
aron+0.905
opes+0.900
ping+0.899
Neg logit contributions
t-0.805
 happened-0.775
 help-0.747
 day-0.739
 please-0.729
Token
Token ID220
Feature activation+3.09e+00

Pos logit contributions
cks+0.067
 necks+0.066
aron+0.066
ping+0.066
opes+0.066
Neg logit contributions
t-0.085
 happened-0.081
 help-0.079
 day-0.078
 please-0.078
Token
Token ID198
Feature activation-7.86e-01

Pos logit contributions
 necks+0.194
ping+0.192
cks+0.191
opes+0.190
aron+0.190
Neg logit contributions
t-0.131
 happened-0.122
 help-0.115
 day-0.115
 please-0.113
TokenThis
Token ID1212
Feature activation+4.94e+00

Pos logit contributions
t+0.037
 happened+0.037
 help+0.035
 day+0.034
 please+0.034
Neg logit contributions
aron-0.043
cks-0.043
 necks-0.043
uted-0.043
opes-0.042
Token time
Token ID640
Feature activation-8.89e+00

Pos logit contributions
 necks+0.313
 strings+0.300
opes+0.300
 valleys+0.299
aron+0.298
Neg logit contributions
t-0.179
 please-0.172
 help-0.158
 awaited-0.153
 thank-0.147
Token louder
Token ID27089
Feature activation+2.27e+00

Pos logit contributions
cks+0.374
 valleys+0.368
 necks+0.367
ping+0.360
aron+0.358
Neg logit contributions
t-0.506
 happened-0.484
 day-0.467
 week-0.460
 awaited-0.459
Token.
Token ID13
Feature activation+1.50e+00

Pos logit contributions
uted+0.145
aters+0.145
rily+0.144
efully+0.142
opes+0.141
Neg logit contributions
t-0.088
 help-0.086
 day-0.084
 happened-0.083
 thank-0.081
Token It
Token ID632
Feature activation+4.61e+00

Pos logit contributions
ping+0.099
opes+0.097
 necks+0.096
cks+0.096
aters+0.094
Neg logit contributions
t-0.060
 please-0.057
 happened-0.055
 thank-0.054
 help-0.054
Token made
Token ID925
Feature activation-5.32e+00

Pos logit contributions
cks+0.288
 necks+0.286
aron+0.283
 valleys+0.281
ping+0.281
Neg logit contributions
t-0.186
 happened-0.173
 help-0.169
 day-0.168
 week-0.166
Token their
Token ID511
Feature activation+3.57e+00

Pos logit contributions
 happened+0.211
 help+0.208
t+0.200
 day+0.199
 thank+0.193
Neg logit contributions
aron-0.344
 necks-0.337
aters-0.332
cks-0.330
opes-0.329
Token ears
Token ID11368
Feature activation+1.54e+01

Pos logit contributions
aron+0.127
cks+0.125
uted+0.124
opes+0.123
ping+0.123
Neg logit contributions
t-0.241
 happened-0.235
 help-0.231
 day-0.230
 please-0.225
Token hurt
Token ID5938
Feature activation-2.47e+00

Pos logit contributions
opes+0.963
efully+0.952
 necks+0.950
ags+0.949
aron+0.949
Neg logit contributions
t-0.670
 help-0.631
 please-0.593
 thank-0.593
 day-0.593
Token.
Token ID13
Feature activation+1.49e+00

Pos logit contributions
 help+0.100
t+0.098
 day+0.096
 ever+0.094
 happened+0.092
Neg logit contributions
bes-0.161
cks-0.159
rily-0.156
opes-0.155
uted-0.154
Token It
Token ID632
Feature activation+4.58e+00

Pos logit contributions
ping+0.101
opes+0.099
 necks+0.098
cks+0.097
aters+0.096
Neg logit contributions
t-0.057
 please-0.054
 happened-0.053
 thank-0.050
 help-0.050
Token made
Token ID925
Feature activation-5.34e+00

Pos logit contributions
cks+0.307
 necks+0.305
aron+0.304
opes+0.303
ping+0.302
Neg logit contributions
t-0.165
 happened-0.155
 help-0.148
 day-0.146
 please-0.143
Token their
Token ID511
Feature activation+3.54e+00

Pos logit contributions
 happened+0.213
 help+0.206
t+0.200
 day+0.198
 thank+0.194
Neg logit contributions
aron-0.346
 necks-0.341
aters-0.336
opes-0.332
cks-0.331
Token She
Token ID1375
Feature activation+3.69e+00

Pos logit contributions
cks+0.094
 necks+0.092
uted+0.090
ping+0.090
aron+0.089
Neg logit contributions
t-0.086
 happened-0.082
 help-0.081
 please-0.080
 day-0.080
Token looked
Token ID3114
Feature activation+3.89e+00

Pos logit contributions
aron+0.249
 necks+0.247
uted+0.245
opes+0.245
cks+0.242
Neg logit contributions
t-0.130
 week-0.112
 happened-0.112
 day-0.110
 please-0.110
Token into
Token ID656
Feature activation+7.75e+00

Pos logit contributions
cks+0.210
 necks+0.209
aron+0.209
opes+0.208
ping+0.207
Neg logit contributions
t-0.191
 happened-0.183
 help-0.176
 day-0.175
 please-0.172
Token Emily
Token ID17608
Feature activation-6.75e+00

Pos logit contributions
cks+0.495
uted+0.480
aron+0.477
opes+0.476
ping+0.475
Neg logit contributions
 help-0.332
 happened-0.321
t-0.313
 day-0.312
 reward-0.304
Token's
Token ID338
Feature activation-2.26e-01

Pos logit contributions
t+0.285
 day+0.279
 help+0.275
 happened+0.264
 week+0.263
Neg logit contributions
cks-0.425
opes-0.404
ags-0.403
uted-0.403
 valleys-0.397
Token ears
Token ID11368
Feature activation+1.56e+01

Pos logit contributions
 help+0.011
 day+0.011
t+0.011
 happened+0.011
 reward+0.011
Neg logit contributions
cks-0.013
uted-0.012
opes-0.012
aron-0.012
ping-0.012
Token,
Token ID11
Feature activation-6.88e+00

Pos logit contributions
cks+0.792
 necks+0.755
opes+0.755
uted+0.742
 valleys+0.738
Neg logit contributions
t-0.872
 happened-0.835
 help-0.810
 day-0.804
 please-0.781
Token nose
Token ID9686
Feature activation+3.81e+00

Pos logit contributions
 help+0.330
 happened+0.323
 day+0.319
 would+0.317
 please+0.313
Neg logit contributions
cks-0.388
uted-0.368
aters-0.367
opes-0.366
rily-0.363
Token and
Token ID290
Feature activation+8.69e+00

Pos logit contributions
cks+0.275
 necks+0.271
opes+0.269
aron+0.269
uted+0.269
Neg logit contributions
t-0.120
 happened-0.113
 help-0.106
 day-0.104
 please-0.101
Token throat
Token ID13589
Feature activation+2.55e+00

Pos logit contributions
cks+0.461
 necks+0.461
aron+0.459
opes+0.458
ping+0.455
Neg logit contributions
t-0.433
 happened-0.412
 help-0.397
 day-0.395
 please-0.390
Token.
Token ID13
Feature activation+1.76e+00

