TOP ACTIVATIONS
MAX = 3.854

listen to the clar inet quint et without fearing that some
im r man became the quint essential Czech hero , a
attack data . Airbus later rede - signed the algorithm and
when I ordered the Y YR Diff usion . In terms
me , what is this quint ess ence of dust ?
. Some of these minor overs ights consisted of such trivial
a few copies of the Canon 24 - 70 Mk II
: Size C , Y YR DS cent ering
back of Notre Dame , Nightmare on Elm Street , and
, according to one of Lois G . Lerner
never occurred before - A Nightmare on Elm Street , Friday
. The list of egregious overs ights by the voters that
- pres cript ive and overs impl ified recommendations that force
population becomes older and more ethn ically diverse , the additional
Po . Business Insider explains : " Ess entially
country , there is some une ase about their ambition to
prescribed therapeutic SS RI or benz od iazep ine .
ically one of the most inh osp itable and challenging places
a way , Julia H ahn is the Patty Hear st
, attended by Julia H ahn , costs about $ 40

MIN ACTIVATIONS
MIN = -3.548

objectives , but , like Sid ew inder , slippery terrain
fish debuted at Sund ance , was acquired by
the entrance to the Bangladesh Sund arb ans , southeast of
This aerial photograph of the Sund arb ans , made in
catastrophe is unprecedented in the Sund arb ans , and we
the waters of Bangladesh 's Sund arb ans , the largest
ested . BT W , Sid Davis updated this movie in
Min ova ir respective of which unit is accused
except by water , the Sund arb ans is a place
chief forest official of the Sund arb ans in Bangladesh ,
re ment or sending so apy water back into the bowl
sund ari tree , the Sund arb ans is a vast
center for the city ," Ful op said .
th Season : Ghost Island TBA TBA The Complete Thirty -
Season : Ghost Island TBA TBA The Complete Thirty - Se
13 days ). Even emperor pengu in dads , who famously
. Expl ained Murd y , We
William Carpenter , Mont pel ier Con Hogan
, teeth are formed from dent in , a liquid that
even in a land of glaciers , Jak ob sh av

INTERVAL 2.004 - 3.854
CONTAINS 0.115%

. Tr uman was g rieved by
- wife of Right eous Brothers singer Bill Med ley ,
play physical and re - route Baldwin to throw the timing
hes story " <|endoftext|> ( Phys . org ) -- An
the 73 rd minute and Ireland also had a number of

INTERVAL 0.153 - 2.004
CONTAINS 34.320%

a failed sensor providing false information , which Remote Agent recognized
The city is claiming at least short - term
we re learning . We learned a lot once
and scar ring if she didn 't act right away '
** In many banks one doesn 't need to take any

INTERVAL -1.697 - 0.153
CONTAINS 65.210%

went to bat for a community resident after the D NR
Barron , director of the new law center .
the asteroid 99 69 Bra ille was only a partial success
fully aware that more subsidies will only exacerbate their pain .
received . I wanted to learn more about social justice from

INTERVAL -3.548 - -1.697
CONTAINS 0.355%

thing I knew you were melting me from the ice
many friends , who affection ately called him " Short y
technology to what Snap and Flat pak offer , so I
goes : About Aleppo and Syria , I truly
Make a file now with proof of your presence [ and
Token listen
Token ID6004
Feature activation+3.79e-01

Pos logit contributions
 Masquerade+0.787
 Goat+0.760
 Caps+0.715
================================================================+0.705
+0.675
Neg logit contributions
itton-0.867
pez-0.845
ocard-0.831
atts-0.784
ourage-0.781
Token to
Token ID284
Feature activation+6.65e-02

Pos logit contributions
itton+0.708
pez+0.688
ocard+0.681
atts+0.644
ourage+0.636
Neg logit contributions
 Masquerade-0.548
 Goat-0.524
 Caps-0.487
================================================================-0.481
-0.467
Token the
Token ID262
Feature activation+1.51e-01

Pos logit contributions
itton+0.121
pez+0.117
ocard+0.116
atts+0.109
ourage+0.109
Neg logit contributions
 Masquerade-0.100
 Goat-0.096
 Caps-0.090
================================================================-0.088
-0.085
Token clar
Token ID10212
Feature activation+5.25e-01

Pos logit contributions
itton+0.268
pez+0.261
ocard+0.257
atts+0.242
ourage+0.241
Neg logit contributions
 Masquerade-0.233
 Goat-0.226
 Caps-0.211
================================================================-0.206
-0.201
Tokeninet
Token ID42504
Feature activation+5.04e-01

Pos logit contributions
itton+0.951
pez+0.920
ocard+0.910
atts+0.861
ourage+0.850
Neg logit contributions
 Masquerade-0.788
 Goat-0.758
 Caps-0.705
================================================================-0.696
-0.678
Token quint
Token ID28533
Feature activation+3.85e+00

Pos logit contributions
itton+0.886
pez+0.859
ocard+0.849
atts+0.800
ourage+0.792
Neg logit contributions
 Masquerade-0.782
 Goat-0.753
 Caps-0.705
================================================================-0.694
-0.677
Tokenet
Token ID316
Feature activation+6.34e-01

Pos logit contributions
itton+5.356
pez+5.219
ocard+4.965
atts+4.753
ourage+4.637
Neg logit contributions
 Masquerade-7.049
 Goat-6.911
================================================================-6.437
 Caps-6.396
-6.250
Token without
Token ID1231
Feature activation-4.91e-01

Pos logit contributions
itton+1.130
pez+1.095
ocard+1.083
atts+1.022
ourage+1.011
Neg logit contributions
 Masquerade-0.970
 Goat-0.933
 Caps-0.872
================================================================-0.859
-0.836
Token fearing
Token ID33188
Feature activation+8.03e-01

Pos logit contributions
 Masquerade+0.771
 Goat+0.747
 Caps+0.698
================================================================+0.683
+0.662
Neg logit contributions
itton-0.853
pez-0.834
ocard-0.819
atts-0.768
ourage-0.763
Token that
Token ID326
Feature activation+2.40e-01

Pos logit contributions
itton+1.433
pez+1.384
ocard+1.372
atts+1.298
ourage+1.280
Neg logit contributions
 Masquerade-1.219
 Goat-1.167
 Caps-1.093
================================================================-1.081
-1.056
Token some
Token ID617
Feature activation+3.18e-01

Pos logit contributions
itton+0.443
pez+0.432
ocard+0.426
atts+0.402
ourage+0.400
Neg logit contributions
 Masquerade-0.352
 Goat-0.340
 Caps-0.316
================================================================-0.308
-0.300
Tokenim
Token ID320
Feature activation-3.34e-01

Pos logit contributions
 Masquerade+1.286
 Goat+1.245
 Caps+1.170
================================================================+1.154
+1.121
Neg logit contributions
itton-1.381
pez-1.349
ocard-1.330
atts-1.250
ourage-1.233
Tokenr
Token ID81
Feature activation+2.55e-01

Pos logit contributions
 Masquerade+0.523
 Goat+0.504
 Caps+0.477
================================================================+0.468
+0.454
Neg logit contributions
itton-0.578
pez-0.556
ocard-0.552
atts-0.521
ourage-0.515
Tokenman
Token ID805
Feature activation-8.95e-02

Pos logit contributions
itton+0.433
pez+0.420
ocard+0.418
atts+0.389
ourage+0.386
Neg logit contributions
 Masquerade-0.406
 Goat-0.392
 Caps-0.369
================================================================-0.363
-0.354
Token became
Token ID2627
Feature activation-8.89e-01

Pos logit contributions
 Masquerade+0.133
 Goat+0.128
 Caps+0.120
================================================================+0.118
+0.115
Neg logit contributions
itton-0.163
pez-0.158
ocard-0.156
atts-0.147
ourage-0.146
Token the
Token ID262
Feature activation-6.29e-02

Pos logit contributions
 Masquerade+1.371
 Goat+1.326
 Caps+1.242
================================================================+1.219
+1.189
Neg logit contributions
itton-1.571
pez-1.522
ocard-1.502
atts-1.413
ourage-1.395
Token quint
Token ID28533
Feature activation+3.58e+00

Pos logit contributions
 Masquerade+0.105
 Goat+0.102
 Caps+0.096
================================================================+0.094
+0.092
Neg logit contributions
itton-0.103
pez-0.100
ocard-0.098
atts-0.092
ourage-0.091
Tokenessential
Token ID31195
Feature activation+8.87e-01

Pos logit contributions
itton+4.480
pez+4.300
ocard+4.174
ourage+3.861
atts+3.797
Neg logit contributions
 Masquerade-7.134
 Goat-6.881
 Caps-6.540
================================================================-6.531
-6.356
Token Czech
Token ID16639
Feature activation+2.25e-01

Pos logit contributions
itton+1.548
pez+1.498
ocard+1.485
atts+1.398
ourage+1.382
Neg logit contributions
 Masquerade-1.380
 Goat-1.326
 Caps-1.239
================================================================-1.226
-1.198
Token hero
Token ID4293
Feature activation+1.81e-01

Pos logit contributions
itton+0.404
pez+0.392
ocard+0.386
atts+0.366
ourage+0.360
Neg logit contributions
 Masquerade-0.343
 Goat-0.330
 Caps-0.309
================================================================-0.304
-0.295
Token,
Token ID11
Feature activation+5.20e-02

Pos logit contributions
itton+0.349
pez+0.338
ocard+0.335
atts+0.317
ourage+0.314
Neg logit contributions
 Masquerade-0.250
 Goat-0.240
 Caps-0.222
================================================================-0.219
-0.213
Token a
Token ID257
Feature activation+1.58e-01

Pos logit contributions
itton+0.091
pez+0.088
ocard+0.087
atts+0.082
ourage+0.081
Neg logit contributions
 Masquerade-0.082
 Goat-0.079
 Caps-0.074
================================================================-0.073
-0.071
Tokenattack
Token ID20358
Feature activation-4.81e-02

Pos logit contributions
 Masquerade+0.201
 Goat+0.196
 Caps+0.187
================================================================+0.186
mentation+0.182
Neg logit contributions
itton-0.120
pez-0.114
ocard-0.112
atts-0.102
ourage-0.100
Token data
Token ID1366
Feature activation+3.56e-01

Pos logit contributions
 Masquerade+0.078
 Goat+0.076
 Caps+0.072
================================================================+0.070
+0.068
Neg logit contributions
itton-0.081
pez-0.078
ocard-0.077
atts-0.072
ourage-0.072
Token.
Token ID13
Feature activation+3.73e-01

Pos logit contributions
itton+0.658
pez+0.637
ocard+0.632
atts+0.595
ourage+0.591
Neg logit contributions
 Masquerade-0.520
 Goat-0.500
 Caps-0.468
================================================================-0.457
-0.445
Token Airbus
Token ID39173
Feature activation+1.13e+00

Pos logit contributions
itton+0.670
pez+0.650
ocard+0.643
atts+0.607
ourage+0.600
Neg logit contributions
 Masquerade-0.564
 Goat-0.542
 Caps-0.507
================================================================-0.499
-0.485
Token later
Token ID1568
Feature activation+8.52e-02

Pos logit contributions
itton+1.970
pez+1.908
ocard+1.886
atts+1.779
ourage+1.757
Neg logit contributions
 Masquerade-1.772
 Goat-1.703
 Caps-1.592
================================================================-1.574
-1.533
Token rede
Token ID21459
Feature activation+3.50e+00

Pos logit contributions
itton+0.148
pez+0.144
ocard+0.143
atts+0.133
ourage+0.132
Neg logit contributions
 Masquerade-0.133
 Goat-0.129
 Caps-0.122
================================================================-0.118
-0.115
Token -
Token ID532
Feature activation+1.59e-01

Pos logit contributions
itton+3.360
pez+3.326
ocard+3.246
atts+2.981
ourage+2.855
Neg logit contributions
 Masquerade-8.014
 Goat-7.750
 Caps-7.347
-7.323
================================================================-7.258
Token signed
Token ID4488
Feature activation-7.12e-01

Pos logit contributions
itton+0.265
pez+0.256
ocard+0.253
atts+0.237
ourage+0.235
Neg logit contributions
 Masquerade-0.259
 Goat-0.250
 Caps-0.236
================================================================-0.233
-0.227
Token the
Token ID262
Feature activation-5.62e-02

Pos logit contributions
 Masquerade+1.096
 Goat+1.061
 Caps+0.999
================================================================+0.966
+0.948
Neg logit contributions
itton-1.254
pez-1.220
ocard-1.203
atts-1.133
ourage-1.124
Token algorithm
Token ID11862
Feature activation-8.81e-01

Pos logit contributions
 Masquerade+0.091
 Goat+0.088
 Caps+0.083
================================================================+0.081
+0.079
Neg logit contributions
itton-0.095
pez-0.092
ocard-0.091
atts-0.085
ourage-0.085
Token and
Token ID290
Feature activation-1.16e-01

Pos logit contributions
 Masquerade+1.281
 Goat+1.234
 Caps+1.158
================================================================+1.126
+1.095
Neg logit contributions
itton-1.635
pez-1.585
ocard-1.561
atts-1.476
ourage-1.468
Token when
Token ID618
Feature activation-1.06e-01

Pos logit contributions
 Masquerade+1.950
 Goat+1.890
 Caps+1.756
================================================================+1.727
+1.669
Neg logit contributions
itton-2.371
ocard-2.286
pez-2.283
atts-2.154
ourage-2.125
Token I
Token ID314
Feature activation-2.49e-01

Pos logit contributions
 Masquerade+0.158
 Goat+0.153
 Caps+0.143
================================================================+0.139
+0.136
Neg logit contributions
itton-0.194
pez-0.188
ocard-0.186
atts-0.176
ourage-0.175
Token ordered
Token ID6149
Feature activation+7.12e-01

Pos logit contributions
 Masquerade+0.365
 Goat+0.354
 Caps+0.331
================================================================+0.323
+0.312
Neg logit contributions
itton-0.461
pez-0.446
ocard-0.442
atts-0.418
ourage-0.415
Token the
Token ID262
Feature activation+3.76e-02

Pos logit contributions
itton+1.235
pez+1.196
ocard+1.182
atts+1.113
ourage+1.100
Neg logit contributions
 Masquerade-1.122
 Goat-1.079
 Caps-1.011
================================================================-0.997
-0.972
Token Y
Token ID575
Feature activation+7.27e-01

Pos logit contributions
itton+0.069
pez+0.067
ocard+0.066
atts+0.062
ourage+0.062
Neg logit contributions
 Masquerade-0.056
 Goat-0.054
 Caps-0.050
================================================================-0.049
-0.048
TokenYR
Token ID38162
Feature activation+3.49e+00

Pos logit contributions
itton+1.098
pez+1.058
ocard+1.044
atts+0.974
ourage+0.961
Neg logit contributions
 Masquerade-1.309
 Goat-1.267
 Caps-1.197
================================================================-1.182
-1.158
Token Diff
Token ID10631
Feature activation+7.93e-02

Pos logit contributions
itton+5.713
pez+5.531
ocard+5.400
atts+5.076
ourage+4.947
Neg logit contributions
 Masquerade-5.512
 Goat-5.165
================================================================-5.041
-4.843
mentation-4.837
Tokenusion
Token ID4241
Feature activation+5.93e-02

Pos logit contributions
itton+0.132
pez+0.127
ocard+0.126
atts+0.118
ourage+0.117
Neg logit contributions
 Masquerade-0.131
 Goat-0.126
 Caps-0.119
================================================================-0.117
-0.114
Token.
Token ID13
Feature activation+3.17e-01

Pos logit contributions
itton+0.107
pez+0.104
ocard+0.103
atts+0.097
ourage+0.096
Neg logit contributions
 Masquerade-0.090
 Goat-0.086
 Caps-0.081
================================================================-0.079
-0.077
Token In
Token ID554
Feature activation-2.51e-02

Pos logit contributions
itton+0.573
pez+0.555
ocard+0.549
atts+0.519
ourage+0.513
Neg logit contributions
 Masquerade-0.482
 Goat-0.464
 Caps-0.434
================================================================-0.425
-0.413
Token terms
Token ID2846
Feature activation-9.86e-02

Pos logit contributions
 Masquerade+0.038
 Goat+0.037
 Caps+0.035
================================================================+0.034
+0.033
Neg logit contributions
itton-0.045
pez-0.044
ocard-0.043
atts-0.041
ourage-0.040
Token me
Token ID502
Feature activation-4.12e-02

Pos logit contributions
 Masquerade+0.027
 Goat+0.026
 Caps+0.024
================================================================+0.024
+0.023
Neg logit contributions
itton-0.031
pez-0.030
ocard-0.030
atts-0.028
ourage-0.028
Token,
Token ID11
Feature activation+3.30e-01

Pos logit contributions
 Masquerade+0.061
 Goat+0.059
 Caps+0.055
================================================================+0.054
+0.052
Neg logit contributions
itton-0.075
pez-0.073
ocard-0.072
atts-0.068
ourage-0.067
Token what
Token ID644
Feature activation+1.26e-01

Pos logit contributions
itton+0.594
pez+0.576
ocard+0.569
atts+0.538
ourage+0.531
Neg logit contributions
 Masquerade-0.502
 Goat-0.483
 Caps-0.451
================================================================-0.443
-0.431
Token is
Token ID318
Feature activation+4.71e-01

Pos logit contributions
itton+0.231
pez+0.224
ocard+0.221
atts+0.209
ourage+0.207
Neg logit contributions
 Masquerade-0.189
 Goat-0.181
 Caps-0.169
================================================================-0.166
-0.161
Token this
Token ID428
Feature activation-5.78e-01

Pos logit contributions
itton+0.828
pez+0.802
ocard+0.793
atts+0.747
ourage+0.739
Neg logit contributions
 Masquerade-0.732
 Goat-0.704
 Caps-0.659
================================================================-0.649
-0.632
Token quint
Token ID28533
Feature activation+3.47e+00

Pos logit contributions
 Masquerade+0.860
 Goat+0.823
 Caps+0.765
================================================================+0.749
+0.725
Neg logit contributions
itton-1.062
pez-1.032
ocard-1.021
atts-0.967
ourage-0.952
Tokeness
Token ID408
Feature activation+3.44e-01

Pos logit contributions
itton+3.762
pez+3.538
ocard+3.363
ourage+3.156
atts+3.043
Neg logit contributions
 Masquerade-7.635
 Goat-7.408
 Caps-7.078
================================================================-7.015
-6.888
Tokenence
Token ID594
Feature activation+6.27e-01

Pos logit contributions
itton+0.506
pez+0.489
ocard+0.482
atts+0.448
ourage+0.441
Neg logit contributions
 Masquerade-0.632
 Goat-0.612
 Caps-0.578
================================================================-0.571
-0.560
Token of
Token ID286
Feature activation-5.71e-02

Pos logit contributions
itton+1.117
pez+1.083
ocard+1.070
atts+1.010
ourage+1.000
Neg logit contributions
 Masquerade-0.957
 Goat-0.920
 Caps-0.860
================================================================-0.850
-0.827
Token dust
Token ID8977
Feature activation-4.30e-02

Pos logit contributions
 Masquerade+0.087
 Goat+0.083
 Caps+0.078
================================================================+0.077
+0.075
Neg logit contributions
itton-0.103
pez-0.099
ocard-0.098
atts-0.093
ourage-0.092
Token?
Token ID30
Feature activation+1.31e-02

Pos logit contributions
 Masquerade+0.059
 Goat+0.056
 Caps+0.052
================================================================+0.051
+0.050
Neg logit contributions
itton-0.083
pez-0.081
ocard-0.080
atts-0.076
ourage-0.075
Token.
Token ID13
Feature activation+1.98e-01

Pos logit contributions
itton+0.912
pez+0.884
ocard+0.876
atts+0.829
ourage+0.820
Neg logit contributions
 Masquerade-0.701
 Goat-0.672
 Caps-0.625
================================================================-0.615
-0.598
Token Some
Token ID2773
Feature activation+4.89e-01

Pos logit contributions
itton+0.360
pez+0.349
ocard+0.344
atts+0.325
ourage+0.321
Neg logit contributions
 Masquerade-0.301
 Goat-0.291
 Caps-0.273
================================================================-0.266
-0.258
Token of
Token ID286
Feature activation+1.71e-01

Pos logit contributions
itton+0.857
pez+0.830
ocard+0.821
atts+0.773
ourage+0.765
Neg logit contributions
 Masquerade-0.761
 Goat-0.737
 Caps-0.692
================================================================-0.676
-0.663
Token these
Token ID777
Feature activation-4.44e-01

Pos logit contributions
itton+0.305
pez+0.294
ocard+0.292
atts+0.275
ourage+0.272
Neg logit contributions
 Masquerade-0.262
 Goat-0.254
 Caps-0.238
================================================================-0.232
-0.227
Token minor
Token ID4159
Feature activation-2.44e-01

Pos logit contributions
 Masquerade+0.711
 Goat+0.693
 Caps+0.654
================================================================+0.634
+0.624
Neg logit contributions
itton-0.761
pez-0.735
ocard-0.725
atts-0.684
ourage-0.675
Token overs
Token ID10753
Feature activation+3.34e+00

Pos logit contributions
 Masquerade+0.418
 Goat+0.406
 Caps+0.385
================================================================+0.375
+0.369
Neg logit contributions
itton-0.391
pez-0.377
ocard-0.372
atts-0.349
ourage-0.344
Tokenights
Token ID2337
Feature activation+1.05e+00

Pos logit contributions
itton+2.743
pez+2.606
ocard+2.532
atts+2.272
ourage+2.191
Neg logit contributions
 Masquerade-8.173
 Goat-7.953
 Caps-7.609
================================================================-7.604
-7.506
Token consisted
Token ID19954
Feature activation+4.82e-02

Pos logit contributions
itton+1.866
pez+1.808
ocard+1.788
atts+1.687
ourage+1.668
Neg logit contributions
 Masquerade-1.604
 Goat-1.542
 Caps-1.441
================================================================-1.421
-1.383
Token of
Token ID286
Feature activation-5.54e-01

Pos logit contributions
itton+0.080
pez+0.077
ocard+0.076
atts+0.071
ourage+0.071
Neg logit contributions
 Masquerade-0.080
 Goat-0.077
 Caps-0.073
================================================================-0.071
-0.070
Token such
Token ID884
Feature activation+9.49e-02

Pos logit contributions
 Masquerade+0.886
 Goat+0.864
 Caps+0.816
================================================================+0.786
+0.771
Neg logit contributions
itton-0.949
pez-0.916
ocard-0.908
atts-0.849
ourage-0.843
Token trivial
Token ID20861
Feature activation-3.35e-01

Pos logit contributions
itton+0.174
pez+0.169
ocard+0.167
atts+0.158
ourage+0.156
Neg logit contributions
 Masquerade-0.140
 Goat-0.135
 Caps-0.126
================================================================-0.124
-0.121
Token a
Token ID257
Feature activation+5.60e-01

Pos logit contributions
itton+1.058
pez+1.025
ocard+1.012
atts+0.955
ourage+0.945
Neg logit contributions
 Masquerade-0.925
 Goat-0.891
 Caps-0.834
================================================================-0.819
-0.798
Token few
Token ID1178
Feature activation-6.31e-01

Pos logit contributions
itton+0.980
pez+0.949
ocard+0.937
atts+0.884
ourage+0.875
Neg logit contributions
 Masquerade-0.874
 Goat-0.842
 Caps-0.789
================================================================-0.775
-0.755
Token copies
Token ID9088
Feature activation+1.18e+00

Pos logit contributions
 Masquerade+0.961
 Goat+0.930
 Caps+0.872
================================================================+0.851
+0.821
Neg logit contributions
itton-1.135
pez-1.097
ocard-1.078
atts-1.024
ourage-1.019
Token of
Token ID286
Feature activation+2.44e-01

Pos logit contributions
itton+1.933
pez+1.868
ocard+1.846
atts+1.733
ourage+1.703
Neg logit contributions
 Masquerade-1.968
 Goat-1.894
 Caps-1.778
================================================================-1.762
-1.720
Token the
Token ID262
Feature activation+2.36e-01

Pos logit contributions
itton+0.448
pez+0.435
ocard+0.430
atts+0.406
ourage+0.402
Neg logit contributions
 Masquerade-0.362
 Goat-0.348
 Caps-0.324
================================================================-0.318
-0.310
Token Canon
Token ID19507
Feature activation+3.30e+00

Pos logit contributions
itton+0.437
pez+0.424
ocard+0.419
atts+0.397
ourage+0.393
Neg logit contributions
 Masquerade-0.344
 Goat-0.330
 Caps-0.308
================================================================-0.302
-0.294
Token 24
Token ID1987
Feature activation+3.30e-02

Pos logit contributions
itton+5.572
pez+5.348
ocard+5.321
atts+5.008
ourage+4.939
Neg logit contributions
 Masquerade-5.180
 Goat-4.968
 Caps-4.625
================================================================-4.616
-4.501
Token-
Token ID12
Feature activation-6.70e-02

Pos logit contributions
itton+0.064
pez+0.062
ocard+0.061
atts+0.058
ourage+0.058
Neg logit contributions
 Masquerade-0.046
 Goat-0.044
 Caps-0.041
================================================================-0.040
-0.039
Token70
Token ID2154
Feature activation+7.36e-01

Pos logit contributions
 Masquerade+0.097
 Goat+0.093
 Caps+0.087
================================================================+0.086
+0.084
Neg logit contributions
itton-0.125
ocard-0.121
pez-0.120
atts-0.114
ourage-0.113
Token Mk
Token ID24798
Feature activation-7.10e-01

Pos logit contributions
itton+1.284
pez+1.244
ocard+1.230
atts+1.159
ourage+1.145
Neg logit contributions
 Masquerade-1.153
 Goat-1.109
 Caps-1.038
================================================================-1.024
-0.998
Token II
Token ID2873
Feature activation+9.78e-02

Pos logit contributions
 Masquerade+1.035
 Goat+1.004
 Caps+0.941
================================================================+0.918
+0.906
Neg logit contributions
itton-1.305
pez-1.265
ocard-1.259
ourage-1.183
atts-1.176
Token:
Token ID25
Feature activation-3.81e-01

Pos logit contributions
itton+0.923
pez+0.894
ocard+0.884
atts+0.833
ourage+0.824
Neg logit contributions
 Masquerade-0.804
 Goat-0.773
 Caps-0.724
================================================================-0.713
-0.694
Token Size
Token ID12849
Feature activation-2.82e-01

Pos logit contributions
 Masquerade+0.524
 Goat+0.502
 Caps+0.468
================================================================+0.456
+0.443
Neg logit contributions
itton-0.739
pez-0.717
ocard-0.711
atts-0.674
ourage-0.667
Token C
Token ID327
Feature activation-9.73e-01

Pos logit contributions
 Masquerade+0.388
 Goat+0.372
 Caps+0.348
================================================================+0.336
+0.326
Neg logit contributions
itton-0.549
pez-0.532
ocard-0.529
atts-0.500
ourage-0.496
Token,
Token ID11
Feature activation-6.46e-02

Pos logit contributions
 Masquerade+1.410
 Goat+1.356
 Caps+1.271
================================================================+1.237
+1.210
Neg logit contributions
itton-1.802
pez-1.749
ocard-1.739
atts-1.641
ourage-1.623
Token Y
Token ID575
Feature activation+6.25e-01

Pos logit contributions
 Masquerade+0.103
 Goat+0.099
 Caps+0.094
================================================================+0.092
+0.090
Neg logit contributions
itton-0.111
pez-0.107
ocard-0.106
atts-0.100
ourage-0.099
TokenYR
Token ID38162
Feature activation+3.29e+00

Pos logit contributions
itton+1.113
pez+1.078
ocard+1.067
atts+1.006
ourage+0.995
Neg logit contributions
 Masquerade-0.955
 Goat-0.919
 Caps-0.859
================================================================-0.845
-0.824
Token DS
Token ID17400
Feature activation+9.26e-01

Pos logit contributions
itton+5.736
pez+5.553
ocard+5.420
atts+5.137
ourage+5.085
Neg logit contributions
 Masquerade-5.028
 Goat-4.725
================================================================-4.486
 Caps-4.405
acly-4.266
Token cent
Token ID1247
Feature activation-3.24e-01

Pos logit contributions
itton+1.669
pez+1.615
ocard+1.591
atts+1.504
ourage+1.488
Neg logit contributions
 Masquerade-1.400
 Goat-1.338
 Caps-1.243
================================================================-1.239
-1.200
Tokenering
Token ID1586
Feature activation-5.66e-01

Pos logit contributions
 Masquerade+0.372
 Goat+0.353
 Caps+0.322
================================================================+0.316
+0.304
Neg logit contributions
itton-0.700
pez-0.682
ocard-0.676
atts-0.644
ourage-0.639
Token
Token ID198
Feature activation-7.81e-03

Pos logit contributions
 Masquerade+0.838
 Goat+0.806
 Caps+0.754
================================================================+0.737
+0.720
Neg logit contributions
itton-1.036
pez-1.005
ocard-0.996
atts-0.940
ourage-0.930
Token
Token ID198
Feature activation-7.13e-02

Pos logit contributions
 Masquerade+0.011
 Goat+0.011
 Caps+0.010
================================================================+0.010
+0.009
Neg logit contributions
itton-0.015
pez-0.014
ocard-0.014
atts-0.013
ourage-0.013
Tokenback
Token ID1891
Feature activation+1.05e-01

Pos logit contributions
itton+1.231
pez+1.188
ocard+1.176
atts+1.090
ourage+1.076
Neg logit contributions
 Masquerade-1.602
 Goat-1.549
 Caps-1.467
================================================================-1.452
-1.426
Token of
Token ID286
Feature activation-1.12e-01

Pos logit contributions
itton+0.192
pez+0.184
ocard+0.178
ourage+0.169
atts+0.169
Neg logit contributions
 Masquerade-0.160
 Goat-0.159
 Caps-0.150
================================================================-0.143
-0.138
Token Notre
Token ID23382
Feature activation+1.56e+00

Pos logit contributions
 Masquerade+0.202
 Goat+0.200
 Caps+0.189
================================================================+0.185
+0.181
Neg logit contributions
itton-0.169
pez-0.163
ocard-0.157
atts-0.149
ourage-0.147
Token Dame
Token ID20377
Feature activation+1.12e+00

Pos logit contributions
itton+1.642
pez+1.594
ocard+1.532
atts+1.392
ourage+1.375
Neg logit contributions
 Masquerade-3.453
 Goat-3.351
================================================================-3.245
 Caps-3.218
acly-3.153
Token,
Token ID11
Feature activation-1.43e-01

Pos logit contributions
itton+2.121
pez+2.062
ocard+2.028
atts+1.928
ourage+1.911
Neg logit contributions
 Masquerade-1.581
 Goat-1.507
 Caps-1.405
================================================================-1.392
-1.344
Token Nightmare
Token ID23951
Feature activation+3.28e+00

Pos logit contributions
 Masquerade+0.198
 Goat+0.190
 Caps+0.176
================================================================+0.172
+0.167
Neg logit contributions
itton-0.278
pez-0.271
ocard-0.268
atts-0.254
ourage-0.251
Token on
Token ID319
Feature activation+3.42e-01

Pos logit contributions
itton+5.218
pez+4.957
ocard+4.919
atts+4.685
ourage+4.593
Neg logit contributions
 Masquerade-5.538
 Goat-5.330
 Caps-5.045
================================================================-5.044
-4.894
Token Elm
Token ID35189
Feature activation-8.78e-02

Pos logit contributions
itton+0.496
pez+0.477
ocard+0.476
atts+0.434
ourage+0.427
Neg logit contributions
 Masquerade-0.645
 Goat-0.639
 Caps-0.598
================================================================-0.579
-0.575
Token Street
Token ID3530
Feature activation+6.72e-03

Pos logit contributions
 Masquerade+0.128
 Goat+0.124
 Caps+0.114
================================================================+0.112
+0.109
Neg logit contributions
itton-0.163
pez-0.159
ocard-0.157
atts-0.148
ourage-0.146
Token,
Token ID11
Feature activation-1.91e-01

Pos logit contributions
itton+0.013
pez+0.012
ocard+0.012
atts+0.012
ourage+0.012
Neg logit contributions
 Masquerade-0.009
 Goat-0.009
 Caps-0.008
================================================================-0.008
-0.008
Token and
Token ID290
Feature activation-2.67e-01

Pos logit contributions
 Masquerade+0.266
 Goat+0.256
 Caps+0.236
================================================================+0.231
+0.224
Neg logit contributions
itton-0.370
pez-0.360
ocard-0.356
atts-0.337
ourage-0.333
Token,
Token ID11
Feature activation+4.59e-01

Pos logit contributions
 Masquerade+0.165
 Goat+0.160
 Caps+0.149
================================================================+0.147
+0.143
Neg logit contributions
itton-0.186
pez-0.179
ocard-0.178
atts-0.166
ourage-0.166
Token according
Token ID1864
Feature activation-1.55e-02

Pos logit contributions
itton+0.786
pez+0.768
ocard+0.759
atts+0.711
ourage+0.701
Neg logit contributions
 Masquerade-0.731
 Goat-0.706
 Caps-0.661
================================================================-0.647
-0.632
Token to
Token ID284
Feature activation+1.09e-01

Pos logit contributions
 Masquerade+0.020
 Goat+0.020
 Caps+0.018
================================================================+0.018
+0.017
Neg logit contributions
itton-0.031
pez-0.030
ocard-0.030
atts-0.028
ourage-0.028
Token one
Token ID530
Feature activation+3.81e-01

Pos logit contributions
itton+0.185
pez+0.182
ocard+0.180
atts+0.168
ourage+0.166
Neg logit contributions
 Masquerade-0.174
 Goat-0.168
 Caps-0.158
================================================================-0.153
-0.151
Token of
Token ID286
Feature activation+3.34e-01