Pos logit contributions
cks+0.148
 necks+0.147
aron+0.147
opes+0.147
ping+0.146
Neg logit contributions
t-0.114
 happened-0.109
 help-0.104
 day-0.103
 please-0.102
Token jewelry
Token ID22634
Feature activation+6.06e+00

Pos logit contributions
 necks+0.270
cks+0.266
aron+0.264
opes+0.262
ping+0.262
Neg logit contributions
t-0.317
 happened-0.306
 help-0.287
 please-0.287
 day-0.287
Token on
Token ID319
Feature activation-2.66e+00

Pos logit contributions
 necks+0.321
cks+0.319
aron+0.318
ping+0.315
opes+0.315
Neg logit contributions
t-0.300
 happened-0.292
 help-0.278
 day-0.275
 please-0.272
Token her
Token ID607
Feature activation+5.65e-01

Pos logit contributions
 help+0.080
 day+0.079
t+0.075
 please+0.072
 week+0.072
Neg logit contributions
cks-0.199
ping-0.196
opes-0.196
uted-0.194
aron-0.194
Token fingers
Token ID9353
Feature activation+1.04e+01

Pos logit contributions
uted+0.030
aron+0.030
cks+0.029
 valleys+0.029
ping+0.029
Neg logit contributions
 help-0.028
t-0.028
 day-0.028
 happened-0.027
 reward-0.027
Token,
Token ID11
Feature activation-6.70e+00

Pos logit contributions
cks+0.595
opes+0.589
 necks+0.588
aron+0.587
uted+0.584
Neg logit contributions
t-0.485
 happened-0.459
 help-0.442
 day-0.441
 please-0.432
Token wrists
Token ID38163
Feature activation+1.78e+01

Pos logit contributions
 help+0.293
 thank+0.288
 please+0.277
 she+0.276
 would+0.267
Neg logit contributions
uted-0.408
opes-0.400
inning-0.400
aters-0.399
efully-0.396
Token,
Token ID11
Feature activation-6.69e+00

Pos logit contributions
cks+1.482
opes+1.464
aron+1.456
uted+1.454
ping+1.443
Neg logit contributions
t-0.367
 happened-0.321
 help-0.315
 day-0.305
 please-0.299
Token and
Token ID290
Feature activation+8.87e+00

Pos logit contributions
 help+0.334
 thank+0.326
 she+0.320
 would+0.318
 please+0.313
Neg logit contributions
inning-0.358
uted-0.354
opes-0.351
aron-0.350
cks-0.348
Token ears
Token ID11368
Feature activation+1.58e+01

Pos logit contributions
aron+0.574
cks+0.570
ping+0.570
opes+0.569
uted+0.569
Neg logit contributions
t-0.333
 happened-0.328
 help-0.319
 day-0.312
 please-0.304
Token.
Token ID13
Feature activation+1.93e+00

Pos logit contributions
cks+0.956
 necks+0.950
opes+0.948
aron+0.944
uted+0.941
Neg logit contributions
t-0.678
 happened-0.642
 help-0.620
 day-0.610
 please-0.601
Token She
Token ID1375
Feature activation+3.92e+00

Pos logit contributions
cks+0.115
ping+0.110
uted+0.107
opes+0.107
inning+0.107
Neg logit contributions
 happened-0.088
t-0.087
 thank-0.087
 day-0.086
 please-0.086
Token watched
Token ID7342
Feature activation+1.00e+00

Pos logit contributions
 necks+0.537
aron+0.525
opes+0.519
ping+0.517
cks+0.517
Neg logit contributions
t-0.358
 happened-0.320
ha-0.303
 please-0.300
 awaited-0.296
Token grow
Token ID1663
Feature activation+5.29e+00

Pos logit contributions
 necks+0.064
cks+0.063
aron+0.063
aters+0.063
 valleys+0.062
Neg logit contributions
 help-0.039
 happened-0.039
t-0.038
 please-0.038
 day-0.038
Token every
Token ID790
Feature activation+4.13e-01

Pos logit contributions
 necks+0.345
bes+0.339
cks+0.329
opes+0.329
 unison+0.325
Neg logit contributions
 day-0.203
 help-0.202
 would-0.202
 happened-0.200
t-0.193
Token day
Token ID1110
Feature activation-1.47e+01

Pos logit contributions
 valleys+0.033
rily+0.032
ping+0.032
 necks+0.032
cks+0.032
Neg logit contributions
t-0.010
 happened-0.008
 awaited-0.007
 please-0.007
ha-0.007
Token.
Token ID13
Feature activation+1.53e+00

Pos logit contributions
t+0.696
 happened+0.665
 help+0.645
 day+0.642
 please+0.627
Neg logit contributions
cks-0.826
 necks-0.819
opes-0.817
aron-0.817
uted-0.813
Token They
Token ID1119
Feature activation+8.09e+00

Pos logit contributions
cks+0.088
ping+0.088
 necks+0.087
opes+0.087
aron+0.087
Neg logit contributions
t-0.070
 happened-0.067
 day-0.065
 help-0.064
 please-0.064
Token were
Token ID547
Feature activation+3.62e-01

Pos logit contributions
 necks+0.489
aron+0.480
opes+0.478
uted+0.474
 valleys+0.473
Neg logit contributions
t-0.353
 happened-0.323
 help-0.302
 day-0.302
 please-0.302
Token very
Token ID845
Feature activation+3.51e+00

Pos logit contributions
 necks+0.022
opes+0.021
cks+0.021
aron+0.021
uted+0.021
Neg logit contributions
 day-0.015
 help-0.015
 happened-0.015
t-0.015
 please-0.014
Token excited
Token ID6568
Feature activation+6.25e-01

Pos logit contributions
aron+0.172
cks+0.171
rily+0.166
 necks+0.166
uted+0.166
Neg logit contributions
t-0.194
 happened-0.186
 awaited-0.174
 help-0.172
 reward-0.171
Token to
Token ID284
Feature activation-9.42e+00

Pos logit contributions
ping+0.044
aron+0.043
 necks+0.043
opes+0.042
uted+0.042
Neg logit contributions
t-0.019
 happened-0.018
ha-0.018
 reward-0.018
 help-0.018
Token eat
Token ID4483
Feature activation-4.19e+00

Pos logit contributions
t+0.303
 happened+0.283
 day+0.258
 help+0.255
 week+0.249
Neg logit contributions
cks-0.673
 necks-0.671
aron-0.669
opes-0.669
ping-0.664
Token.
Token ID13
Feature activation+2.29e+00

Pos logit contributions
cks+0.568
 necks+0.565
aron+0.564
opes+0.562
ping+0.560
Neg logit contributions
t-0.412
 happened-0.393
 help-0.376
 day-0.373
 please-0.366
Token They
Token ID1119
Feature activation+8.99e+00

Pos logit contributions
cks+0.117
ping+0.117
 necks+0.114
opes+0.114
aron+0.113
Neg logit contributions
t-0.122
 happened-0.115
 please-0.115
 day-0.114
 help-0.112
Token were
Token ID547
Feature activation+1.28e+00