Pos logit contributions
itton+0.671
pez+0.652
ocard+0.646
atts+0.607
ourage+0.601
Neg logit contributions
 Masquerade-0.589
 Goat-0.567
 Caps-0.531
================================================================-0.522
-0.508
Token Lois
Token ID42879
Feature activation+3.28e+00

Pos logit contributions
itton+0.587
pez+0.570
ocard+0.563
atts+0.530
ourage+0.525
Neg logit contributions
 Masquerade-0.519
 Goat-0.501
 Caps-0.468
================================================================-0.459
-0.449
Token G
Token ID402
Feature activation-4.33e-01

Pos logit contributions
itton+4.064
pez+3.689
ocard+3.663
atts+3.416
ourage+3.278
Neg logit contributions
 Masquerade-6.583
 Goat-6.364
================================================================-6.109
 Caps-6.046
-5.986
Token.
Token ID13
Feature activation+3.36e-01

Pos logit contributions
 Masquerade+0.582
 Goat+0.558
 Caps+0.517
================================================================+0.504
+0.491
Neg logit contributions
itton-0.844
pez-0.824
ocard-0.814
atts-0.774
ourage-0.764
Token Lerner
Token ID49750
Feature activation+2.38e+00

Pos logit contributions
itton+0.483
pez+0.462
ocard+0.454
atts+0.424
ourage+0.419
Neg logit contributions
 Masquerade-0.628
 Goat-0.606
 Caps-0.574
================================================================-0.572
-0.560
Token
Token ID447
Feature activation+1.45e-01

Pos logit contributions
itton+4.218
pez+4.088
ocard+3.983
atts+3.852
ourage+3.782
Neg logit contributions
 Masquerade-3.610
 Goat-3.448
 Caps-3.224
================================================================-3.208
-3.106
Token
Token ID247
Feature activation+3.87e-01

Pos logit contributions
itton+0.328
pez+0.320
ocard+0.318
atts+0.303
ourage+0.301
Neg logit contributions
 Masquerade-0.150
 Goat-0.143
 Caps-0.128
================================================================-0.126
-0.126
Token never
Token ID1239
Feature activation-3.14e-01

Pos logit contributions
 Masquerade+0.088
 Goat+0.084
 Caps+0.079
================================================================+0.078
+0.076
Neg logit contributions
itton-0.094
pez-0.091
ocard-0.091
atts-0.085
ourage-0.084
Token occurred
Token ID5091
Feature activation-5.85e-01

Pos logit contributions
 Masquerade+0.452
 Goat+0.434
 Caps+0.404
================================================================+0.395
+0.384
Neg logit contributions
itton-0.589
pez-0.572
ocard-0.568
atts-0.534
ourage-0.530
Token before
Token ID878
Feature activation-2.40e-01

Pos logit contributions
 Masquerade+0.789
 Goat+0.756
 Caps+0.702
================================================================+0.684
+0.666
Neg logit contributions
itton-1.149
ocard-1.102
pez-1.101
atts-1.043
ourage-1.035
Token -
Token ID532
Feature activation-3.50e-02

Pos logit contributions
 Masquerade+0.349
 Goat+0.335
 Caps+0.313
================================================================+0.307
+0.296
Neg logit contributions
itton-0.448
pez-0.431
ocard-0.430
atts-0.407
ourage-0.402
Token A
Token ID317
Feature activation-1.02e+00

Pos logit contributions
 Masquerade+0.051
 Goat+0.049
 Caps+0.045
================================================================+0.044
+0.043
Neg logit contributions
itton-0.065
pez-0.063
ocard-0.063
atts-0.059
ourage-0.059
Token Nightmare
Token ID23951
Feature activation+3.25e+00

Pos logit contributions
 Masquerade+1.557
 Goat+1.495
 Caps+1.385
================================================================+1.358
+1.320
Neg logit contributions
itton-1.806
pez-1.759
ocard-1.738
atts-1.636
ourage-1.624
Token on
Token ID319
Feature activation+6.36e-02

Pos logit contributions
itton+5.045
pez+4.754
ocard+4.752
atts+4.460
ourage+4.387
Neg logit contributions
 Masquerade-5.501
 Goat-5.348
 Caps-5.081
================================================================-5.072
-4.966
Token Elm
Token ID35189
Feature activation-3.14e-01

Pos logit contributions
itton+0.087
pez+0.084
ocard+0.083
atts+0.077
ourage+0.075
Neg logit contributions
 Masquerade-0.124
 Goat-0.121
 Caps-0.114
================================================================-0.112
-0.111
Token Street
Token ID3530
Feature activation-2.48e-01

Pos logit contributions
 Masquerade+0.456
 Goat+0.441
 Caps+0.407
================================================================+0.400
+0.389
Neg logit contributions
itton-0.583
pez-0.569
ocard-0.562
atts-0.530
ourage-0.523
Token,
Token ID11
Feature activation-1.32e-01

Pos logit contributions
 Masquerade+0.359
 Goat+0.343
 Caps+0.320
================================================================+0.313
+0.304
Neg logit contributions
itton-0.467
pez-0.452
ocard-0.449
atts-0.424
ourage-0.419
Token Friday
Token ID3217
Feature activation-5.35e-01

Pos logit contributions
 Masquerade+0.206
 Goat+0.198
 Caps+0.185
================================================================+0.181
+0.175
Neg logit contributions
itton-0.235
pez-0.227
ocard-0.226
atts-0.213
ourage-0.210
Token.
Token ID13
Feature activation+6.56e-02

Pos logit contributions
 Masquerade+0.366
 Goat+0.351
 Caps+0.326
================================================================+0.319
+0.313
Neg logit contributions
itton-0.502
pez-0.486
ocard-0.482
atts-0.455
ourage-0.452
Token The
Token ID383
Feature activation-9.77e-02

Pos logit contributions
itton+0.121
pez+0.117
ocard+0.116
atts+0.110
ourage+0.109
Neg logit contributions
 Masquerade-0.097
 Goat-0.093
 Caps-0.087
================================================================-0.085
-0.083
Token list
Token ID1351
Feature activation+1.43e-01

Pos logit contributions
 Masquerade+0.153
 Goat+0.147
 Caps+0.138
================================================================+0.135
+0.132
Neg logit contributions
itton-0.172
pez-0.166
ocard-0.164
atts-0.155
ourage-0.153
Token of
Token ID286
Feature activation-1.42e-01

Pos logit contributions
itton+0.251
pez+0.244
ocard+0.240
atts+0.226
ourage+0.224
Neg logit contributions
 Masquerade-0.222
 Goat-0.215
 Caps-0.201
================================================================-0.198
-0.193
Token egregious
Token ID34372
Feature activation+7.15e-01

Pos logit contributions
 Masquerade+0.221
 Goat+0.214
 Caps+0.201
================================================================+0.196
+0.193
Neg logit contributions
itton-0.248
pez-0.240
ocard-0.238
atts-0.223
ourage-0.221
Token overs
Token ID10753
Feature activation+3.22e+00

Pos logit contributions
itton+1.176
pez+1.137
ocard+1.123
atts+1.055
ourage+1.042
Neg logit contributions
 Masquerade-1.190
 Goat-1.146
 Caps-1.077
================================================================-1.065
-1.038
Tokenights
Token ID2337
Feature activation+9.48e-01

Pos logit contributions
itton+2.311
pez+2.138
ocard+2.077
atts+1.834
ourage+1.747
Neg logit contributions
 Masquerade-8.277
 Goat-8.116
 Caps-7.760
================================================================-7.725
-7.626
Token by
Token ID416
Feature activation+3.63e-01

Pos logit contributions
itton+1.690
pez+1.638
ocard+1.620
atts+1.530
ourage+1.513
Neg logit contributions
 Masquerade-1.447
 Goat-1.389
 Caps-1.298
================================================================-1.281
-1.247
Token the
Token ID262
Feature activation-9.97e-02

Pos logit contributions
itton+0.636
pez+0.616
ocard+0.609
atts+0.574
ourage+0.567
Neg logit contributions
 Masquerade-0.568
 Goat-0.548
 Caps-0.513
================================================================-0.504
-0.492
Token voters
Token ID4446
Feature activation-2.95e-01

Pos logit contributions
 Masquerade+0.156
 Goat+0.150
 Caps+0.141
================================================================+0.137
+0.134
Neg logit contributions
itton-0.176
pez-0.170
ocard-0.168
atts-0.158
ourage-0.157
Token that
Token ID326
Feature activation+1.95e-01

Pos logit contributions
 Masquerade+0.434
 Goat+0.417
 Caps+0.389
================================================================+0.383
+0.372
Neg logit contributions
itton-0.543
pez-0.527
ocard-0.521
atts-0.492
ourage-0.486
Token-
Token ID12
Feature activation+1.00e-01

Pos logit contributions
itton+2.092
pez+2.019
ocard+1.991
atts+1.862
ourage+1.838
Neg logit contributions
 Masquerade-2.337
 Goat-2.258
 Caps-2.131
================================================================-2.104
-2.056
Tokenpres
Token ID18302
Feature activation+1.23e+00

Pos logit contributions
itton+0.163
pez+0.157
ocard+0.154
atts+0.145
ourage+0.142
Neg logit contributions
 Masquerade-0.167
 Goat-0.160
 Caps-0.152
================================================================-0.152
-0.147
Tokencript
Token ID6519
Feature activation-4.72e-01

Pos logit contributions
itton+1.531
pez+1.460
ocard+1.433
atts+1.319
ourage+1.292
Neg logit contributions
 Masquerade-2.556
 Goat-2.486
 Caps-2.368
================================================================-2.340
-2.301
Tokenive
Token ID425
Feature activation-8.38e-01

Pos logit contributions
 Masquerade+0.578
 Goat+0.551
 Caps+0.508
================================================================+0.497
+0.481
Neg logit contributions
itton-0.982
pez-0.956
ocard-0.948
atts-0.901
ourage-0.893
Token and
Token ID290
Feature activation-1.66e-01

Pos logit contributions
 Masquerade+1.503
 Goat+1.455
 Caps+1.396
================================================================+1.347
mentation+1.321
Neg logit contributions
itton-1.269
pez-1.217
ocard-1.187
atts-1.110
ourage-1.099
Token overs
Token ID10753
Feature activation+3.19e+00

Pos logit contributions
 Masquerade+0.278
 Goat+0.269
 Caps+0.255
================================================================+0.250
+0.245
Neg logit contributions
itton-0.271
pez-0.261
ocard-0.256
atts-0.241
ourage-0.237
Tokenimpl
Token ID23928
Feature activation+1.44e+00

Pos logit contributions
itton+4.837
pez+4.701
ocard+4.621
atts+4.343
ourage+4.263
Neg logit contributions
 Masquerade-5.655
 Goat-5.484
 Caps-5.157
================================================================-5.102
-4.998
Tokenified
Token ID1431
Feature activation-6.59e-01

Pos logit contributions
itton+1.859
pez+1.786
ocard+1.752
atts+1.618
ourage+1.603
Neg logit contributions
 Masquerade-2.904
 Goat-2.826
 Caps-2.668
================================================================-2.637
-2.586
Token recommendations
Token ID10763
Feature activation-1.00e-01

Pos logit contributions
 Masquerade+1.189
 Goat+1.149
 Caps+1.100
================================================================+1.063
+1.041
Neg logit contributions
itton-1.000
pez-0.956
ocard-0.936
atts-0.873
ourage-0.867
Token that
Token ID326
Feature activation+9.43e-02

Pos logit contributions
 Masquerade+0.139
 Goat+0.134
 Caps+0.124
================================================================+0.122
+0.118
Neg logit contributions
itton-0.193
pez-0.187
ocard-0.185
atts-0.175
ourage-0.174
Token force
Token ID2700
Feature activation-1.31e+00

Pos logit contributions
itton+0.169
pez+0.163
ocard+0.160
atts+0.152
ourage+0.149
Neg logit contributions
 Masquerade-0.145
 Goat-0.139
 Caps-0.131
================================================================-0.127
-0.124
Token population
Token ID3265
Feature activation-9.65e-01

Pos logit contributions
 Masquerade+0.765
 Goat+0.737
 Caps+0.696
================================================================+0.680
+0.659
Neg logit contributions
itton-0.866
pez-0.835
ocard-0.822
atts-0.774
ourage-0.772
Token becomes
Token ID4329
Feature activation-9.93e-01

Pos logit contributions
 Masquerade+1.156
 Goat+1.098
 Caps+1.034
================================================================+0.990
mentation+0.956
Neg logit contributions
itton-2.039
pez-1.980
ocard-1.955
ourage-1.858
atts-1.845
Token older
Token ID4697
Feature activation-4.37e-01

Pos logit contributions
 Masquerade+1.247
 Goat+1.187
 Caps+1.100
================================================================+1.070
+1.046
Neg logit contributions
itton-2.045
pez-1.994
ocard-1.961
ourage-1.855
atts-1.853
Token and
Token ID290
Feature activation-2.25e-01

Pos logit contributions
 Masquerade+0.590
 Goat+0.565
 Caps+0.524
================================================================+0.513
+0.499
Neg logit contributions
itton-0.856
pez-0.829
ocard-0.823
atts-0.778
ourage-0.772
Token more
Token ID517
Feature activation+8.54e-02

Pos logit contributions
 Masquerade+0.322
 Goat+0.308
 Caps+0.287
================================================================+0.282
+0.273
Neg logit contributions
itton-0.426
pez-0.413
ocard-0.408
atts-0.385
ourage-0.383
Token ethn
Token ID33961
Feature activation+3.17e+00

Pos logit contributions
itton+0.150
pez+0.145
ocard+0.143
atts+0.135
ourage+0.133
Neg logit contributions
 Masquerade-0.134
 Goat-0.128
 Caps-0.120
================================================================-0.119
-0.116
Tokenically
Token ID1146
Feature activation+2.98e-01

Pos logit contributions
itton+2.434
ocard+2.396
pez+2.327
ourage+1.951
atts+1.947
Neg logit contributions
 Masquerade-8.050
 Goat-7.813
 Caps-7.455
================================================================-7.338
-7.217
Token diverse
Token ID10084
Feature activation-2.56e-02

Pos logit contributions
itton+0.543
pez+0.526
ocard+0.520
atts+0.492
ourage+0.486
Neg logit contributions
 Masquerade-0.445
 Goat-0.427
 Caps-0.399
================================================================-0.393
-0.382
Token,
Token ID11
Feature activation+3.03e-01

Pos logit contributions
 Masquerade+0.037
 Goat+0.036
 Caps+0.034
================================================================+0.033
+0.032
Neg logit contributions
itton-0.047
pez-0.046
ocard-0.045
atts-0.043
ourage-0.042
Token the
Token ID262
Feature activation+8.74e-02

Pos logit contributions
itton+0.532
pez+0.515
ocard+0.509
atts+0.480
ourage+0.474
Neg logit contributions
 Masquerade-0.472
 Goat-0.455
 Caps-0.426
================================================================-0.419
-0.409
Token additional
Token ID3224
Feature activation+2.75e-02

Pos logit contributions
itton+0.148
pez+0.144
ocard+0.141
atts+0.133
ourage+0.131
Neg logit contributions
 Masquerade-0.142
 Goat-0.137
 Caps-0.129
================================================================-0.126
-0.123
TokenPo
Token ID18833
Feature activation+1.33e+00

Pos logit contributions
 Masquerade+1.094
 Goat+1.042
 Caps+0.966
================================================================+0.948
+0.891
Neg logit contributions
itton-1.885
pez-1.864
ocard-1.807
ourage-1.725
atts-1.698
Token.
Token ID13
Feature activation+1.31e-01

Pos logit contributions
itton+2.549
pez+2.473
ocard+2.449
atts+2.329
ourage+2.296
Neg logit contributions
 Masquerade-1.844
 Goat-1.764
 Caps-1.634
================================================================-1.616
-1.565
Token
Token ID198
Feature activation+1.70e-01

Pos logit contributions
itton+0.239
pez+0.232
ocard+0.229
atts+0.217
ourage+0.214
Neg logit contributions
 Masquerade-0.197
 Goat-0.189
 Caps-0.177
================================================================-0.173
-0.169
Token
Token ID198
Feature activation+9.22e-02

Pos logit contributions
itton+0.321
pez+0.311
ocard+0.308
atts+0.291
ourage+0.288
Neg logit contributions
 Masquerade-0.245
 Goat-0.236
 Caps-0.221
================================================================-0.218
-0.209
TokenBusiness
Token ID24749
Feature activation-1.84e-01

Pos logit contributions
itton+0.161
pez+0.155
ocard+0.153
atts+0.144
ourage+0.143
Neg logit contributions
 Masquerade-0.145
 Goat-0.140
 Caps-0.132
================================================================-0.131
-0.127
Token Insider
Token ID22167
Feature activation+3.14e+00