Pos logit contributions
 necks+0.585
cks+0.584
aron+0.579
opes+0.579
 valleys+0.576
Neg logit contributions
t-0.340
 happened-0.319
 day-0.300
 help-0.299
 please-0.293
Token tw
Token ID665
Feature activation+8.75e+00

Pos logit contributions
aron+0.070
cks+0.070
 necks+0.070
opes+0.069
uted+0.069
Neg logit contributions
t-0.061
 happened-0.059
 help-0.057
 day-0.057
 please-0.056
Tokenirling
Token ID24297
Feature activation+1.74e+01

Pos logit contributions
aron+0.337
ping+0.323
uted+0.314
 valleys+0.305
opes+0.304
Neg logit contributions
t-0.563
 please-0.527
 help-0.526
 happened-0.509
 day-0.507
Token and
Token ID290
Feature activation+9.22e+00

Pos logit contributions
cks+0.997
aron+0.966
opes+0.966
aters+0.955
 necks+0.941
Neg logit contributions
t-0.852
 day-0.815
 happened-0.815
 help-0.761
 would-0.757
Token jumping
Token ID14284
Feature activation+6.06e+00

Pos logit contributions
cks+0.460
aron+0.459
 necks+0.457
opes+0.456
uted+0.454
Neg logit contributions
t-0.490
 happened-0.472
 help-0.457
 day-0.455
 please-0.446
Token,
Token ID11
Feature activation-6.44e+00

Pos logit contributions
cks+0.386
aters+0.376
 necks+0.368
opes+0.367
ady+0.367
Neg logit contributions
t-0.267
 day-0.244
 happened-0.241
 would-0.237
 help-0.237
Token when
Token ID618
Feature activation+1.71e+00

Pos logit contributions
 day+0.291
 they+0.285
 would+0.285
 she+0.284
 help+0.281
Neg logit contributions
aters-0.366
aron-0.361
ags-0.360
opes-0.356
cks-0.356
Token suddenly
Token ID6451
Feature activation-4.50e-01

Pos logit contributions
 valleys+0.123
 necks+0.118
opes+0.117
cks+0.116
aters+0.114
Neg logit contributions
t-0.056
 happened-0.047
 help-0.045
 reward-0.044
 please-0.043
Token,
Token ID11
Feature activation-6.57e+00

Pos logit contributions
t+0.017
 please+0.015
 help+0.014
 day+0.014
 week+0.014
Neg logit contributions
 valleys-0.030
 necks-0.029
opes-0.029
cks-0.029
ping-0.028
Token to
Token ID284
Feature activation-9.43e+00

Pos logit contributions
 necks+0.184
cks+0.183
opes+0.182
ping+0.181
 valleys+0.181
Neg logit contributions
t-0.047
 happened-0.041
 help-0.035
 day-0.035
 please-0.034
Token roll
Token ID4836
Feature activation+5.60e+00

Pos logit contributions
 help+0.292
t+0.273
 please+0.268
 day+0.257
 thank+0.250
Neg logit contributions
uted-0.706
ping-0.698
aron-0.691
rily-0.689
opes-0.689
Token the
Token ID262
Feature activation+4.82e-01

Pos logit contributions
aron+0.400
ping+0.396
opes+0.395
uted+0.392
cks+0.391
Neg logit contributions
t-0.189
 day-0.173
 happened-0.172
 help-0.167
 please-0.161
Token ball
Token ID2613
Feature activation+9.55e-01

Pos logit contributions
aron+0.032
cks+0.031
uted+0.031
ping+0.031
rily+0.030
Neg logit contributions
t-0.020
 day-0.019
 help-0.018
 happened-0.018
 week-0.017
Token to
Token ID284
Feature activation-9.42e+00

Pos logit contributions
aron+0.054
cks+0.054
 necks+0.054
opes+0.054
ping+0.054
Neg logit contributions
t-0.045
 happened-0.042
 day-0.041
 help-0.041
 please-0.040
Token each
Token ID1123
Feature activation+5.64e+00

Pos logit contributions
 help+0.391
 day+0.355
 please+0.347
 thank+0.339
 would+0.330
Neg logit contributions
uted-0.623
aron-0.620
ping-0.616
aters-0.610
opes-0.610
Token other
Token ID584
Feature activation-6.76e+00

Pos logit contributions
aron+0.390
cks+0.387
opes+0.385
 necks+0.384
ping+0.382
Neg logit contributions
t-0.199
 day-0.184
 happened-0.184
 help-0.180
 week-0.174
Token and
Token ID290
Feature activation+8.47e+00

Pos logit contributions
 day+0.346
t+0.333
 help+0.326
 week+0.324
 would+0.314
Neg logit contributions
cks-0.361
opes-0.348
uted-0.348
rily-0.343
 valleys-0.342
Token catch
Token ID4929
Feature activation+1.14e+00

Pos logit contributions
 necks+0.558
cks+0.552
aron+0.545
opes+0.543
 valleys+0.543
Neg logit contributions
t-0.326
 happened-0.307
 day-0.275
 week-0.272
 help-0.272
Token it
Token ID340
Feature activation-2.17e+00

Pos logit contributions
aron+0.096
opes+0.093
edly+0.092
aters+0.091
ping+0.091
Neg logit contributions
 day-0.025
 help-0.023
 happened-0.023
t-0.020
 week-0.020
Token.
Token ID13
Feature activation+1.50e+00

Pos logit contributions
t+0.096
 day+0.092
 happened+0.090
 help+0.090
 please+0.087
Neg logit contributions
aron-0.130
opes-0.128
uted-0.127
 necks-0.127
ping-0.127
Token She
Token ID1375
Feature activation+3.48e+00

Pos logit contributions
cks+0.254
 necks+0.254
opes+0.253
aron+0.253
uted+0.252
Neg logit contributions
t-0.165
 happened-0.157
 help-0.150
 day-0.149
 please-0.145
Token had
Token ID550
Feature activation-4.41e+00

Pos logit contributions
aron+0.223
 necks+0.222
cks+0.221
opes+0.221
uted+0.221
Neg logit contributions
t-0.135
 happened-0.125
 day-0.121
 help-0.121
 week-0.118
Token found
Token ID1043
Feature activation-5.84e+00

Pos logit contributions
t+0.175
 day+0.162
 happened+0.160
 awaited+0.157
 please+0.157
Neg logit contributions
 necks-0.276
cks-0.271
opes-0.270
ping-0.269
 valleys-0.269
Token Sam
Token ID3409
Feature activation-7.74e+00

Pos logit contributions
t+0.281
 happened+0.267
 day+0.255
 please+0.252
 help+0.252
Neg logit contributions
cks-0.323
opes-0.318
 necks-0.318
ping-0.318
uted-0.317
Token with
Token ID351
Feature activation+4.36e+00

Pos logit contributions
t+0.383
 happened+0.367
 help+0.354
 day+0.352
 please+0.346
Neg logit contributions
cks-0.415
 necks-0.413
aron-0.412
opes-0.411
uted-0.407
Token all
Token ID477
Feature activation+6.31e+00

Pos logit contributions
cks+0.233
 necks+0.232
opes+0.231
ping+0.229
aron+0.229
Neg logit contributions
t-0.217
 happened-0.206
 day-0.197
 help-0.196
 please-0.194
Token the
Token ID262
Feature activation+5.00e-01

Pos logit contributions
 necks+0.405
cks+0.405
opes+0.403
aron+0.403
uted+0.399
Neg logit contributions
t-0.247
 happened-0.235
 help-0.225
 day-0.225
 week-0.216
Token plastic
Token ID7309
Feature activation+7.49e+00

Pos logit contributions
cks+0.025
aron+0.025
uted+0.025
ping+0.025
opes+0.025
Neg logit contributions
t-0.027
 happened-0.026
 help-0.026
 day-0.025
 week-0.025
Token pieces
Token ID5207
Feature activation+7.66e+00

Pos logit contributions
cks+0.331
aron+0.324
uted+0.322
ping+0.320
opes+0.318
Neg logit contributions
t-0.453
 happened-0.435
 help-0.428
 day-0.423
 please-0.411
Token,
Token ID11
Feature activation-7.08e+00

Pos logit contributions
cks+0.415
ping+0.411
 necks+0.411
aron+0.411
opes+0.408
Neg logit contributions
t-0.364
 happened-0.351
 help-0.338
 please-0.335
 day-0.334
Token and
Token ID290
Feature activation+8.48e+00

Pos logit contributions
t+0.367
 happened+0.364
 help+0.358
 day+0.349
 would+0.342
Neg logit contributions
cks-0.362
uted-0.352
aters-0.350
rily-0.350
aron-0.349
Token Mia
Token ID32189
Feature activation-5.28e+00

Pos logit contributions
aron+0.081
 valleys+0.079
 necks+0.079
cks+0.078
rily+0.077
Neg logit contributions
t-0.056
 happened-0.054
 awaited-0.052
 help-0.051
 day-0.050
Token said
Token ID531
Feature activation-9.12e+00

Pos logit contributions
t+0.134
 happened+0.120
 help+0.113
 day+0.112
 week+0.108
Neg logit contributions
aron-0.412
 necks-0.410
uted-0.406
cks-0.405
opes-0.404
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
t+0.469
 happened+0.449
 day+0.436
 awaited+0.432
 week+0.430
Neg logit contributions
aron-0.464
ping-0.459
rily-0.459
uted-0.456
cks-0.453
Token
Token ID198
Feature activation-8.17e-01

Pos logit contributions
cks+0.088
ping+0.087
opes+0.087
 necks+0.086
rily+0.085
Neg logit contributions
t-0.066
 happened-0.062
 help-0.060
 please-0.060
 day-0.058
Token
Token ID198
Feature activation-8.05e-01

Pos logit contributions
t+0.037
 happened+0.035
 help+0.034
 day+0.034
 please+0.033
Neg logit contributions
cks-0.047
 necks-0.047
aron-0.047
opes-0.047
ping-0.047
TokenThey
Token ID2990
Feature activation+1.14e+01

Pos logit contributions
t+0.038
 please+0.035
 help+0.034
 happened+0.033
 day+0.033
Neg logit contributions
ping-0.048
rily-0.048
opes-0.047
aters-0.047
cks-0.046
Token leaned
Token ID23831
Feature activation+8.03e+00

Pos logit contributions
cks+0.745
aron+0.739
ping+0.737
opes+0.730
uted+0.728
Neg logit contributions
t-0.432
 happened-0.418
 help-0.407
 day-0.386
 please-0.386
Token over
Token ID625
Feature activation+1.53e+00

Pos logit contributions
opes+0.510
cks+0.499
aron+0.497
 necks+0.495
bes+0.491
Neg logit contributions
t-0.352
 day-0.328
 happened-0.328
 please-0.322
 help-0.319
Token the
Token ID262
Feature activation+4.53e-01

Pos logit contributions
opes+0.098
aron+0.098
uted+0.098
cks+0.098
ping+0.097
Neg logit contributions
 help-0.065
 day-0.061
t-0.061
 happened-0.060
 week-0.057
Token hole
Token ID7604
Feature activation+9.07e+00

Pos logit contributions
aron+0.018
cks+0.018
uted+0.018
opes+0.018
aters+0.018
Neg logit contributions
t-0.029
 happened-0.028
 help-0.028
 day-0.028
 please-0.027
Token and
Token ID290
Feature activation+8.41e+00

Pos logit contributions
cks+0.463
opes+0.458
aters+0.450
 necks+0.448
aron+0.445
Neg logit contributions
t-0.502
 day-0.468
 happened-0.460
 help-0.452
 week-0.448
Token little
Token ID1310
Feature activation-1.07e-01

Pos logit contributions
ping+0.384
 necks+0.372
 valleys+0.371
uted+0.368
opes+0.364
Neg logit contributions
t-0.374
 happened-0.353
 please-0.343
 would-0.330
 awaited-0.329
Token girl
Token ID2576
Feature activation-2.68e+00

Pos logit contributions
t+0.005
 happened+0.005
 please+0.004
 help+0.004
 awaited+0.004
Neg logit contributions
 necks-0.006
 valleys-0.006
ping-0.006
aron-0.006
rily-0.006
Token was
Token ID373
Feature activation-4.75e-01

Pos logit contributions
t+0.108
 happened+0.100
 help+0.096
 day+0.096
 week+0.095
Neg logit contributions
 necks-0.170
aron-0.168
uted-0.166
opes-0.166
cks-0.166
Token scared
Token ID12008
Feature activation+1.35e+00

Pos logit contributions
t+0.024
 happened+0.023
 help+0.022
 day+0.022
 please+0.022
Neg logit contributions
opes-0.026
 necks-0.026
cks-0.025
aters-0.025
aron-0.025
Token but
Token ID475
Feature activation+6.35e+00

Pos logit contributions
ping+0.074
aron+0.073
 necks+0.072
uted+0.072
cks+0.072
Neg logit contributions
t-0.065
 happened-0.062
 help-0.059
 reward-0.058
 day-0.058
Token brave
Token ID14802
Feature activation-3.13e+00

Pos logit contributions
uted+0.427
 valleys+0.427
ping+0.427
 necks+0.426
cks+0.424
Neg logit contributions
t-0.224
 happened-0.201
 help-0.192
 week-0.187
 reward-0.186
Token.
Token ID13
Feature activation+1.78e+00

Pos logit contributions
t+0.172
 happened+0.155
 help+0.153
 please+0.151
 reward+0.150
Neg logit contributions
ping-0.157
aron-0.156
 necks-0.151
rily-0.151
 valleys-0.149
Token She
Token ID1375
Feature activation+3.78e+00

Pos logit contributions
cks+0.107
 necks+0.099
opes+0.098
bes+0.098
aters+0.095
Neg logit contributions
t-0.086
 happened-0.084
 please-0.083
 day-0.082
 help-0.081
Token started
Token ID2067
Feature activation+7.77e-01

Pos logit contributions
 necks+0.245
aron+0.244
cks+0.243
opes+0.242
ping+0.241
Neg logit contributions
t-0.146
 happened-0.137
 help-0.131
 day-0.130
 please-0.127
Token to
Token ID284
Feature activation-9.10e+00