Pos logit contributions
 Masquerade+0.345
 Goat+0.335
 Caps+0.319
================================================================+0.315
+0.308
Neg logit contributions
itton-0.262
pez-0.254
ocard-0.251
atts-0.231
ourage-0.228
Token explains
Token ID6688
Feature activation-6.72e-01

Pos logit contributions
itton+4.995
pez+4.840
ocard+4.777
atts+4.509
ourage+4.454
Neg logit contributions
 Masquerade-5.185
 Goat-4.966
================================================================-4.679
 Caps-4.640
-4.591
Token:
Token ID25
Feature activation-2.59e-02

Pos logit contributions
 Masquerade+0.965
 Goat+0.926
 Caps+0.866
================================================================+0.843
+0.824
Neg logit contributions
itton-1.261
pez-1.220
ocard-1.209
atts-1.141
ourage-1.129
Token "
Token ID366
Feature activation+5.12e-01

Pos logit contributions
 Masquerade+0.038
 Goat+0.037
 Caps+0.035
================================================================+0.034
+0.033
Neg logit contributions
itton-0.047
pez-0.046
ocard-0.045
atts-0.043
ourage-0.042
TokenEss
Token ID29508
Feature activation+2.59e+00

Pos logit contributions
itton+0.841
pez+0.813
ocard+0.804
atts+0.753
ourage+0.744
Neg logit contributions
 Masquerade-0.855
 Goat-0.825
 Caps-0.777
================================================================-0.767
-0.748
Tokenentially
Token ID3746
Feature activation+7.55e-03

Pos logit contributions
itton+3.235
pez+3.065
ocard+2.997
atts+2.763
ourage+2.755
Neg logit contributions
 Masquerade-5.306
 Goat-5.121
 Caps-4.836
================================================================-4.814
-4.666
Token country
Token ID1499
Feature activation-6.09e-01

Pos logit contributions
 Masquerade+0.395
 Goat+0.382
 Caps+0.362
================================================================+0.358
+0.350
Neg logit contributions
itton-0.315
pez-0.303
ocard-0.299
atts-0.278
ourage-0.274
Token,
Token ID11
Feature activation+1.83e-01

Pos logit contributions
 Masquerade+0.868
 Goat+0.836
 Caps+0.778
================================================================+0.764
+0.742
Neg logit contributions
itton-1.144
pez-1.107
ocard-1.104
atts-1.042
ourage-1.025
Token there
Token ID612
Feature activation-9.13e-01

Pos logit contributions
itton+0.339
pez+0.329
ocard+0.326
atts+0.308
ourage+0.304
Neg logit contributions
 Masquerade-0.268
 Goat-0.257
 Caps-0.240
================================================================-0.236
-0.229
Token is
Token ID318
Feature activation-7.14e-02

Pos logit contributions
 Masquerade+1.236
 Goat+1.195
 Caps+1.109
================================================================+1.080
mentation+1.057
Neg logit contributions
itton-1.774
pez-1.716
ocard-1.700
atts-1.612
ourage-1.589
Token some
Token ID617
Feature activation-1.09e-01

Pos logit contributions
 Masquerade+0.113
 Goat+0.109
 Caps+0.102
================================================================+0.100
+0.098
Neg logit contributions
itton-0.124
pez-0.120
ocard-0.119
atts-0.111
ourage-0.110
Token une
Token ID17809
Feature activation+3.08e+00

Pos logit contributions
 Masquerade+0.169
 Goat+0.162
 Caps+0.152
================================================================+0.149
+0.145
Neg logit contributions
itton-0.194
pez-0.188
ocard-0.186
atts-0.175
ourage-0.173
Tokenase
Token ID589
Feature activation-4.53e-01

Pos logit contributions
itton+4.329
pez+4.155
ocard+4.073
atts+3.841
ourage+3.828
Neg logit contributions
 Masquerade-5.744
 Goat-5.646
 Caps-5.300
-5.183
================================================================-5.173
Token about
Token ID546
Feature activation+1.02e-01

Pos logit contributions
 Masquerade+0.758
 Goat+0.731
 Caps+0.688
================================================================+0.676
+0.654
Neg logit contributions
itton-0.748
pez-0.717
ocard-0.711
atts-0.666
ourage-0.653
Token their
Token ID511
Feature activation+3.98e-01

Pos logit contributions
itton+0.187
pez+0.181
ocard+0.180
atts+0.170
ourage+0.168
Neg logit contributions
 Masquerade-0.152
 Goat-0.146
 Caps-0.137
================================================================-0.134
-0.131
Token ambition
Token ID20505
Feature activation-2.77e-01

Pos logit contributions
itton+0.661
pez+0.640
ocard+0.631
atts+0.592
ourage+0.585
Neg logit contributions
 Masquerade-0.659
 Goat-0.634
 Caps-0.597
================================================================-0.587
-0.572
Token to
Token ID284
Feature activation-3.22e-01

Pos logit contributions
 Masquerade+0.385
 Goat+0.368
 Caps+0.342
================================================================+0.336
+0.325
Neg logit contributions
itton-0.534
pez-0.517
ocard-0.513
atts-0.485
ourage-0.480
Token prescribed
Token ID14798
Feature activation+1.68e+00

Pos logit contributions
itton+2.953
pez+2.930
ocard+2.820
atts+2.611
ourage+2.570
Neg logit contributions
 Masquerade-4.306
 Goat-4.152
================================================================-3.938
 Caps-3.909
-3.837
Token therapeutic
Token ID21546
Feature activation+5.46e-01

Pos logit contributions
itton+2.519
pez+2.449
ocard+2.418
atts+2.234
ourage+2.223
Neg logit contributions
 Masquerade-3.000
 Goat-2.889
================================================================-2.718
 Caps-2.714
-2.660
Token SS
Token ID6723
Feature activation+1.99e+00

Pos logit contributions
itton+0.814
pez+0.781
ocard+0.772
atts+0.720
ourage+0.710
Neg logit contributions
 Masquerade-0.996
 Goat-0.965
 Caps-0.915
================================================================-0.901
-0.880
TokenRI
Token ID7112
Feature activation-6.20e-01

Pos logit contributions
itton+3.843
pez+3.743
ocard+3.704
atts+3.480
ourage+3.455
Neg logit contributions
 Masquerade-2.759
 Goat-2.597
 Caps-2.407
================================================================-2.394
-2.289
Token or
Token ID393
Feature activation+3.69e-01

Pos logit contributions
 Masquerade+0.860
 Goat+0.829
 Caps+0.779
================================================================+0.756
+0.733
Neg logit contributions
itton-1.192
pez-1.146
ocard-1.140
atts-1.085
ourage-1.069
Token benz
Token ID39601
Feature activation+3.07e+00

Pos logit contributions
itton+0.583
pez+0.560
ocard+0.553
atts+0.520
ourage+0.511
Neg logit contributions
 Masquerade-0.641
 Goat-0.621
 Caps-0.586
================================================================-0.576
-0.563
Tokenod
Token ID375
Feature activation+3.25e-01

Pos logit contributions
itton+5.688
pez+5.640
ocard+5.608
atts+5.209
ourage+5.208
Neg logit contributions
 Masquerade-4.435
 Goat-4.260
 Caps-3.936
================================================================-3.839
-3.767
Tokeniazep
Token ID48826
Feature activation+9.61e-01

Pos logit contributions
itton+0.312
pez+0.291
ocard+0.286
atts+0.258
ourage+0.247
Neg logit contributions
 Masquerade-0.756
 Goat-0.741
 Caps-0.711
================================================================-0.706
-0.691
Tokenine
Token ID500
Feature activation+5.52e-01

Pos logit contributions
itton+1.620
pez+1.569
ocard+1.549
atts+1.450
ourage+1.439
Neg logit contributions
 Masquerade-1.567
 Goat-1.507
 Caps-1.411
================================================================-1.397
-1.361
Token.
Token ID13
Feature activation+2.53e-01

Pos logit contributions
itton+0.992
pez+0.960
ocard+0.950
atts+0.898
ourage+0.887
Neg logit contributions
 Masquerade-0.837
 Goat-0.805
 Caps-0.753
================================================================-0.740
-0.720
Token
Token ID198
Feature activation+1.04e-01

Pos logit contributions
itton+0.491
pez+0.477
ocard+0.472
atts+0.448
ourage+0.443
Neg logit contributions
 Masquerade-0.346
 Goat-0.331
 Caps-0.307
================================================================-0.302
-0.293
Tokenically
Token ID1146
Feature activation-5.09e-02

Pos logit contributions
itton+1.739
pez+1.622
ocard+1.580
atts+1.366
ourage+1.320
Neg logit contributions
 Masquerade-5.531
 Goat-5.389
 Caps-5.159
================================================================-5.125
-5.052
Token one
Token ID530
Feature activation-1.76e-01

Pos logit contributions
 Masquerade+0.081
 Goat+0.078
 Caps+0.073
================================================================+0.072
+0.070
Neg logit contributions
itton-0.088
pez-0.085
ocard-0.084
atts-0.079
ourage-0.078
Token of
Token ID286
Feature activation+1.60e-01

Pos logit contributions
 Masquerade+0.284
 Goat+0.274
 Caps+0.257
================================================================+0.253
+0.247
Neg logit contributions
itton-0.298
pez-0.288
ocard-0.285
atts-0.268
ourage-0.265
Token the
Token ID262
Feature activation+1.53e-01

Pos logit contributions
itton+0.272
pez+0.263
ocard+0.260
atts+0.244
ourage+0.241
Neg logit contributions
 Masquerade-0.259
 Goat-0.250
 Caps-0.234
================================================================-0.231
-0.226
Token most
Token ID749
Feature activation+1.44e+00

Pos logit contributions
itton+0.250
pez+0.241
ocard+0.237
atts+0.222
ourage+0.221
Neg logit contributions
 Masquerade-0.257
 Goat-0.249
 Caps-0.235
================================================================-0.230
-0.225
Token inh
Token ID25783
Feature activation+3.07e+00

Pos logit contributions
itton+2.177
pez+2.099
ocard+2.081
atts+1.937
ourage+1.912
Neg logit contributions
 Masquerade-2.590
 Goat-2.498
 Caps-2.360
================================================================-2.335
-2.283
Tokenosp
Token ID2117
Feature activation-5.53e-01

Pos logit contributions
itton+3.192
ocard+3.015
pez+3.006
atts+2.695
ourage+2.640
Neg logit contributions
 Masquerade-7.001
 Goat-6.769
 Caps-6.443
================================================================-6.347
-6.323
Tokenitable
Token ID4674
Feature activation+1.57e-01

Pos logit contributions
 Masquerade+1.210
 Goat+1.189
 Caps+1.142
================================================================+1.135
+1.115
Neg logit contributions
itton-0.574
ocard-0.554
pez-0.546
atts-0.487
 horm-0.472
Token and
Token ID290
Feature activation-6.07e-02

Pos logit contributions
itton+0.266
pez+0.256
ocard+0.253
atts+0.238
ourage+0.237
Neg logit contributions
 Masquerade-0.254
 Goat-0.246
 Caps-0.232
================================================================-0.227
-0.221
Token challenging
Token ID9389
Feature activation+8.82e-01

Pos logit contributions
 Masquerade+0.105
 Goat+0.102
 Caps+0.097
================================================================+0.095
+0.093
Neg logit contributions
itton-0.096
pez-0.093
ocard-0.091
atts-0.085
ourage-0.084
Token places
Token ID4113
Feature activation+1.25e-01

Pos logit contributions
itton+1.472
pez+1.422
ocard+1.406
atts+1.321
ourage+1.305
Neg logit contributions
 Masquerade-1.448
 Goat-1.397
 Caps-1.312
================================================================-1.294
-1.262
Token a
Token ID257
Feature activation+3.17e-01

Pos logit contributions
 Masquerade+0.039
 Goat+0.038
 Caps+0.035
================================================================+0.035
+0.034
Neg logit contributions
itton-0.045
pez-0.044
ocard-0.044
atts-0.041
ourage-0.041
Token way
Token ID835
Feature activation+1.35e-01

Pos logit contributions
itton+0.550
pez+0.532
ocard+0.526
atts+0.495
ourage+0.489
Neg logit contributions
 Masquerade-0.501
 Goat-0.482
 Caps-0.453
================================================================-0.445
-0.434
Token,
Token ID11
Feature activation+2.82e-01

Pos logit contributions
itton+0.249
pez+0.241
ocard+0.239
atts+0.226
ourage+0.223
Neg logit contributions
 Masquerade-0.197
 Goat-0.189
 Caps-0.176
================================================================-0.173
-0.169
Token Julia
Token ID22300
Feature activation-1.39e+00

Pos logit contributions
itton+0.496
pez+0.480
ocard+0.475
atts+0.447
ourage+0.442
Neg logit contributions
 Masquerade-0.441
 Goat-0.424
 Caps-0.398
================================================================-0.390
-0.381
Token H
Token ID367
Feature activation-2.16e-01

Pos logit contributions
 Masquerade+2.155
 Goat+2.074
 Caps+1.942
================================================================+1.894
+1.866
Neg logit contributions
itton-2.433
pez-2.355
ocard-2.351
atts-2.193
ourage-2.183
Tokenahn
Token ID15386
Feature activation+3.03e+00

Pos logit contributions
 Masquerade+0.368
 Goat+0.356
================================================================+0.336
 Caps+0.336
mentation+0.324
Neg logit contributions
itton-0.338
pez-0.328
ocard-0.325
atts-0.302
ourage-0.297
Token is
Token ID318
Feature activation+1.63e-01

Pos logit contributions
itton+5.249
pez+5.150
ocard+5.002
atts+4.769
ourage+4.681
Neg logit contributions
 Masquerade-4.522
 Goat-4.401
 Caps-4.052
================================================================-4.030
-3.929
Token the
Token ID262
Feature activation-3.11e-02

Pos logit contributions
itton+0.280
pez+0.271
ocard+0.267
atts+0.251
ourage+0.249
Neg logit contributions
 Masquerade-0.262
 Goat-0.252
 Caps-0.237
================================================================-0.233
-0.227
Token Patty
Token ID42417
Feature activation-4.99e-01

Pos logit contributions
 Masquerade+0.048
 Goat+0.046
 Caps+0.043
================================================================+0.042
+0.041
Neg logit contributions
itton-0.055
pez-0.054
ocard-0.053
atts-0.050
ourage-0.049
Token Hear
Token ID26319
Feature activation+9.13e-02

Pos logit contributions
 Masquerade+0.722
 Goat+0.702
 Caps+0.650
================================================================+0.631
+0.619
Neg logit contributions
itton-0.926
pez-0.899
ocard-0.894
atts-0.839
ourage-0.836
Tokenst
Token ID301
Feature activation+1.73e-01

Pos logit contributions
itton+0.135
pez+0.130
ocard+0.128
atts+0.119
ourage+0.118
Neg logit contributions
 Masquerade-0.167
 Goat-0.162
 Caps-0.153
================================================================-0.151
-0.148
Token,
Token ID11
Feature activation-9.83e-02

Pos logit contributions
 Masquerade+0.930
 Goat+0.893
 Caps+0.833
================================================================+0.815
+0.793
Neg logit contributions
itton-1.135
pez-1.102
ocard-1.092
atts-1.027
ourage-1.015
Token attended
Token ID9141
Feature activation-2.63e-01

Pos logit contributions
 Masquerade+0.150
 Goat+0.144
 Caps+0.135
================================================================+0.132
+0.128
Neg logit contributions
itton-0.176
pez-0.172
ocard-0.170
atts-0.159
ourage-0.158
Token by
Token ID416
Feature activation-5.75e-02

Pos logit contributions
 Masquerade+0.437
 Goat+0.421
 Caps+0.396
================================================================+0.389
+0.381
Neg logit contributions
itton-0.434
pez-0.418
ocard-0.416
atts-0.390
ourage-0.385
Token Julia
Token ID22300
Feature activation-1.69e+00

Pos logit contributions
 Masquerade+0.093
 Goat+0.089
 Caps+0.084
================================================================+0.083
+0.081
Neg logit contributions
itton-0.098
pez-0.095
ocard-0.094
atts-0.088
ourage-0.087
Token H
Token ID367
Feature activation-4.92e-01

Pos logit contributions
 Masquerade+2.361
 Goat+2.282
 Caps+2.127
================================================================+2.022
+2.009
Neg logit contributions
itton-3.225
pez-3.129
ocard-3.083
atts-2.929
ourage-2.910
Tokenahn
Token ID15386
Feature activation+3.02e+00

Pos logit contributions
 Masquerade+0.858
 Goat+0.830
 Caps+0.783
================================================================+0.775
+0.752
Neg logit contributions
itton-0.761
pez-0.736
ocard-0.725
atts-0.679
ourage-0.669
Token,
Token ID11
Feature activation-2.16e-01

Pos logit contributions
itton+5.348
pez+5.204
ocard+5.064
atts+4.857
ourage+4.777
Neg logit contributions
 Masquerade-4.485
 Goat-4.266
================================================================-3.969
 Caps-3.947
-3.826
Token costs
Token ID3484
Feature activation-7.64e-01

Pos logit contributions
 Masquerade+0.325
 Goat+0.313
 Caps+0.293
================================================================+0.287
+0.280
Neg logit contributions
itton-0.392
pez-0.378
ocard-0.376
atts-0.354
ourage-0.350
Token about
Token ID546
Feature activation+1.55e-01

Pos logit contributions
 Masquerade+1.141
 Goat+1.083
 Caps+1.019
================================================================+0.990
+0.970
Neg logit contributions
itton-1.401
pez-1.354
ocard-1.346
atts-1.269
ourage-1.258
Token $
Token ID720
Feature activation+3.98e-01

Pos logit contributions
itton+0.271
pez+0.263
ocard+0.260
atts+0.245
ourage+0.242
Neg logit contributions
 Masquerade-0.241
 Goat-0.232
 Caps-0.217
================================================================-0.214
-0.209
Token40
Token ID1821
Feature activation+4.60e-01

Pos logit contributions
itton+0.738
pez+0.716
ocard+0.709
atts+0.668
ourage+0.662
Neg logit contributions
 Masquerade-0.582
 Goat-0.559
 Caps-0.523
================================================================-0.516
-0.500
Token objectives
Token ID15221
Feature activation+8.49e-01

Pos logit contributions
itton+0.609
pez+0.590
ocard+0.583
atts+0.551
ourage+0.544
Neg logit contributions
 Masquerade-0.532
 Goat-0.514
 Caps-0.482
================================================================-0.471
-0.458
Token,
Token ID11
Feature activation+2.93e-01

Pos logit contributions
itton+1.602
pez+1.555
ocard+1.539
atts+1.456
ourage+1.441
Neg logit contributions
 Masquerade-1.208
 Goat-1.158
 Caps-1.077
================================================================-1.060
-1.030
Token but
Token ID475
Feature activation+8.41e-01

Pos logit contributions
itton+0.569
pez+0.556
ocard+0.548
atts+0.520
ourage+0.514
Neg logit contributions
 Masquerade-0.403
 Goat-0.388
 Caps-0.360
================================================================-0.353
-0.342
Token,
Token ID11
Feature activation-7.09e-02

Pos logit contributions
itton+1.510
pez+1.464
ocard+1.447
atts+1.369
ourage+1.350
Neg logit contributions
 Masquerade-1.281
 Goat-1.234
 Caps-1.155
================================================================-1.132
-1.103
Token like
Token ID588
Feature activation-3.11e-01

Pos logit contributions
 Masquerade+0.110
 Goat+0.107
 Caps+0.100
================================================================+0.097
+0.095
Neg logit contributions
itton-0.126
pez-0.121
ocard-0.120
atts-0.114
ourage-0.112
Token Sid
Token ID15686
Feature activation-3.55e+00

Pos logit contributions
 Masquerade+0.461
 Goat+0.444
 Caps+0.418
================================================================+0.401
+0.392
Neg logit contributions
itton-0.575
pez-0.558
ocard-0.552
atts-0.524
ourage-0.515
Tokenew
Token ID413
Feature activation+8.13e-01

Pos logit contributions
 Masquerade+4.255
 Goat+4.091
 Caps+3.707
================================================================+3.608
+3.582
Neg logit contributions
itton-7.237
pez-7.058
ocard-6.850
atts-6.614
ourage-6.586
Tokeninder
Token ID5540
Feature activation-2.49e-01

Pos logit contributions
itton+1.687
pez+1.644
ocard+1.626
atts+1.561
ourage+1.538
Neg logit contributions
 Masquerade-1.005
 Goat-0.956
 Caps-0.883
================================================================-0.864
-0.839
Token,
Token ID11
Feature activation-2.01e-01

Pos logit contributions
 Masquerade+0.359
 Goat+0.345
 Caps+0.322
================================================================+0.313
+0.304
Neg logit contributions
itton-0.468
pez-0.454
ocard-0.450
atts-0.424
ourage-0.421
Token slippery
Token ID32911
Feature activation-8.56e-01

Pos logit contributions
 Masquerade+0.292
 Goat+0.281
 Caps+0.264
================================================================+0.256
+0.249
Neg logit contributions
itton-0.375
pez-0.363
ocard-0.359
atts-0.340
ourage-0.336
Token terrain
Token ID15510
Feature activation-1.26e-01

Pos logit contributions
 Masquerade+1.353
 Goat+1.308
 Caps+1.228
================================================================+1.198
+1.162
Neg logit contributions
itton-1.489
pez-1.441
ocard-1.424
atts-1.344
ourage-1.327
Tokenfish
Token ID11084
Feature activation+5.21e-01

Pos logit contributions
itton+1.049
pez+1.023
ocard+1.013
atts+0.969
ourage+0.961
Neg logit contributions
 Masquerade-0.470
 Goat-0.441
 Caps-0.398
================================================================-0.389
-0.373
Token
Token ID447
Feature activation-1.43e-01

Pos logit contributions
itton+0.926
pez+0.897
ocard+0.888
atts+0.837
ourage+0.828
Neg logit contributions
 Masquerade-0.799
 Goat-0.768
 Caps-0.718
================================================================-0.708
-0.689
Token
Token ID251
Feature activation+2.55e-01

Pos logit contributions
 Masquerade+0.153
 Goat+0.144
 Caps+0.131
================================================================+0.128
+0.124
Neg logit contributions
itton-0.322
pez-0.314
ocard-0.312
atts-0.298
ourage-0.295
Token debuted
Token ID26376
Feature activation+1.93e-01

Pos logit contributions
itton+0.440
pez+0.425
ocard+0.420
atts+0.395
ourage+0.392
Neg logit contributions
 Masquerade-0.407
 Goat-0.392
 Caps-0.367
================================================================-0.361
-0.353
Token at
Token ID379
Feature activation-9.26e-01

Pos logit contributions
itton+0.331
pez+0.320
ocard+0.317
atts+0.298
ourage+0.295
Neg logit contributions
 Masquerade-0.308
 Goat-0.297
 Caps-0.278
================================================================-0.274
-0.267
Token Sund
Token ID3309
Feature activation-3.54e+00

Pos logit contributions
 Masquerade+1.474
 Goat+1.419
 Caps+1.342
================================================================+1.297
+1.265
Neg logit contributions
itton-1.608
pez-1.557
ocard-1.535
atts-1.446
ourage-1.435
Tokenance
Token ID590
Feature activation-5.39e-01

Pos logit contributions
 Masquerade+5.850
 Goat+5.544
 Caps+5.338
================================================================+5.149
mentation+5.090
Neg logit contributions
pez-5.686
itton-5.659
ocard-5.295
 horm-5.019
atts-4.957
Token,
Token ID11
Feature activation-2.11e-01

Pos logit contributions
 Masquerade+0.805
 Goat+0.775
 Caps+0.727
================================================================+0.707
+0.689
Neg logit contributions
itton-0.986
pez-0.956
ocard-0.947
atts-0.890
ourage-0.883
Token was
Token ID373
Feature activation-1.77e-01

Pos logit contributions
 Masquerade+0.334
 Goat+0.322
 Caps+0.303
================================================================+0.295
+0.289
Neg logit contributions
itton-0.366
pez-0.354
ocard-0.351
atts-0.330
ourage-0.327
Token acquired
Token ID9477
Feature activation-6.30e-01

Pos logit contributions
 Masquerade+0.280
 Goat+0.271
 Caps+0.255
================================================================+0.248
+0.243
Neg logit contributions
itton-0.306
pez-0.296
ocard-0.293
atts-0.275
ourage-0.273
Token by
Token ID416
Feature activation-1.43e-01

Pos logit contributions
 Masquerade+1.029
 Goat+0.996
 Caps+0.933
================================================================+0.913
+0.892
Neg logit contributions
itton-1.058
pez-1.021
ocard-1.011
atts-0.952
ourage-0.940
Token the
Token ID262
Feature activation+8.74e-02

Pos logit contributions
 Masquerade+0.830
 Goat+0.804
 Caps+0.750
================================================================+0.736
+0.719
Neg logit contributions
itton-0.950
pez-0.921
ocard-0.909
atts-0.857
ourage-0.849
Token entrance
Token ID10384
Feature activation+1.47e-01

Pos logit contributions
itton+0.152
pez+0.147
ocard+0.145
atts+0.137
ourage+0.135
Neg logit contributions
 Masquerade-0.138
 Goat-0.133
 Caps-0.125
================================================================-0.122
-0.120
Token to
Token ID284
Feature activation-1.56e-01

Pos logit contributions
itton+0.274
pez+0.266
ocard+0.263
atts+0.249
ourage+0.246
Neg logit contributions
 Masquerade-0.212
 Goat-0.203
 Caps-0.189
================================================================-0.186
-0.181
Token the
Token ID262
Feature activation+7.44e-02

Pos logit contributions
 Masquerade+0.229
 Goat+0.221
 Caps+0.205
================================================================+0.201
+0.196
Neg logit contributions
itton-0.287
pez-0.278
ocard-0.275
atts-0.260
ourage-0.257
Token Bangladesh
Token ID19483
Feature activation+1.24e+00

Pos logit contributions
itton+0.177
pez+0.173
ocard+0.172
atts+0.164
ourage+0.163
Neg logit contributions
 Masquerade-0.069
 Goat-0.065
 Caps-0.058
================================================================-0.056
-0.054
Token Sund
Token ID3309
Feature activation-3.53e+00

Pos logit contributions
itton+2.226
pez+2.162
ocard+2.142
atts+2.017
ourage+1.998
Neg logit contributions
 Masquerade-1.869
 Goat-1.785
 Caps-1.667
================================================================-1.653
-1.607
Tokenarb
Token ID38039
Feature activation-5.79e-01

Pos logit contributions
 Masquerade+4.891
 Goat+4.867
 Caps+4.627
================================================================+4.537
mentation+4.490
Neg logit contributions
itton-6.145
pez-5.953
ocard-5.853
 horm-5.660
 situational-5.528
Tokenans
Token ID504
Feature activation-7.57e-01

Pos logit contributions
 Masquerade+0.931
 Goat+0.911
 Caps+0.868
================================================================+0.846
mentation+0.828
Neg logit contributions
itton-0.963
pez-0.928
ocard-0.920
atts-0.856
ourage-0.843
Token,
Token ID11
Feature activation-9.88e-02

Pos logit contributions
 Masquerade+1.082
 Goat+1.042
 Caps+0.972
================================================================+0.948
+0.919
Neg logit contributions
itton-1.428
pez-1.384
ocard-1.370
atts-1.299
ourage-1.282
Token southeast
Token ID26015
Feature activation-9.20e-01

Pos logit contributions
 Masquerade+0.155
 Goat+0.151
 Caps+0.141
================================================================+0.137
+0.134
Neg logit contributions
itton-0.173
pez-0.168
ocard-0.166
atts-0.156
ourage-0.154
Token of
Token ID286
Feature activation-1.98e-01

Pos logit contributions
 Masquerade+1.430
 Goat+1.408
 Caps+1.312
================================================================+1.284
+1.261
Neg logit contributions
itton-1.596
pez-1.554
ocard-1.528
atts-1.431
ourage-1.423
Token This
Token ID770
Feature activation-5.54e-01

Pos logit contributions
itton+1.460
pez+1.413
ocard+1.397
atts+1.315
ourage+1.299
Neg logit contributions
 Masquerade-1.348
 Goat-1.300
 Caps-1.219
================================================================-1.200
-1.169
Token aerial
Token ID17789
Feature activation+3.91e-01

Pos logit contributions
 Masquerade+0.903
 Goat+0.883
 Caps+0.830
================================================================+0.806
+0.786
Neg logit contributions
itton-0.931
pez-0.895
ocard-0.889
atts-0.840
ourage-0.824
Token photograph
Token ID8408
Feature activation+1.17e+00

Pos logit contributions
itton+0.577
pez+0.553
ocard+0.545
atts+0.509
ourage+0.497
Neg logit contributions
 Masquerade-0.721
 Goat-0.701
 Caps-0.664
================================================================-0.651
-0.639
Token of
Token ID286
Feature activation-4.86e-02

Pos logit contributions
itton+1.988
pez+1.925
ocard+1.902
atts+1.790
ourage+1.769
Neg logit contributions
 Masquerade-1.885
 Goat-1.815
 Caps-1.702
================================================================-1.683
-1.640
Token the
Token ID262
Feature activation+1.27e-01

Pos logit contributions
 Masquerade+0.076
 Goat+0.074
 Caps+0.069
================================================================+0.067
+0.066
Neg logit contributions
itton-0.085
pez-0.083
ocard-0.082
atts-0.077
ourage-0.076
Token Sund
Token ID3309
Feature activation-3.43e+00

Pos logit contributions
itton+0.230
pez+0.223
ocard+0.220
atts+0.208
ourage+0.206
Neg logit contributions
 Masquerade-0.191
 Goat-0.185
 Caps-0.173
================================================================-0.169
-0.165
Tokenarb
Token ID38039
Feature activation-6.05e-01

Pos logit contributions
 Goat+4.705
 Masquerade+4.698
 Caps+4.426
mentation+4.377
================================================================+4.363
Neg logit contributions
itton-5.954
pez-5.677
ocard-5.668
 horm-5.513
 situational-5.370
Tokenans
Token ID504
Feature activation-6.59e-01

Pos logit contributions
 Masquerade+0.957
 Goat+0.939
 Caps+0.896
================================================================+0.870
mentation+0.852
Neg logit contributions
itton-1.014
pez-0.974
ocard-0.972
atts-0.898
 horm-0.891
Token,
Token ID11
Feature activation+7.59e-02

Pos logit contributions
 Masquerade+0.992
 Goat+0.956
 Caps+0.894
================================================================+0.874
+0.842
Neg logit contributions
itton-1.199
pez-1.153
ocard-1.145
atts-1.086
ourage-1.070
Token made
Token ID925
Feature activation+2.35e-02

Pos logit contributions
itton+0.133
pez+0.129
ocard+0.127
atts+0.120
ourage+0.118
Neg logit contributions
 Masquerade-0.119
 Goat-0.116
 Caps-0.108
================================================================-0.105
-0.103
Token in
Token ID287
Feature activation-7.45e-02

Pos logit contributions
itton+0.039
ocard+0.037
pez+0.037
atts+0.035
ourage+0.034
Neg logit contributions
 Masquerade-0.039
 Goat-0.038
 Caps-0.036
================================================================-0.035
-0.034
Token catastrophe
Token ID27767
Feature activation+3.87e-01

Pos logit contributions
 Masquerade+0.545
 Goat+0.529
 Caps+0.493
================================================================+0.480
+0.462
Neg logit contributions
itton-0.703
pez-0.684
ocard-0.675
atts-0.641
ourage-0.632
Token is
Token ID318
Feature activation+7.34e-02

Pos logit contributions
itton+0.732
pez+0.711
ocard+0.703
atts+0.665
ourage+0.657
Neg logit contributions
 Masquerade-0.554
 Goat-0.531
 Caps-0.495
================================================================-0.485
-0.470
Token unprecedented
Token ID13029
Feature activation+1.29e+00

Pos logit contributions
itton+0.125
pez+0.121
ocard+0.120
atts+0.112
ourage+0.111
Neg logit contributions
 Masquerade-0.119
 Goat-0.115
 Caps-0.108
================================================================-0.106
-0.103
Token in
Token ID287
Feature activation-4.31e-04

Pos logit contributions
itton+2.260
pez+2.190
ocard+2.164
atts+2.042
ourage+2.019
Neg logit contributions
 Masquerade-1.991
 Goat-1.912
 Caps-1.789
================================================================-1.766
-1.726
Token the
Token ID262
Feature activation+5.57e-02

Pos logit contributions
 Masquerade+0.001
 Goat+0.001
 Caps+0.001
================================================================+0.001
+0.001
Neg logit contributions
itton-0.001
pez-0.001
ocard-0.001
atts-0.001
ourage-0.001
Token Sund
Token ID3309
Feature activation-3.35e+00

Pos logit contributions
itton+0.102
pez+0.099
ocard+0.097
atts+0.092
ourage+0.091
Neg logit contributions
 Masquerade-0.083
 Goat-0.080
 Caps-0.075
================================================================-0.073
-0.071
Tokenarb
Token ID38039
Feature activation-2.66e-01

Pos logit contributions
 Goat+4.711
 Masquerade+4.701
 Caps+4.465
================================================================+4.384
mentation+4.297
Neg logit contributions
itton-5.844
pez-5.633
ocard-5.523
 horm-5.356
 situational-5.232
Tokenans
Token ID504
Feature activation-7.33e-01

Pos logit contributions
 Masquerade+0.440
 Goat+0.429
 Caps+0.406
================================================================+0.399
+0.388
Neg logit contributions
itton-0.433
pez-0.418
ocard-0.413
atts-0.385
ourage-0.380
Token,
Token ID11
Feature activation+7.99e-02