Pos logit contributions
cks+0.065
aron+0.065
 necks+0.065
opes+0.064
uted+0.064
Neg logit contributions
t-0.015
 happened-0.014
 help-0.013
 day-0.012
 please-0.012
Token shout
Token ID9191
Feature activation-1.72e-01

Pos logit contributions
 help+0.348
 happened+0.341
t+0.339
 day+0.325
 please+0.322
Neg logit contributions
cks-0.590
aron-0.586
opes-0.585
rily-0.583
aters-0.581
Token tried
Token ID3088
Feature activation-1.84e+00

Pos logit contributions
t+0.196
 happened+0.182
 please+0.177
 week+0.174
 help+0.174
Neg logit contributions
 necks-0.392
opes-0.385
aron-0.383
cks-0.381
 valleys-0.380
Token to
Token ID284
Feature activation-9.22e+00

Pos logit contributions
t+0.044
 happened+0.040
 help+0.039
 day+0.038
 please+0.035
Neg logit contributions
cks-0.147
aron-0.147
uted-0.146
opes-0.145
rily-0.145
Token fly
Token ID6129
Feature activation+4.32e+00

Pos logit contributions
 help+0.318
t+0.311
 please+0.289
 day+0.287
 happened+0.285
Neg logit contributions
cks-0.637
uted-0.635
opes-0.634
rily-0.633
 valleys-0.629
Token and
Token ID290
Feature activation+8.66e+00

Pos logit contributions
opes+0.250
cks+0.250
aron+0.248
uted+0.248
 necks+0.246
Neg logit contributions
t-0.199
 help-0.188
 happened-0.187
 day-0.185
 please-0.182
Token even
Token ID772
Feature activation+4.89e+00

Pos logit contributions
 necks+0.493
 valleys+0.487
cks+0.468
 neck+0.467
bes+0.457
Neg logit contributions
t-0.399
 happened-0.381
 awaited-0.350
 week-0.346
ha-0.346
Token turned
Token ID2900
Feature activation+4.76e+00

Pos logit contributions
 valleys+0.271
cks+0.269
 necks+0.267
ping+0.263
aron+0.254
Neg logit contributions
t-0.243
 happened-0.213
 awaited-0.207
 please-0.204
ha-0.199
Token it
Token ID340
Feature activation-1.95e+00

Pos logit contributions
cks+0.277
 necks+0.276
aron+0.275
opes+0.275
uted+0.273
Neg logit contributions
t-0.214
 happened-0.204
 help-0.197
 day-0.195
 please-0.191
Token into
Token ID656
Feature activation+7.76e+00

Pos logit contributions
t+0.099
 happened+0.095
 help+0.092
 day+0.091
 please+0.090
Neg logit contributions
cks-0.101
 necks-0.101
aron-0.101
opes-0.100
ping-0.100
Token a
Token ID257
Feature activation+5.32e+00

Pos logit contributions
uted+0.505
cks+0.502
aron+0.494
ping+0.490
opes+0.487
Neg logit contributions
 help-0.324
 day-0.304
 happened-0.299
 week-0.285
 please-0.285
Token pirate
Token ID25868
Feature activation-1.63e+00

Pos logit contributions
 valleys+0.272
 necks+0.266
aron+0.263
rily+0.254
ping+0.253
Neg logit contributions
t-0.278
 happened-0.267
 awaited-0.246
 help-0.241
 please-0.236
Token ship
Token ID4074
Feature activation+1.97e+00

Pos logit contributions
t+0.081
 happened+0.078
 help+0.074
 day+0.073
 please+0.072
Neg logit contributions
 necks-0.088
cks-0.087
aron-0.087
opes-0.086
ping-0.086
Token her
Token ID607
Feature activation+3.23e-01

Pos logit contributions
t+0.151
 happened+0.144
 day+0.132
 help+0.131
 please+0.131
Neg logit contributions
ping-0.179
aron-0.179
 necks-0.178
cks-0.176
opes-0.176
Token and
Token ID290
Feature activation+8.60e+00

Pos logit contributions
cks+0.020
 necks+0.020
aron+0.020
opes+0.020
ping+0.020
Neg logit contributions
t-0.013
 happened-0.013
 help-0.012
 day-0.012
 please-0.012
Token went
Token ID1816
Feature activation-2.67e+00

Pos logit contributions
ping+0.505
 necks+0.500
uted+0.499
aron+0.496
cks+0.494
Neg logit contributions
t-0.393
ha-0.324
 happened-0.317
 please-0.310
 week-0.309
Token inside
Token ID2641
Feature activation-3.18e+00

Pos logit contributions
t+0.100
 happened+0.096
 help+0.088
 day+0.087
 please+0.086
Neg logit contributions
cks-0.175
 necks-0.175
aron-0.174
ping-0.173
 valleys-0.172
Token her
Token ID607
Feature activation+2.80e-01

Pos logit contributions
t+0.124
 happened+0.118
 help+0.114
 day+0.112
 please+0.110
Neg logit contributions
cks-0.203
 necks-0.202
aron-0.202
opes-0.201
uted-0.200
Token house
Token ID2156
Feature activation+8.57e-01

Pos logit contributions
 necks+0.015
cks+0.014
opes+0.014
 valleys+0.014
aters+0.014
Neg logit contributions
t-0.015
 happened-0.014
 please-0.013
ha-0.013
 help-0.013
Token.
Token ID13
Feature activation+1.58e+00

Pos logit contributions
cks+0.048
 necks+0.047
aron+0.047
opes+0.047
ping+0.047
Neg logit contributions
t-0.040
 happened-0.039
 help-0.037
 day-0.037
 please-0.036
Token She
Token ID1375
Feature activation+3.56e+00

Pos logit contributions
cks+0.091
 necks+0.089
ping+0.089
opes+0.089
uted+0.087
Neg logit contributions
t-0.076
 day-0.072
 happened-0.072
 help-0.071
 week-0.070
Token knew
Token ID2993
Feature activation-7.30e+00

Pos logit contributions
 necks+0.224
aron+0.221
 valleys+0.216
opes+0.216
uted+0.215
Neg logit contributions
t-0.145
 happened-0.131
 please-0.125
 help-0.124
 week-0.123
Token she
Token ID673
Feature activation-5.84e+00

Pos logit contributions
t+0.282
 happened+0.232
 week+0.225
ha+0.223
 reward+0.216
Neg logit contributions
uted-0.452
rily-0.449
 valleys-0.444
ping-0.441
aron-0.441
Token'd
Token ID1549
Feature activation-4.87e+00

Pos logit contributions
t+0.161
 week+0.155
 please+0.154
 help+0.149
 reward+0.148
Neg logit contributions
aron-0.404
ping-0.396
 necks-0.395
opes-0.394
uted-0.390
Token decided
Token ID3066
Feature activation+6.45e-04

Pos logit contributions
t+0.251
 happened+0.234
 awaited+0.232
 help+0.228
 week+0.223
Neg logit contributions
 necks-0.339
aron-0.330
opes-0.324
 valleys-0.323
uted-0.321
Token he
Token ID339
Feature activation-5.68e+00

Pos logit contributions
 necks+0.000
ping+0.000
uted+0.000
 valleys+0.000
aron+0.000
Neg logit contributions
t-0.000
 happened-0.000
 day-0.000
 awaited-0.000
 reward-0.000
Token would
Token ID561
Feature activation-1.12e+01

Pos logit contributions
t+0.148
 week+0.136
 day+0.136
 happened+0.135
 help+0.133
Neg logit contributions
 necks-0.419
aron-0.418
opes-0.416
uted-0.410
cks-0.408
Token try
Token ID1949
Feature activation-4.67e+00

Pos logit contributions
t+0.400
 happened+0.384
 day+0.354
 help+0.350
 please+0.342
Neg logit contributions
cks-0.748
 necks-0.748
aron-0.747
opes-0.744
ping-0.739
Token.
Token ID13
Feature activation+1.50e+00

Pos logit contributions
 help+0.120
 happened+0.119
 day+0.116
t+0.112
 to+0.109
Neg logit contributions
aron-0.361
rily-0.355
uted-0.355
aters-0.355
edly-0.353
Token
Token ID220
Feature activation+3.14e+00

Pos logit contributions
cks+0.098
ping+0.097
opes+0.096
uted+0.096
 necks+0.095
Neg logit contributions
t-0.062
 day-0.057
 happened-0.056
 help-0.055
 week-0.054
Token
Token ID198
Feature activation-7.47e-01

Pos logit contributions
 necks+0.189
cks+0.188
opes+0.188
ping+0.188
aron+0.187
Neg logit contributions
t-0.137
 happened-0.128
 help-0.123
 day-0.122
 please-0.120
Token
Token ID198
Feature activation-7.44e-01

Pos logit contributions
t+0.032
 happened+0.028
 day+0.028
 help+0.028
 week+0.027
Neg logit contributions
opes-0.047
 necks-0.047
cks-0.047
ping-0.047
uted-0.046
TokenHe
Token ID1544
Feature activation+9.27e+00

Pos logit contributions
t+0.040
 day+0.034
 week+0.034
 would+0.033
ha+0.033
Neg logit contributions
rily-0.046
cks-0.045
ags-0.045
aters-0.044
opes-0.044
Token saw
Token ID2497
Feature activation-5.04e+00

Pos logit contributions
 necks+0.574
 valleys+0.559
aron+0.557
opes+0.556
cks+0.548
Neg logit contributions
t-0.391
 happened-0.355
 please-0.346
 help-0.345
 awaited-0.343
Token a
Token ID257
Feature activation+5.10e+00

Pos logit contributions
t+0.265
 happened+0.257
 help+0.250
 day+0.247
 please+0.242
Neg logit contributions
cks-0.255
aron-0.255
 necks-0.253
opes-0.252
ping-0.250
Token Lily
Token ID20037
Feature activation-5.91e+00

Pos logit contributions
t+0.366
 happened+0.336
 awaited+0.306
 day+0.304
 week+0.298
Neg logit contributions
cks-0.616
ping-0.613
rily-0.610
aron-0.608
uted-0.602
Token with
Token ID351
Feature activation+4.32e+00

Pos logit contributions
 day+0.231
 help+0.231
t+0.231
 week+0.213
 please+0.212
Neg logit contributions
 valleys-0.384
opes-0.379
cks-0.376
uted-0.373
 necks-0.373
Token a
Token ID257
Feature activation+5.04e+00

Pos logit contributions
cks+0.226
 necks+0.223
ping+0.220
opes+0.219
aron+0.219
Neg logit contributions
t-0.222
 happened-0.200
 day-0.197
 week-0.195
 awaited-0.193
Token big
Token ID1263
Feature activation-3.68e+00

Pos logit contributions
aron+0.270
rily+0.266
 necks+0.265
cks+0.259
aters+0.258
Neg logit contributions
t-0.238
 happened-0.221
 awaited-0.215
 day-0.214
 week-0.209
Token smile
Token ID8212
Feature activation+2.74e+00

Pos logit contributions
t+0.154
 happened+0.144
 day+0.135
 awaited+0.133
 week+0.132
Neg logit contributions
aron-0.225
 necks-0.225
cks-0.222
ping-0.220
opes-0.220
Token.
Token ID13
Feature activation+1.47e+00

Pos logit contributions
aron+0.143
ping+0.142
cks+0.141
 necks+0.140
rily+0.139
Neg logit contributions
t-0.140
 happened-0.132
 help-0.130
 please-0.127
 day-0.127
Token Lily
Token ID20037
Feature activation-5.91e+00

Pos logit contributions
cks+0.091
 necks+0.090
ping+0.090
opes+0.090
uted+0.089
Neg logit contributions
t-0.062
 happened-0.059
 day-0.056
 help-0.056
 please-0.055
Token was
Token ID373
Feature activation-7.71e-01

Pos logit contributions
t+0.194
 happened+0.186
 help+0.177
 would+0.173
 day+0.171
Neg logit contributions
cks-0.425
 valleys-0.415
ags-0.412
opes-0.411
aters-0.411
Token so
Token ID523
Feature activation+6.72e+00

Pos logit contributions
t+0.034
 help+0.033
 happened+0.033
 day+0.033
 please+0.032
Neg logit contributions
opes-0.047
 necks-0.046
 valleys-0.046
cks-0.045
aters-0.044
Token happy
Token ID3772
Feature activation-9.25e-01

Pos logit contributions
uted+0.355
aron+0.354
cks+0.353
ping+0.349
 necks+0.343
Neg logit contributions
t-0.332
 happened-0.318
 help-0.304
 awaited-0.299
 day-0.299
Token!
Token ID0
Feature activation+4.07e+00

Pos logit contributions
t+0.045
 happened+0.043
 help+0.042
 day+0.041
 please+0.041
Neg logit contributions
aron-0.050
ping-0.049
 necks-0.049
cks-0.049
uted-0.049
Token a
Token ID257
Feature activation+5.62e+00

Pos logit contributions
t+0.174
 please+0.154
 day+0.154
 awaited+0.153
 help+0.152
Neg logit contributions
 necks-0.220
 valleys-0.218
cks-0.216
opes-0.215
ping-0.213
Token good
Token ID922
Feature activation-1.00e+01

Pos logit contributions
 neck+0.297
 necks+0.294
 piles+0.292
 unison+0.287
 valleys+0.287
Neg logit contributions
t-0.267
 awaited-0.231
 happened-0.223
ha-0.208
ll-0.205
Token idea
Token ID2126
Feature activation-4.90e+00

Pos logit contributions
t+0.407
 awaited+0.351
 happened+0.348
 please+0.345
ha+0.340
Neg logit contributions
 necks-0.626
aron-0.620
ping-0.610
opes-0.600
aters-0.598
Token.
Token ID13
Feature activation+1.95e+00

Pos logit contributions
t+0.267
 happened+0.256
 day+0.247
 week+0.247
 reward+0.244
Neg logit contributions
aron-0.231
cks-0.226
ping-0.224
uted-0.222
 necks-0.221
Token He
Token ID679
Feature activation+3.97e+00