Pos logit contributions
 Masquerade+1.018
 Goat+0.978
 Caps+0.910
================================================================+0.893
+0.863
Neg logit contributions
itton-1.410
pez-1.369
ocard-1.355
atts-1.283
ourage-1.271
Token and
Token ID290
Feature activation-8.86e-02

Pos logit contributions
itton+0.147
pez+0.143
ocard+0.141
atts+0.133
ourage+0.132
Neg logit contributions
 Masquerade-0.118
 Goat-0.114
 Caps-0.106
================================================================-0.104
-0.101
Token we
Token ID356
Feature activation+2.54e-01

Pos logit contributions
 Masquerade+0.133
 Goat+0.130
 Caps+0.122
================================================================+0.118
+0.114
Neg logit contributions
itton-0.161
pez-0.156
ocard-0.154
atts-0.145
ourage-0.143
Token the
Token ID262
Feature activation+1.48e-01

Pos logit contributions
itton+0.284
pez+0.276
ocard+0.272
atts+0.257
ourage+0.255
Neg logit contributions
 Masquerade-0.235
 Goat-0.227
 Caps-0.211
================================================================-0.207
-0.202
Token waters
Token ID10150
Feature activation+6.46e-01

Pos logit contributions
itton+0.278
pez+0.270
ocard+0.266
atts+0.252
ourage+0.250
Neg logit contributions
 Masquerade-0.213
 Goat-0.205
 Caps-0.190
================================================================-0.186
-0.181
Token of
Token ID286
Feature activation+1.42e-01

Pos logit contributions
itton+1.153
pez+1.117
ocard+1.105
atts+1.042
ourage+1.031
Neg logit contributions
 Masquerade-0.986
 Goat-0.948
 Caps-0.886
================================================================-0.873
-0.851
Token Bangladesh
Token ID19483
Feature activation+1.56e+00

Pos logit contributions
itton+0.257
pez+0.250
ocard+0.246
atts+0.233
ourage+0.230
Neg logit contributions
 Masquerade-0.213
 Goat-0.205
 Caps-0.191
================================================================-0.187
-0.183
Token's
Token ID338
Feature activation+6.05e-01

Pos logit contributions
itton+2.864
pez+2.771
ocard+2.739
atts+2.599
ourage+2.577
Neg logit contributions
 Masquerade-2.301
 Goat-2.191
 Caps-2.046
================================================================-2.021
-1.966
Token Sund
Token ID3309
Feature activation-3.31e+00

Pos logit contributions
itton+1.072
pez+1.038
ocard+1.027
atts+0.969
ourage+0.958
Neg logit contributions
 Masquerade-0.929
 Goat-0.893
 Caps-0.835
================================================================-0.823
-0.802
Tokenarb
Token ID38039
Feature activation-1.52e-01

Pos logit contributions
 Goat+4.821
 Masquerade+4.818
 Caps+4.550
================================================================+4.376
ppa+4.247
Neg logit contributions
pez-5.654
itton-5.622
ocard-5.484
 horm-5.136
ourage-5.118
Tokenans
Token ID504
Feature activation-5.49e-01

Pos logit contributions
 Goat+0.231
 Masquerade+0.229
 Caps+0.221
================================================================+0.215
mentation+0.208
Neg logit contributions
itton-0.260
pez-0.254
ocard-0.246
atts-0.231
 horm-0.228
Token,
Token ID11
Feature activation+2.44e-02

Pos logit contributions
 Masquerade+0.800
 Goat+0.772
 Caps+0.720
================================================================+0.707
+0.687
Neg logit contributions
itton-1.014
pez-0.983
ocard-0.976
atts-0.921
ourage-0.911
Token the
Token ID262
Feature activation+6.05e-02

Pos logit contributions
itton+0.043
pez+0.042
ocard+0.041
atts+0.039
ourage+0.038
Neg logit contributions
 Masquerade-0.038
 Goat-0.037
 Caps-0.035
================================================================-0.034
-0.033
Token largest
Token ID4387
Feature activation+8.96e-01

Pos logit contributions
itton+0.105
pez+0.102
ocard+0.100
atts+0.094
ourage+0.094
Neg logit contributions
 Masquerade-0.095
 Goat-0.093
 Caps-0.087
================================================================-0.085
-0.083
Tokenested
Token ID7287
Feature activation-1.02e+00

Pos logit contributions
 Masquerade+2.768
 Goat+2.697
 Caps+2.558
================================================================+2.550
mentation+2.507
Neg logit contributions
itton-1.977
pez-1.881
ocard-1.850
 horm-1.739
atts-1.696
Token.
Token ID13
Feature activation-6.62e-02

Pos logit contributions
 Masquerade+1.401
 Goat+1.342
 Caps+1.229
================================================================+1.224
+1.178
Neg logit contributions
itton-1.971
ocard-1.897
pez-1.896
atts-1.783
ourage-1.763
TokenBT
Token ID19313
Feature activation+1.98e-01

Pos logit contributions
 Masquerade+0.098
 Goat+0.094
 Caps+0.088
================================================================+0.086
+0.084
Neg logit contributions
itton-0.122
pez-0.119
ocard-0.117
atts-0.111
ourage-0.109
TokenW
Token ID54
Feature activation+6.85e-01

Pos logit contributions
itton+0.361
pez+0.351
ocard+0.347
atts+0.327
ourage+0.324
Neg logit contributions
 Masquerade-0.294
 Goat-0.284
 Caps-0.264
================================================================-0.261
-0.253
Token,
Token ID11
Feature activation+2.35e-02

Pos logit contributions
itton+1.243
pez+1.205
ocard+1.192
atts+1.126
ourage+1.114
Neg logit contributions
 Masquerade-1.024
 Goat-0.983
 Caps-0.917
================================================================-0.904
-0.880
Token Sid
Token ID15686
Feature activation-3.29e+00

Pos logit contributions
itton+0.042
pez+0.041
ocard+0.040
atts+0.038
ourage+0.038
Neg logit contributions
 Masquerade-0.036
 Goat-0.035
 Caps-0.032
================================================================-0.032
-0.031
Token Davis
Token ID7802
Feature activation+6.05e-01

Pos logit contributions
 Masquerade+4.883
 Goat+4.716
 Caps+4.364
================================================================+4.267
+4.197
Neg logit contributions
itton-5.901
pez-5.669
ocard-5.587
ourage-5.244
atts-5.233
Token updated
Token ID6153
Feature activation+1.36e-01

Pos logit contributions
itton+1.096
pez+1.063
ocard+1.051
atts+0.993
ourage+0.982
Neg logit contributions
 Masquerade-0.906
 Goat-0.871
 Caps-0.813
================================================================-0.801
-0.779
Token this
Token ID428
Feature activation-1.05e+00

Pos logit contributions
itton+0.243
pez+0.235
ocard+0.232
atts+0.219
ourage+0.217
Neg logit contributions
 Masquerade-0.210
 Goat-0.202
 Caps-0.189
================================================================-0.186
-0.181
Token movie
Token ID3807
Feature activation+5.44e-01

Pos logit contributions
 Masquerade+1.561
 Goat+1.508
 Caps+1.400
================================================================+1.373
+1.326
Neg logit contributions
itton-1.921
pez-1.861
ocard-1.841
atts-1.744
ourage-1.734
Token in
Token ID287
Feature activation-2.83e-01

Pos logit contributions
itton+0.950
pez+0.919
ocard+0.909
atts+0.856
ourage+0.847
Neg logit contributions
 Masquerade-0.854
 Goat-0.822
 Caps-0.769
================================================================-0.758
-0.738
Token Min
Token ID1855
Feature activation+3.84e-01

Pos logit contributions
 Masquerade+0.039
 Goat+0.037
 Caps+0.035
================================================================+0.034
+0.033
Neg logit contributions
itton-0.043
pez-0.042
ocard-0.042
atts-0.039
ourage-0.039
Tokenova
Token ID10071
Feature activation-3.37e-02

Pos logit contributions
itton+0.638
pez+0.616
ocard+0.609
atts+0.572
ourage+0.565
Neg logit contributions
 Masquerade-0.631
 Goat-0.609
 Caps-0.572
================================================================-0.565
-0.551
Token
Token ID564
Feature activation-6.44e-01

Pos logit contributions
 Masquerade+0.046
 Goat+0.043
 Caps+0.040
================================================================+0.040
+0.038
Neg logit contributions
itton-0.066
pez-0.064
ocard-0.064
atts-0.060
ourage-0.060
Token
Token ID250
Feature activation-3.07e-01

Pos logit contributions
 Masquerade+1.059
 Goat+1.025
 Caps+0.961
================================================================+0.953
+0.948
Neg logit contributions
itton-1.066
pez-1.028
ocard-1.022
atts-0.960
ourage-0.949
Tokenir
Token ID343
Feature activation+3.93e-01

Pos logit contributions
 Masquerade+0.440
 Goat+0.419
 Caps+0.393
================================================================+0.387
+0.376
Neg logit contributions
itton-0.576
pez-0.560
ocard-0.555
atts-0.524
ourage-0.518
Tokenrespective
Token ID36990
Feature activation-3.24e+00

Pos logit contributions
itton+0.662
pez+0.648
ocard+0.634
atts+0.597
ourage+0.589
Neg logit contributions
 Masquerade-0.633
 Goat-0.613
 Caps-0.574
================================================================-0.570
-0.553
Token of
Token ID286
Feature activation-3.20e-01

Pos logit contributions
 Masquerade+4.650
 Goat+4.464
 Caps+4.218
================================================================+4.141
+4.113
Neg logit contributions
itton-5.785
pez-5.691
ocard-5.526
atts-5.245
ourage-5.215
Token which
Token ID543
Feature activation+3.46e-01

Pos logit contributions
 Masquerade+0.506
 Goat+0.487
 Caps+0.456
================================================================+0.448
+0.436
Neg logit contributions
itton-0.555
pez-0.539
ocard-0.532
atts-0.500
ourage-0.495
Token unit
Token ID4326
Feature activation+1.09e-01

Pos logit contributions
itton+0.580
pez+0.561
ocard+0.555
atts+0.521
ourage+0.515
Neg logit contributions
 Masquerade-0.565
 Goat-0.545
 Caps-0.512
================================================================-0.505
-0.493
Token is
Token ID318
Feature activation-2.16e-01

Pos logit contributions
itton+0.201
pez+0.196
ocard+0.193
atts+0.182
ourage+0.180
Neg logit contributions
 Masquerade-0.159
 Goat-0.153
 Caps-0.143
================================================================-0.140
-0.137
Token accused
Token ID5371
Feature activation-9.47e-01

Pos logit contributions
 Masquerade+0.326
 Goat+0.314
 Caps+0.295
================================================================+0.287
+0.280
Neg logit contributions
itton-0.391
pez-0.378
ocard-0.376
atts-0.353
ourage-0.349
Token except
Token ID2845
Feature activation+7.86e-01

Pos logit contributions
 Masquerade+0.091
 Goat+0.088
 Caps+0.082
================================================================+0.081
+0.079
Neg logit contributions
itton-0.114
pez-0.111
ocard-0.110
atts-0.104
ourage-0.103
Token by
Token ID416
Feature activation+3.37e-01

Pos logit contributions
itton+1.254
pez+1.207
ocard+1.198
atts+1.120
ourage+1.103
Neg logit contributions
 Masquerade-1.349
 Goat-1.310
 Caps-1.233
================================================================-1.214
-1.185
Token water
Token ID1660
Feature activation+4.59e-01

Pos logit contributions
itton+0.595
pez+0.576
ocard+0.570
atts+0.537
ourage+0.531
Neg logit contributions
 Masquerade-0.521
 Goat-0.503
 Caps-0.470
================================================================-0.462
-0.450
Token,
Token ID11
Feature activation+3.24e-01

Pos logit contributions
itton+0.793
pez+0.768
ocard+0.760
atts+0.715
ourage+0.706
Neg logit contributions
 Masquerade-0.726
 Goat-0.701
 Caps-0.658
================================================================-0.646
-0.631
Token the
Token ID262
Feature activation+1.97e-01

Pos logit contributions
itton+0.686
pez+0.668
ocard+0.662
atts+0.631
ourage+0.624
Neg logit contributions
 Masquerade-0.387
 Goat-0.370
 Caps-0.339
================================================================-0.331
-0.321
Token Sund
Token ID3309
Feature activation-3.17e+00

Pos logit contributions
itton+0.496
pez+0.486
ocard+0.482
atts+0.463
ourage+0.459
Neg logit contributions
 Masquerade-0.155
 Goat-0.144
 Caps-0.125
================================================================-0.120
-0.114
Tokenarb
Token ID38039
Feature activation-5.99e-01

Pos logit contributions
 Masquerade+4.399
 Goat+4.367
 Caps+4.146
================================================================+4.093
mentation+4.076
Neg logit contributions
itton-5.561
pez-5.284
ocard-5.277
 horm-5.062
 situational-4.972
Tokenans
Token ID504
Feature activation-6.54e-01

Pos logit contributions
 Masquerade+0.953
 Goat+0.931
 Caps+0.890
================================================================+0.869
mentation+0.847
Neg logit contributions
itton-1.003
pez-0.963
ocard-0.960
atts-0.884
ourage-0.878
Token is
Token ID318
Feature activation-1.60e-01

Pos logit contributions
 Masquerade+0.930
 Goat+0.896
 Caps+0.834
================================================================+0.815
+0.785
Neg logit contributions
itton-1.238
pez-1.191
ocard-1.185
atts-1.119
ourage-1.108
Token a
Token ID257
Feature activation+3.58e-02

Pos logit contributions
 Masquerade+0.255
 Goat+0.247
 Caps+0.231
================================================================+0.228
+0.222
Neg logit contributions
itton-0.275
pez-0.265
ocard-0.263
atts-0.246
ourage-0.244
Token place
Token ID1295
Feature activation-1.41e-01

Pos logit contributions
itton+0.060
pez+0.058
ocard+0.057
atts+0.054
ourage+0.053
Neg logit contributions
 Masquerade-0.059
 Goat-0.057
 Caps-0.054
================================================================-0.053
-0.051
Token chief
Token ID4039
Feature activation+3.60e-01

Pos logit contributions
 Masquerade+0.004
 Goat+0.004
 Caps+0.004
================================================================+0.004
+0.004
Neg logit contributions
itton-0.005
pez-0.004
ocard-0.004
atts-0.004
ourage-0.004
Token forest
Token ID8222
Feature activation+7.58e-01

Pos logit contributions
itton+0.609
pez+0.590
ocard+0.583
atts+0.548
ourage+0.542
Neg logit contributions
 Masquerade-0.581
 Goat-0.560
 Caps-0.526
================================================================-0.518
-0.506
Token official
Token ID1743
Feature activation+6.50e-01

Pos logit contributions
itton+1.234
pez+1.192
ocard+1.180
atts+1.105
ourage+1.094
Neg logit contributions
 Masquerade-1.279
 Goat-1.228
 Caps-1.156
================================================================-1.143
-1.117
Token of
Token ID286
Feature activation+1.51e-02

Pos logit contributions
itton+1.074
pez+1.037
ocard+1.024
atts+0.961
ourage+0.948
Neg logit contributions
 Masquerade-1.079
 Goat-1.042
 Caps-0.981
================================================================-0.965
-0.943
Token the
Token ID262
Feature activation+4.54e-03

Pos logit contributions
itton+0.028
pez+0.027
ocard+0.026
atts+0.025
ourage+0.025
Neg logit contributions
 Masquerade-0.022
 Goat-0.022
 Caps-0.020
================================================================-0.020
-0.019
Token Sund
Token ID3309
Feature activation-3.16e+00

Pos logit contributions
itton+0.009
pez+0.009
ocard+0.009
atts+0.008
ourage+0.008
Neg logit contributions
 Masquerade-0.006
 Goat-0.006
 Caps-0.006
================================================================-0.005
-0.005
Tokenarb
Token ID38039
Feature activation-2.03e-01

Pos logit contributions
 Masquerade+4.452
 Goat+4.439
 Caps+4.218
================================================================+4.107
mentation+4.041
Neg logit contributions
itton-5.507
pez-5.296
ocard-5.232
 horm-5.037
 situational-4.897
Tokenans
Token ID504
Feature activation-5.82e-01

Pos logit contributions
 Masquerade+0.334
 Goat+0.326
 Caps+0.309
================================================================+0.302
mentation+0.294
Neg logit contributions
itton-0.332
pez-0.320
ocard-0.316
atts-0.295
ourage-0.291
Token in
Token ID287
Feature activation-7.84e-02

Pos logit contributions
 Masquerade+0.909
 Goat+0.884
 Caps+0.830
================================================================+0.806
+0.783
Neg logit contributions
itton-1.020
pez-0.986
ocard-0.977
atts-0.921
ourage-0.904
Token Bangladesh
Token ID19483
Feature activation+1.18e+00

Pos logit contributions
 Masquerade+0.119
 Goat+0.115
 Caps+0.107
================================================================+0.105
+0.102
Neg logit contributions
itton-0.141
pez-0.137
ocard-0.135
atts-0.127
ourage-0.126
Token,
Token ID11
Feature activation-7.85e-02