Pos logit contributions
cks+0.098
ping+0.097
opes+0.095
 necks+0.095
uted+0.094
Neg logit contributions
t-0.106
 happened-0.100
 day-0.099
 please-0.099
 help-0.098
Token asked
Token ID1965
Feature activation-6.47e+00

Pos logit contributions
 necks+0.241
aron+0.239
opes+0.236
uted+0.234
rily+0.233
Neg logit contributions
t-0.169
 happened-0.153
 day-0.149
 help-0.148
 awaited-0.148
Token the
Token ID262
Feature activation+8.71e-01

Pos logit contributions
t+0.368
 happened+0.345
 awaited+0.318
 day+0.316
 week+0.313
Neg logit contributions
aron-0.312
rily-0.310
ping-0.307
 necks-0.306
 valleys-0.304
Token other
Token ID584
Feature activation-6.44e+00

Pos logit contributions
 necks+0.049
 valleys+0.049
ping+0.047
aron+0.047
opes+0.047
Neg logit contributions
t-0.041
 happened-0.038
 awaited-0.036
ha-0.034
 please-0.034
Token animals
Token ID4695
Feature activation+4.82e+00

Pos logit contributions
t+0.310
 happened+0.295
 awaited+0.271
 please+0.265
ha+0.261
Neg logit contributions
 necks-0.362
aron-0.349
 valleys-0.349
ping-0.348
uted-0.346
Token in
Token ID287
Feature activation+1.84e+00

Pos logit contributions
uted+0.303
ping+0.302
 necks+0.302
 valleys+0.301
aron+0.299
Neg logit contributions
t-0.177
 happened-0.169
ha-0.157
 reward-0.147
 awaited-0.147
Token the
Token ID262
Feature activation+7.55e-01

Pos logit contributions
cks+0.111
 necks+0.111
aron+0.110
 valleys+0.109
opes+0.109
Neg logit contributions
t-0.079
 happened-0.075
 help-0.070
 day-0.070
 please-0.069
Token old
Token ID1468
Feature activation-1.75e-01

Pos logit contributions
t+0.047
 happened+0.044
 help+0.041
 awaited+0.041
 day+0.040
Neg logit contributions
aron-0.049
ping-0.048
 necks-0.047
uted-0.047
 valleys-0.047
Token bird
Token ID6512
Feature activation-5.75e+00

Pos logit contributions
t+0.008
 happened+0.007
 awaited+0.006
 help+0.006
 please+0.006
Neg logit contributions
 necks-0.010
aron-0.010
ping-0.010
opes-0.010
 valleys-0.010
Token saw
Token ID2497
Feature activation-4.68e+00

Pos logit contributions
t+0.223
 reward+0.202
 week+0.197
 help+0.197
 please+0.195
Neg logit contributions
cks-0.378
ping-0.363
uted-0.360
 necks-0.358
opes-0.355
Token them
Token ID606
Feature activation+1.90e+00

Pos logit contributions
t+0.218
 happened+0.207
 help+0.200
 day+0.199
 please+0.195
Neg logit contributions
cks-0.267
 necks-0.264
aron-0.264
opes-0.263
uted-0.262
Token and
Token ID290
Feature activation+8.80e+00

Pos logit contributions
aron+0.107
 valleys+0.104
rily+0.104
 necks+0.103
aters+0.102
Neg logit contributions
t-0.093
 help-0.091
 happened-0.090
 day-0.090
 please-0.085
Token said
Token ID531
Feature activation-8.75e+00

Pos logit contributions
cks+0.565
 necks+0.564
uted+0.560
ping+0.558
opes+0.557
Neg logit contributions
t-0.343
 day-0.302
 happened-0.298
 week-0.296
 please-0.288
Token,
Token ID11
Feature activation-6.81e+00

Pos logit contributions
t+0.313
 day+0.297
 week+0.292
 awaited+0.286
 reward+0.269
Neg logit contributions
uted-0.561
rily-0.548
aron-0.545
opes-0.540
 necks-0.538
Token "
Token ID366
Feature activation+1.69e+00

Pos logit contributions
t+0.294
 happened+0.280
 please+0.272
 help+0.271
 day+0.261
Neg logit contributions
cks-0.416
 necks-0.410
aters-0.410
opes-0.404
aron-0.403
TokenStop
Token ID19485
Feature activation-6.21e-01

Pos logit contributions
aron+0.087
opes+0.087
cks+0.086
 necks+0.085
aters+0.085
Neg logit contributions
t-0.091
 happened-0.085
 help-0.082
 day-0.082
 please-0.081
Token fighting
Token ID4330
Feature activation+3.47e+00

Pos logit contributions
t+0.029
 week+0.027
 day+0.027
 happened+0.026
 reward+0.026
Neg logit contributions
uted-0.035
ping-0.035
cks-0.035
opes-0.034
 necks-0.034
Token!
Token ID0
Feature activation+4.29e+00

Pos logit contributions
cks+0.220
 necks+0.219
aron+0.219
opes+0.218
ping+0.217
Neg logit contributions
t-0.138
 happened-0.131
 help-0.126
 day-0.124
 please-0.122
Token busy
Token ID8179
Feature activation-1.45e+00

Pos logit contributions
 happened+0.377
t+0.376
ha+0.334
 day+0.334
 week+0.329
Neg logit contributions
 necks-0.543
cks-0.531
aron-0.529
ping-0.522
aters-0.518
Token poking
Token ID39048
Feature activation+1.29e+00

Pos logit contributions
t+0.070
 happened+0.067
 help+0.065
 day+0.064
 please+0.063
Neg logit contributions
cks-0.078
 necks-0.078
aron-0.078
opes-0.078
ping-0.077
Token around
Token ID1088
Feature activation+1.35e+00

Pos logit contributions
 necks+0.074
aron+0.074
cks+0.073
opes+0.073
uted+0.073
Neg logit contributions
t-0.058
 happened-0.057
 help-0.055
 day-0.054
 please-0.053
Token the
Token ID262
Feature activation+1.41e+00

Pos logit contributions
cks+0.077
aron+0.076
 necks+0.076
uted+0.076
opes+0.076
Neg logit contributions
t-0.062
 happened-0.060
 day-0.059
 help-0.059
 week-0.057
Token shelves
Token ID20726
Feature activation+9.42e+00

Pos logit contributions
cks+0.069
uted+0.066
aron+0.065
rily+0.065
opes+0.065
Neg logit contributions
 day-0.079
 help-0.077
t-0.076
 happened-0.075
 week-0.075
Token,
Token ID11
Feature activation-6.32e+00

Pos logit contributions
cks+0.559
opes+0.552
 necks+0.550
aron+0.545
ping+0.541
Neg logit contributions
t-0.439
 happened-0.399
 day-0.397
 help-0.391
 week-0.382
Token his
Token ID465
Feature activation+3.56e+00

Pos logit contributions
 day+0.289
 happened+0.286
 help+0.284
t+0.282
 please+0.277
Neg logit contributions
aters-0.360
cks-0.357
ags-0.346
uted-0.345
opes-0.344
Token mom
Token ID1995
Feature activation-8.73e+00

Pos logit contributions
 necks+0.214
opes+0.212
cks+0.212
aron+0.212
ping+0.210
Neg logit contributions
t-0.154
 happened-0.145
 help-0.138
 day-0.137
 please-0.135
Tokenmy
Token ID1820
Feature activation-1.27e+00