Pos logit contributions
itton+2.126
pez+2.062
ocard+2.036
atts+1.927
ourage+1.911
Neg logit contributions
 Masquerade-1.789
 Goat-1.710
 Caps-1.597
================================================================-1.578
-1.537
Tokenre
Token ID260
Feature activation+4.52e-01

Pos logit contributions
itton+0.002
pez+0.002
ocard+0.002
atts+0.002
ourage+0.002
Neg logit contributions
 Masquerade-0.001
 Goat-0.001
 Caps-0.001
================================================================-0.001
-0.001
Tokenment
Token ID434
Feature activation-1.93e-02

Pos logit contributions
itton+1.140
pez+1.115
ocard+1.106
atts+1.063
ourage+1.055
Neg logit contributions
 Masquerade-0.356
 Goat-0.328
 Caps-0.284
================================================================-0.276
-0.260
Token or
Token ID393
Feature activation+2.74e-01

Pos logit contributions
 Masquerade+0.028
 Goat+0.027
 Caps+0.025
================================================================+0.025
+0.024
Neg logit contributions
itton-0.036
pez-0.035
ocard-0.034
atts-0.032
ourage-0.032
Token sending
Token ID7216
Feature activation+4.28e-01

Pos logit contributions
itton+0.459
pez+0.444
ocard+0.438
atts+0.412
ourage+0.407
Neg logit contributions
 Masquerade-0.450
 Goat-0.435
 Caps-0.410
================================================================-0.402
-0.390
Token so
Token ID523
Feature activation-1.09e-01

Pos logit contributions
itton+0.761
pez+0.733
ocard+0.726
atts+0.684
ourage+0.676
Neg logit contributions
 Masquerade-0.663
 Goat-0.639
 Caps-0.601
================================================================-0.587
-0.572
Tokenapy
Token ID12826
Feature activation-3.07e+00

Pos logit contributions
 Masquerade+0.158
 Goat+0.151
 Caps+0.141
================================================================+0.139
+0.135
Neg logit contributions
itton-0.203
pez-0.197
ocard-0.195
atts-0.184
ourage-0.182
Token water
Token ID1660
Feature activation+3.55e-01

Pos logit contributions
 Masquerade+4.816
 Goat+4.725
 Caps+4.526
================================================================+4.283
mentation+4.138
Neg logit contributions
itton-5.226
pez-4.944
ocard-4.878
atts-4.582
ourage-4.528
Token back
Token ID736
Feature activation+2.67e-01

Pos logit contributions
itton+0.658
pez+0.637
ocard+0.631
atts+0.594
ourage+0.589
Neg logit contributions
 Masquerade-0.520
 Goat-0.500
 Caps-0.467
================================================================-0.458
-0.444
Token into
Token ID656
Feature activation-4.58e-01

Pos logit contributions
itton+0.520
pez+0.505
ocard+0.500
atts+0.473
ourage+0.469
Neg logit contributions
 Masquerade-0.364
 Goat-0.349
 Caps-0.324
================================================================-0.318
-0.308
Token the
Token ID262
Feature activation-7.84e-02

Pos logit contributions
 Masquerade+0.709
 Goat+0.688
 Caps+0.646
================================================================+0.624
+0.612
Neg logit contributions
itton-0.809
pez-0.779
ocard-0.769
atts-0.727
ourage-0.717
Token bowl
Token ID9396
Feature activation-5.36e-01

Pos logit contributions
 Masquerade+0.128
 Goat+0.123
 Caps+0.116
================================================================+0.113
+0.111
Neg logit contributions
itton-0.133
pez-0.128
ocard-0.126
atts-0.120
ourage-0.118
Token sund
Token ID37437
Feature activation-2.56e+00

Pos logit contributions
 Masquerade+0.523
 Goat+0.507
 Caps+0.472
================================================================+0.459
+0.447
Neg logit contributions
itton-0.657
pez-0.639
ocard-0.629
atts-0.596
ourage-0.588
Tokenari
Token ID2743
Feature activation-1.29e+00

Pos logit contributions
 Masquerade+4.040
 Goat+3.948
 Caps+3.689
================================================================+3.603
acly+3.560
Neg logit contributions
itton-4.234
pez-4.119
ocard-4.055
atts-3.854
ourage-3.746
Token tree
Token ID5509
Feature activation+3.31e-01

Pos logit contributions
 Masquerade+1.952
 Goat+1.907
 Caps+1.783
================================================================+1.728
+1.698
Neg logit contributions
itton-2.305
pez-2.230
ocard-2.206
atts-2.093
ourage-2.064
Token,
Token ID11
Feature activation+4.12e-02

Pos logit contributions
itton+0.600
pez+0.582
ocard+0.575
atts+0.543
ourage+0.537
Neg logit contributions
 Masquerade-0.498
 Goat-0.478
 Caps-0.446
================================================================-0.440
-0.428
Token the
Token ID262
Feature activation+2.42e-02

Pos logit contributions
itton+0.077
pez+0.075
ocard+0.074
atts+0.070
ourage+0.069
Neg logit contributions
 Masquerade-0.059
 Goat-0.057
 Caps-0.053
================================================================-0.052
-0.051
Token Sund
Token ID3309
Feature activation-3.05e+00

Pos logit contributions
itton+0.048
pez+0.047
ocard+0.046
atts+0.044
ourage+0.044
Neg logit contributions
 Masquerade-0.032
 Goat-0.031
 Caps-0.028
================================================================-0.028
-0.027
Tokenarb
Token ID38039
Feature activation-3.24e-01

Pos logit contributions
 Masquerade+4.343
 Goat+4.296
 Caps+4.052
================================================================+4.029
mentation+3.995
Neg logit contributions
itton-5.273
pez-5.036
ocard-5.012
 horm-4.780
 situational-4.707
Tokenans
Token ID504
Feature activation-6.47e-01

Pos logit contributions
 Masquerade+0.536
 Goat+0.522
 Caps+0.495
================================================================+0.485
mentation+0.471
Neg logit contributions
itton-0.528
pez-0.508
ocard-0.504
atts-0.469
ourage-0.463
Token is
Token ID318
Feature activation-1.24e-01

Pos logit contributions
 Masquerade+0.958
 Goat+0.926
 Caps+0.869
================================================================+0.843
+0.818
Neg logit contributions
itton-1.182
pez-1.139
ocard-1.133
atts-1.072
ourage-1.058
Token a
Token ID257
Feature activation-1.53e-02

Pos logit contributions
 Masquerade+0.193
 Goat+0.188
 Caps+0.176
================================================================+0.173
+0.168
Neg logit contributions
itton-0.218
pez-0.211
ocard-0.209
atts-0.196
ourage-0.194
Token vast
Token ID5909
Feature activation+3.32e-01

Pos logit contributions
 Masquerade+0.025
 Goat+0.024
 Caps+0.023
================================================================+0.022
+0.022
Neg logit contributions
itton-0.026
pez-0.025
ocard-0.025
atts-0.023
ourage-0.023
Token center
Token ID3641
Feature activation+3.11e-01

Pos logit contributions
 Masquerade+0.389
 Goat+0.375
 Caps+0.353
================================================================+0.347
+0.339
Neg logit contributions
itton-0.391
pez-0.379
ocard-0.374
atts-0.352
ourage-0.347
Token for
Token ID329
Feature activation+2.44e-01

Pos logit contributions
itton+0.581
pez+0.563
ocard+0.557
atts+0.528
ourage+0.522
Neg logit contributions
 Masquerade-0.448
 Goat-0.430
 Caps-0.400
================================================================-0.394
-0.383
Token the
Token ID262
Feature activation-3.33e-02

Pos logit contributions
itton+0.422
pez+0.409
ocard+0.404
atts+0.380
ourage+0.376
Neg logit contributions
 Masquerade-0.386
 Goat-0.372
 Caps-0.349
================================================================-0.343
-0.335
Token city
Token ID1748
Feature activation-6.81e-01

Pos logit contributions
 Masquerade+0.052
 Goat+0.050
 Caps+0.047
================================================================+0.046
+0.045
Neg logit contributions
itton-0.058
pez-0.056
ocard-0.056
atts-0.053
ourage-0.052
Token,"
Token ID553
Feature activation-8.02e-01

Pos logit contributions
 Masquerade+0.889
 Goat+0.856
 Caps+0.789
================================================================+0.771
+0.746
Neg logit contributions
itton-1.365
pez-1.324
ocard-1.311
atts-1.241
ourage-1.226
Token Ful
Token ID28040
Feature activation-3.01e+00

Pos logit contributions
 Masquerade+1.040
 Goat+0.996
 Caps+0.918
================================================================+0.895
+0.861
Neg logit contributions
itton-1.619
pez-1.574
ocard-1.558
atts-1.486
ourage-1.459
Tokenop
Token ID404
Feature activation-8.57e-01

Pos logit contributions
 Masquerade+2.536
 Goat+2.435
 Caps+2.275
================================================================+2.200
ppa+2.191
Neg logit contributions
itton-6.919
ocard-6.695
pez-6.658
 horm-6.609
atts-6.411
Token said
Token ID531
Feature activation-6.34e-01

Pos logit contributions
 Masquerade+1.283
 Goat+1.233
 Caps+1.153
================================================================+1.128
+1.108
Neg logit contributions
itton-1.548
pez-1.497
ocard-1.488
atts-1.399
ourage-1.386
Token.
Token ID13
Feature activation+1.14e-01

Pos logit contributions
 Masquerade+0.915
 Goat+0.877
 Caps+0.814
================================================================+0.795
+0.779
Neg logit contributions
itton-1.181
pez-1.142
ocard-1.133
atts-1.072
ourage-1.054
Token
Token ID198
Feature activation+2.35e-01

Pos logit contributions
itton+0.204
pez+0.197
ocard+0.195
atts+0.184
ourage+0.183
Neg logit contributions
 Masquerade-0.173
 Goat-0.166
 Caps-0.155
================================================================-0.153
-0.149
Token
Token ID198
Feature activation+1.79e-01

Pos logit contributions
itton+0.441
pez+0.427
ocard+0.423
atts+0.399
ourage+0.395
Neg logit contributions
 Masquerade-0.339
 Goat-0.327
 Caps-0.306
================================================================-0.302
-0.289
Tokenth
Token ID400
Feature activation-6.29e-02

Pos logit contributions
 Masquerade+0.700
 Goat+0.673
 Caps+0.628
================================================================+0.617
+0.599
Neg logit contributions
itton-0.858
pez-0.832
ocard-0.824
atts-0.778
ourage-0.770
Token Season
Token ID7369
Feature activation-2.45e-01

Pos logit contributions
 Masquerade+0.081
 Goat+0.077
 Caps+0.071
================================================================+0.069
+0.067
Neg logit contributions
itton-0.128
pez-0.124
ocard-0.123
atts-0.117
ourage-0.116
Token:
Token ID25
Feature activation-6.95e-01

Pos logit contributions
 Masquerade+0.379
 Goat+0.364
 Caps+0.341
================================================================+0.336
+0.325
Neg logit contributions
itton-0.434
pez-0.420
ocard-0.416
atts-0.393
ourage-0.388
Token Ghost
Token ID9897
Feature activation+4.73e-01

Pos logit contributions
 Masquerade+1.055
 Goat+1.016
 Caps+0.952
================================================================+0.929
+0.897
Neg logit contributions
itton-1.257
pez-1.218
ocard-1.208
atts-1.141
ourage-1.124
Token Island
Token ID5451
Feature activation-1.43e-01

Pos logit contributions
itton+0.804
pez+0.778
ocard+0.768
atts+0.722
ourage+0.712
Neg logit contributions
 Masquerade-0.768
 Goat-0.740
 Caps-0.696
================================================================-0.681
-0.665
Token TBA
Token ID48591
Feature activation-3.00e+00

Pos logit contributions
 Masquerade+0.211
 Goat+0.202
 Caps+0.189
================================================================+0.185
+0.179
Neg logit contributions
itton-0.264
pez-0.256
ocard-0.254
atts-0.240
ourage-0.237
Token TBA
Token ID48591
Feature activation-2.99e+00

Pos logit contributions
 Masquerade+4.219
 Goat+4.023
 Caps+3.725
================================================================+3.591
 Pengu+3.400
Neg logit contributions
itton-5.691
pez-5.600
ocard-5.556
atts-5.158
ourage-5.113
Token The
Token ID383
Feature activation-6.97e-01

Pos logit contributions
 Masquerade+4.380
 Goat+4.208
 Caps+3.897
================================================================+3.762
 Pengu+3.584
Neg logit contributions
itton-5.544
pez-5.423
ocard-5.402
atts-5.027
ourage-4.970
Token Complete
Token ID13248
Feature activation-7.29e-01

Pos logit contributions
 Masquerade+1.046
 Goat+1.005
 Caps+0.934
================================================================+0.914
+0.881
Neg logit contributions
itton-1.276
pez-1.243
ocard-1.223
atts-1.156
ourage-1.143
Token Thirty
Token ID29948
Feature activation+7.53e-03

Pos logit contributions
 Masquerade+1.245
 Goat+1.203
 Caps+1.131
================================================================+1.111
+1.083
Neg logit contributions
itton-1.177
pez-1.140
ocard-1.125
atts-1.051
ourage-1.037
Token-
Token ID12
Feature activation-2.85e-01

Pos logit contributions
itton+0.015
pez+0.015
ocard+0.015
atts+0.014
ourage+0.014
Neg logit contributions
 Masquerade-0.010
 Goat-0.009
 Caps-0.009
================================================================-0.008
-0.008
Token Season
Token ID7369
Feature activation-2.45e-01

Pos logit contributions
 Masquerade+0.081
 Goat+0.077
 Caps+0.071
================================================================+0.069
+0.067
Neg logit contributions
itton-0.128
pez-0.124
ocard-0.123
atts-0.117
ourage-0.116
Token:
Token ID25
Feature activation-6.95e-01

Pos logit contributions
 Masquerade+0.379
 Goat+0.364
 Caps+0.341
================================================================+0.336
+0.325
Neg logit contributions
itton-0.434
pez-0.420
ocard-0.416
atts-0.393
ourage-0.388
Token Ghost
Token ID9897
Feature activation+4.73e-01

Pos logit contributions
 Masquerade+1.055
 Goat+1.016
 Caps+0.952
================================================================+0.929
+0.897
Neg logit contributions
itton-1.257
pez-1.218
ocard-1.208
atts-1.141
ourage-1.124
Token Island
Token ID5451
Feature activation-1.43e-01

Pos logit contributions
itton+0.804
pez+0.778
ocard+0.768
atts+0.722
ourage+0.712
Neg logit contributions
 Masquerade-0.768
 Goat-0.740
 Caps-0.696
================================================================-0.681
-0.665
Token TBA
Token ID48591
Feature activation-3.00e+00

Pos logit contributions
 Masquerade+0.211
 Goat+0.202
 Caps+0.189
================================================================+0.185
+0.179
Neg logit contributions
itton-0.264
pez-0.256
ocard-0.254
atts-0.240
ourage-0.237
Token TBA
Token ID48591
Feature activation-2.99e+00

Pos logit contributions
 Masquerade+4.219
 Goat+4.023
 Caps+3.725
================================================================+3.591
 Pengu+3.400
Neg logit contributions
itton-5.691
pez-5.600
ocard-5.556
atts-5.158
ourage-5.113
Token The
Token ID383
Feature activation-6.97e-01

Pos logit contributions
 Masquerade+4.380
 Goat+4.208
 Caps+3.897
================================================================+3.762
 Pengu+3.584
Neg logit contributions
itton-5.544
pez-5.423
ocard-5.402
atts-5.027
ourage-4.970
Token Complete
Token ID13248
Feature activation-7.29e-01

Pos logit contributions
 Masquerade+1.046
 Goat+1.005
 Caps+0.934
================================================================+0.914
+0.881
Neg logit contributions
itton-1.276
pez-1.243
ocard-1.223
atts-1.156
ourage-1.143
Token Thirty
Token ID29948
Feature activation+7.53e-03

Pos logit contributions
 Masquerade+1.245
 Goat+1.203
 Caps+1.131
================================================================+1.111
+1.083
Neg logit contributions
itton-1.177
pez-1.140
ocard-1.125
atts-1.051
ourage-1.037
Token-
Token ID12
Feature activation-2.85e-01

Pos logit contributions
itton+0.015
pez+0.015
ocard+0.015
atts+0.014
ourage+0.014
Neg logit contributions
 Masquerade-0.010
 Goat-0.009
 Caps-0.009
================================================================-0.008
-0.008
TokenSe
Token ID4653
Feature activation+5.63e-02

Pos logit contributions
 Masquerade+0.593
 Goat+0.581
 Caps+0.552
================================================================+0.549
+0.538
Neg logit contributions
itton-0.347
pez-0.330
ocard-0.327
atts-0.302
ourage-0.293
Token 13
Token ID1511
Feature activation-1.25e-01