Pos logit contributions
t+0.369
 happened+0.336
 help+0.323
 day+0.320
 reward+0.319
Neg logit contributions
aron-0.536
ping-0.529
 necks-0.527
cks-0.526
opes-0.524
Token came
Token ID1625
Feature activation-7.64e+00

Pos logit contributions
t+0.050
 happened+0.045
 day+0.043
 help+0.043
 week+0.043
Neg logit contributions
aron-0.081
ping-0.080
 necks-0.080
uted-0.080
opes-0.080
Token into
Token ID656
Feature activation+8.14e+00

Pos logit contributions
t+0.289
 help+0.286
 day+0.277
 please+0.277
 happened+0.276
Neg logit contributions
 necks-0.501
opes-0.501
cks-0.499
aron-0.487
bes-0.485
Token paying
Token ID5989
Feature activation+2.45e+00

Pos logit contributions
cks+0.031
ping+0.031
 valleys+0.030
 necks+0.030
uted+0.030
Neg logit contributions
t-0.029
 happened-0.027
 please-0.026
 help-0.026
 awaited-0.026
Token the
Token ID262
Feature activation+7.36e-01

Pos logit contributions
ping+0.145
cks+0.145
aron+0.144
 necks+0.144
 valleys+0.143
Neg logit contributions
t-0.104
 happened-0.099
 please-0.091
 day-0.091
 awaited-0.090
Token price
Token ID2756
Feature activation-2.98e+00

Pos logit contributions
 necks+0.042
 valleys+0.042
ping+0.042
aron+0.041
opes+0.041
Neg logit contributions
t-0.033
 happened-0.031
 please-0.029
 awaited-0.029
ha-0.028
Token.
Token ID13
Feature activation+1.74e+00

Pos logit contributions
t+0.131
 happened+0.124
 please+0.120
 day+0.119
 help+0.119
Neg logit contributions
ping-0.168
 necks-0.168
opes-0.167
aron-0.167
cks-0.167
Token Sadly
Token ID27213
Feature activation-1.67e+00

Pos logit contributions
cks+0.105
 necks+0.104
ping+0.104
opes+0.104
uted+0.102
Neg logit contributions
t-0.078
 happened-0.073
 day-0.071
 help-0.070
 week-0.069
Token,
Token ID11
Feature activation-6.84e+00

Pos logit contributions
t+0.049
 please+0.044
 help+0.043
 happened+0.042
 reward+0.039
Neg logit contributions
ping-0.120
aron-0.119
rily-0.119
 valleys-0.119
opes-0.119
Token they
Token ID484
Feature activation-3.70e+00

Pos logit contributions
t+0.249
 happened+0.234
 help+0.222
 please+0.219
 day+0.215
Neg logit contributions
cks-0.453
 necks-0.452
 valleys-0.451
opes-0.449
ping-0.449
Token were
Token ID547
Feature activation+6.24e-01

Pos logit contributions
t+0.147
 please+0.141
 happened+0.140
 week+0.137
 day+0.133
Neg logit contributions
 valleys-0.217
uted-0.215
 necks-0.214
ping-0.212
cks-0.212
Token stuck
Token ID7819
Feature activation+4.76e+00

Pos logit contributions
cks+0.035
ping+0.035
uted+0.034
 necks+0.034
aron+0.034
Neg logit contributions
t-0.029
 happened-0.028
 awaited-0.027
 please-0.026
 help-0.026
Token in
Token ID287
Feature activation+1.82e+00

Pos logit contributions
cks+0.274
opes+0.271
aron+0.271
 necks+0.271
uted+0.267
Neg logit contributions
t-0.221
 happened-0.211
 day-0.202
 help-0.202
 week-0.196
Token the
Token ID262
Feature activation+7.72e-01

Pos logit contributions
aron+0.112
cks+0.112
uted+0.112
opes+0.111
ping+0.111
Neg logit contributions
 help-0.076
t-0.076
 day-0.075
 happened-0.074
 week-0.072
Token laughed
Token ID13818
Feature activation-2.01e-01

Pos logit contributions
 necks+0.558
aron+0.547
ping+0.545
cks+0.544
opes+0.540
Neg logit contributions
t-0.358
 please-0.316
 happened-0.315
 help-0.306
 week-0.296
Token,
Token ID11
Feature activation-6.81e+00

Pos logit contributions
 day+0.008
 thank+0.008
 help+0.008
 happened+0.008
 please+0.007
Neg logit contributions
cks-0.014
 valleys-0.013
 necks-0.013
aters-0.013
ady-0.013
Token having
Token ID1719
Feature activation+7.39e+00

Pos logit contributions
 day+0.314
 thank+0.312
 they+0.307
t+0.301
 help+0.295
Neg logit contributions
aters-0.404
cks-0.396
ady-0.392
efully-0.390
ags-0.388
Token a
Token ID257
Feature activation+5.39e+00

Pos logit contributions
cks+0.517
opes+0.510
aron+0.510
rily+0.509
uted+0.509
Neg logit contributions
 happened-0.251
 day-0.247
 help-0.241
t-0.233
 week-0.229
Token great
Token ID1049
Feature activation-4.67e+00

Pos logit contributions
aron+0.296
 necks+0.293
 valleys+0.287
 unison+0.286
cks+0.282
Neg logit contributions
t-0.248
 happened-0.234
 awaited-0.223
 please-0.216
 help-0.211
Token time
Token ID640
Feature activation-8.56e+00

Pos logit contributions
t+0.127
 happened+0.112
 please+0.112
 awaited+0.107
 help+0.106
Neg logit contributions
 necks-0.347
aron-0.342
opes-0.336
ping-0.336
cks-0.334
Token.
Token ID13
Feature activation+1.83e+00

Pos logit contributions
t+0.369
 happened+0.357
 help+0.348
 day+0.347
 please+0.328
Neg logit contributions
rily-0.506
aron-0.506
opes-0.505
cks-0.505
 necks-0.502
Token Bob
Token ID5811
Feature activation-5.35e+00

Pos logit contributions
rily+0.094
aron+0.093
cks+0.093
aters+0.092
 necks+0.092
Neg logit contributions
t-0.095
 day-0.092
 happened-0.092
 help-0.088
 week-0.087
Token was
Token ID373
Feature activation-4.06e-01

Pos logit contributions
t+0.299
 happened+0.290
 help+0.280
 day+0.280
 please+0.273
Neg logit contributions
cks-0.252
opes-0.248
 necks-0.247
aron-0.247
ping-0.246
Token so
Token ID523
Feature activation+7.06e+00

Pos logit contributions
t+0.017
 happened+0.017
 help+0.016
 day+0.016
 please+0.016
Neg logit contributions
opes-0.025
 necks-0.025
cks-0.025
aron-0.024
aters-0.024
Token happy
Token ID3772
Feature activation-5.58e-01

Pos logit contributions
cks+0.336
uted+0.328
ping+0.328
aron+0.325
 valleys+0.318
Neg logit contributions
t-0.371
 happened-0.368
 awaited-0.354
ha-0.347
 problem-0.342