Pos logit contributions
 Masquerade+0.001
 Goat+0.001
 Caps+0.001
================================================================+0.001
+0.001
Neg logit contributions
itton-0.001
pez-0.001
ocard-0.001
atts-0.001
ourage-0.001
Token days
Token ID1528
Feature activation+9.60e-01

Pos logit contributions
 Masquerade+0.192
 Goat+0.184
 Caps+0.173
================================================================+0.170
+0.165
Neg logit contributions
itton-0.221
pez-0.214
ocard-0.212
atts-0.200
ourage-0.198
Token).
Token ID737
Feature activation-7.05e-01

Pos logit contributions
itton+1.862
pez+1.810
ocard+1.791
atts+1.702
ourage+1.682
Neg logit contributions
 Masquerade-1.318
 Goat-1.255
 Caps-1.162
================================================================-1.145
-1.113
Token Even
Token ID3412
Feature activation+6.36e-02

Pos logit contributions
 Masquerade+1.015
 Goat+0.982
 Caps+0.920
================================================================+0.896
+0.866
Neg logit contributions
itton-1.329
pez-1.290
ocard-1.274
atts-1.209
ourage-1.196
Token emperor
Token ID23129
Feature activation-8.20e-01

Pos logit contributions
itton+0.114
pez+0.110
ocard+0.109
atts+0.103
ourage+0.102
Neg logit contributions
 Masquerade-0.097
 Goat-0.094
 Caps-0.088
================================================================-0.086
-0.084
Token pengu
Token ID38373
Feature activation-2.94e+00

Pos logit contributions
 Masquerade+0.800
 Goat+0.760
 Caps+0.682
================================================================+0.661
+0.631
Neg logit contributions
itton-1.908
pez-1.862
ocard-1.845
atts-1.766
ourage-1.757
Tokenin
Token ID259
Feature activation-4.45e-01

Pos logit contributions
 Masquerade+3.603
 Goat+3.513
 Caps+3.373
================================================================+3.220
+3.139
Neg logit contributions
itton-5.806
ocard-5.507
pez-5.421
ourage-5.251
 horm-5.207
Token dads
Token ID47713
Feature activation+2.52e-02

Pos logit contributions
 Masquerade+0.764
 Goat+0.736
 Caps+0.697
================================================================+0.685
+0.669
Neg logit contributions
itton-0.712
pez-0.686
ocard-0.677
atts-0.633
ourage-0.627
Token,
Token ID11
Feature activation+2.31e-01

Pos logit contributions
itton+0.045
pez+0.043
ocard+0.043
atts+0.040
ourage+0.040
Neg logit contributions
 Masquerade-0.039
 Goat-0.037
 Caps-0.035
================================================================-0.034
-0.034
Token who
Token ID508
Feature activation+4.00e-01

Pos logit contributions
itton+0.413
pez+0.400
ocard+0.396
atts+0.373
ourage+0.369
Neg logit contributions
 Masquerade-0.351
 Goat-0.338
 Caps-0.317
================================================================-0.311
-0.303
Token famously
Token ID20524
Feature activation+1.41e+00

Pos logit contributions
itton+0.675
pez+0.653
ocard+0.646
atts+0.607
ourage+0.600
Neg logit contributions
 Masquerade-0.651
 Goat-0.626
 Caps-0.591
================================================================-0.579
-0.564
Token.
Token ID13
Feature activation-1.11e-01

Pos logit contributions
 Masquerade+0.140
 Goat+0.135
 Caps+0.125
================================================================+0.123
+0.119
Neg logit contributions
itton-0.183
pez-0.177
ocard-0.176
atts-0.166
ourage-0.164
Token
Token ID198
Feature activation-1.34e-01

Pos logit contributions
 Masquerade+0.170
 Goat+0.163
 Caps+0.153
================================================================+0.150
+0.146
Neg logit contributions
itton-0.198
pez-0.191
ocard-0.189
atts-0.179
ourage-0.177
Token
Token ID198
Feature activation-2.23e-01

Pos logit contributions
 Masquerade+0.188
 Goat+0.181
 Caps+0.170
================================================================+0.168
mentation+0.159
Neg logit contributions
itton-0.257
pez-0.248
ocard-0.245
atts-0.232
ourage-0.230
TokenExpl
Token ID18438
Feature activation+8.45e-01

Pos logit contributions
 Masquerade+0.349
 Goat+0.336
 Caps+0.315
================================================================+0.313
+0.303
Neg logit contributions
itton-0.391
pez-0.377
ocard-0.374
atts-0.352
ourage-0.348
Tokenained
Token ID1328
Feature activation-9.46e-01

Pos logit contributions
itton+1.399
pez+1.353
ocard+1.337
atts+1.257
ourage+1.243
Neg logit contributions
 Masquerade-1.404
 Goat-1.352
 Caps-1.270
================================================================-1.254
-1.222
Token Murd
Token ID20305
Feature activation-2.94e+00

Pos logit contributions
 Masquerade+1.359
 Goat+1.306
 Caps+1.214
================================================================+1.181
+1.145
Neg logit contributions
itton-1.789
pez-1.729
ocard-1.710
atts-1.624
ourage-1.606
Tokeny
Token ID88
Feature activation+1.41e-01

Pos logit contributions
 Masquerade+3.475
 Goat+3.300
 Caps+3.090
================================================================+2.993
mentation+2.976
Neg logit contributions
itton-5.903
ocard-5.714
pez-5.697
 horm-5.521
ourage-5.334
Token,
Token ID11
Feature activation-1.76e-02

Pos logit contributions
itton+0.255
pez+0.247
ocard+0.244
atts+0.230
ourage+0.228
Neg logit contributions
 Masquerade-0.213
 Goat-0.205
 Caps-0.191
================================================================-0.188
-0.183
Token
Token ID564
Feature activation-6.90e-01

Pos logit contributions
 Masquerade+0.028
 Goat+0.027
 Caps+0.025
================================================================+0.025
+0.024
Neg logit contributions
itton-0.031
pez-0.030
ocard-0.029
atts-0.028
ourage-0.027
Token
Token ID250
Feature activation-3.56e-01

Pos logit contributions
 Masquerade+0.668
 Goat+0.629
 Caps+0.561
================================================================+0.552
+0.540
Neg logit contributions
itton-1.612
pez-1.574
ocard-1.562
atts-1.496
ourage-1.484
TokenWe
Token ID1135
Feature activation+4.98e-02

Pos logit contributions
 Masquerade+0.562
 Goat+0.540
 Caps+0.506
================================================================+0.503
+0.487
Neg logit contributions
itton-0.624
pez-0.602
ocard-0.594
atts-0.558
ourage-0.552
Token
Token ID198
Feature activation-1.26e-02

Pos logit contributions
itton+0.155
pez+0.150
ocard+0.149
atts+0.140
ourage+0.139
Neg logit contributions
 Masquerade-0.117
 Goat-0.113
 Caps-0.106
================================================================-0.104
-0.100
TokenWilliam
Token ID17121
Feature activation+2.61e-01

Pos logit contributions
 Masquerade+0.020
 Goat+0.019
 Caps+0.018
================================================================+0.018
+0.017
Neg logit contributions
itton-0.022
pez-0.021
ocard-0.021
atts-0.020
ourage-0.020
Token Carpenter
Token ID32659
Feature activation+5.20e-02

Pos logit contributions
itton+0.505
pez+0.490
ocard+0.485
atts+0.461
ourage+0.456
Neg logit contributions
 Masquerade-0.359
 Goat-0.343
 Caps-0.318
================================================================-0.314
-0.304
Token,
Token ID11
Feature activation-3.80e-02

Pos logit contributions
itton+0.096
pez+0.093
ocard+0.092
atts+0.087
ourage+0.086
Neg logit contributions
 Masquerade-0.076
 Goat-0.073
 Caps-0.068
================================================================-0.067
-0.065
Token Mont
Token ID5575
Feature activation-3.14e-01

Pos logit contributions
 Masquerade+0.053
 Goat+0.051
 Caps+0.048
================================================================+0.046
+0.045
Neg logit contributions
itton-0.073
pez-0.071
ocard-0.070
atts-0.066
ourage-0.066
Tokenpel
Token ID30242
Feature activation-2.93e+00

Pos logit contributions
 Masquerade+0.301
 Goat+0.283
 Caps+0.253
================================================================+0.246
+0.233
Neg logit contributions
itton-0.738
pez-0.719
ocard-0.715
atts-0.684
ourage-0.678
Tokenier
Token ID959
Feature activation+1.34e-01

Pos logit contributions
 Masquerade+4.828
 Goat+4.689
 Caps+4.399
mentation+4.394
================================================================+4.376
Neg logit contributions
itton-4.358
pez-4.316
ocard-4.257
 horm-4.104
atts-4.015
Token
Token ID198
Feature activation-2.59e-02

Pos logit contributions
itton+0.242
pez+0.235
ocard+0.232
atts+0.220
ourage+0.217
Neg logit contributions
 Masquerade-0.201
 Goat-0.193
 Caps-0.180
================================================================-0.178
-0.173
Token
Token ID198
Feature activation-1.27e-01

Pos logit contributions
 Masquerade+0.037
 Goat+0.035
 Caps+0.033
================================================================+0.033
+0.031
Neg logit contributions
itton-0.049
pez-0.048
ocard-0.047
atts-0.045
ourage-0.044
TokenCon
Token ID3103
Feature activation-3.08e-01

Pos logit contributions
 Masquerade+0.198
 Goat+0.192
 Caps+0.180
================================================================+0.179
+0.173
Neg logit contributions
itton-0.221
pez-0.213
ocard-0.211
atts-0.198
ourage-0.197
Token Hogan
Token ID25316
Feature activation+3.94e-01

Pos logit contributions
 Masquerade+0.534
 Goat+0.520
 Caps+0.490
================================================================+0.484
+0.470
Neg logit contributions
itton-0.481
pez-0.467
ocard-0.460
atts-0.431
ourage-0.422
Token,
Token ID11
Feature activation+3.28e-01

Pos logit contributions
itton+1.027
pez+0.996
ocard+0.985
atts+0.930
ourage+0.920
Neg logit contributions
 Masquerade-0.863
 Goat-0.829
 Caps-0.773
================================================================-0.762
-0.743
Token teeth
Token ID9941
Feature activation-1.28e+00

Pos logit contributions
itton+0.577
pez+0.559
ocard+0.553
atts+0.521
ourage+0.515
Neg logit contributions
 Masquerade-0.509
 Goat-0.490
 Caps-0.459
================================================================-0.452
-0.441
Token are
Token ID389
Feature activation+1.71e-01

Pos logit contributions
 Masquerade+1.879
 Goat+1.806
 Caps+1.704
================================================================+1.658
+1.615
Neg logit contributions
itton-2.315
pez-2.252
ocard-2.214
atts-2.112
ourage-2.075
Token formed
Token ID7042
Feature activation-6.45e-01

Pos logit contributions
itton+0.298
pez+0.288
ocard+0.286
atts+0.269
ourage+0.266
Neg logit contributions
 Masquerade-0.268
 Goat-0.259
 Caps-0.243
================================================================-0.239
-0.233
Token from
Token ID422
Feature activation-3.36e-01

Pos logit contributions
 Masquerade+1.050
 Goat+1.017
 Caps+0.958
================================================================+0.936
+0.914
Neg logit contributions
itton-1.087
pez-1.041
ocard-1.036
atts-0.977
ourage-0.959
Token dent
Token ID18794
Feature activation-2.93e+00

Pos logit contributions
 Masquerade+0.523
 Goat+0.506
 Caps+0.475
================================================================+0.465
+0.453
Neg logit contributions
itton-0.588
pez-0.569
ocard-0.561
atts-0.533
ourage-0.525
Tokenin
Token ID259
Feature activation-4.51e-01

Pos logit contributions
 Masquerade+4.739
 Goat+4.646
 Caps+4.429
================================================================+4.271
mentation+4.248
Neg logit contributions
itton-4.681
pez-4.564
ocard-4.360
atts-4.236
 horm-4.135
Token,
Token ID11
Feature activation-4.65e-02

Pos logit contributions
 Masquerade+0.648
 Goat+0.621
 Caps+0.577
================================================================+0.568
+0.552
Neg logit contributions
itton-0.846
pez-0.821
ocard-0.813
atts-0.768
ourage-0.761
Token a
Token ID257
Feature activation-2.66e-02

Pos logit contributions
 Masquerade+0.072
 Goat+0.070
 Caps+0.065
================================================================+0.064
+0.063
Neg logit contributions
itton-0.081
pez-0.079
ocard-0.078
atts-0.074
ourage-0.073
Token liquid
Token ID8122
Feature activation-9.33e-01

Pos logit contributions
 Masquerade+0.041
 Goat+0.039
 Caps+0.037
================================================================+0.036
+0.035
Neg logit contributions
itton-0.047
pez-0.046
ocard-0.045
atts-0.043
ourage-0.042
Token that
Token ID326
Feature activation+5.43e-02

Pos logit contributions
 Masquerade+1.376
 Goat+1.330
 Caps+1.244
================================================================+1.213
+1.184
Neg logit contributions
itton-1.706
pez-1.653
ocard-1.639
atts-1.557
ourage-1.530
Token even
Token ID772
Feature activation-1.29e-01

Pos logit contributions
itton+1.159
pez+1.122
ocard+1.110
atts+1.047
ourage+1.035
Neg logit contributions
 Masquerade-1.008
 Goat-0.970
 Caps-0.909
================================================================-0.893
-0.870
Token in
Token ID287
Feature activation+7.40e-02

Pos logit contributions
 Masquerade+0.194
 Goat+0.187
 Caps+0.176
================================================================+0.171
+0.166
Neg logit contributions
itton-0.235
pez-0.226
ocard-0.223
atts-0.211
ourage-0.209
Token a
Token ID257
Feature activation+3.17e-01

Pos logit contributions
itton+0.132
pez+0.128
ocard+0.126
atts+0.119
ourage+0.118
Neg logit contributions
 Masquerade-0.113
 Goat-0.109
 Caps-0.102
================================================================-0.100
-0.098
Token land
Token ID1956
Feature activation-3.93e-01

Pos logit contributions
itton+0.555
pez+0.537
ocard+0.531
atts+0.500
ourage+0.495
Neg logit contributions
 Masquerade-0.495
 Goat-0.477
 Caps-0.446
================================================================-0.439
-0.428
Token of
Token ID286
Feature activation-5.47e-02

Pos logit contributions
 Masquerade+0.524
 Goat+0.503
 Caps+0.466
================================================================+0.456
+0.444
Neg logit contributions
itton-0.774
pez-0.751
ocard-0.745
atts-0.708
ourage-0.700
Token glaciers
Token ID40509
Feature activation-2.93e+00

Pos logit contributions
 Masquerade+0.085
 Goat+0.082
 Caps+0.077
================================================================+0.075
+0.073
Neg logit contributions
itton-0.097
pez-0.094
ocard-0.092
atts-0.087
ourage-0.086
Token,
Token ID11
Feature activation+2.26e-01

Pos logit contributions
 Masquerade+3.937
 Goat+3.802
 Caps+3.610
================================================================+3.444
+3.345
Neg logit contributions
itton-5.617
ocard-5.442
pez-5.378
ourage-5.072
atts-5.042
Token Jak
Token ID25845
Feature activation-5.60e-01

Pos logit contributions
itton+0.406
pez+0.394
ocard+0.389
atts+0.367
ourage+0.363
Neg logit contributions
 Masquerade-0.342
 Goat-0.329
 Caps-0.308
================================================================-0.302
-0.294
Tokenob
Token ID672
Feature activation+2.48e-01

Pos logit contributions
 Masquerade+1.209
 Goat+1.183
 Caps+1.135
================================================================+1.119
+1.098
Neg logit contributions
itton-0.634
pez-0.597
ocard-0.590
atts-0.536
ourage-0.527
Tokensh
Token ID1477
Feature activation+6.03e-01

Pos logit contributions
itton+0.393
pez+0.379
ocard+0.375
atts+0.350
ourage+0.346
Neg logit contributions
 Masquerade-0.429
 Goat-0.415
 Caps-0.391
================================================================-0.386
-0.377
Tokenav
Token ID615
Feature activation+8.17e-01

Pos logit contributions
itton+0.784
pez+0.751
ocard+0.740
atts+0.682
ourage+0.671
Neg logit contributions
 Masquerade-1.214
 Goat-1.178
 Caps-1.119
================================================================-1.106
-1.088
Token.
Token ID13
Feature activation+1.48e-01

Pos logit contributions
itton+1.913
pez+1.858
ocard+1.837
atts+1.744
ourage+1.731
Neg logit contributions
 Masquerade-1.372
 Goat-1.314
 Caps-1.211
================================================================-1.193
-1.163
Token
Token ID198
Feature activation+8.72e-02

Pos logit contributions
itton+0.269
pez+0.261
ocard+0.258
atts+0.244
ourage+0.241
Neg logit contributions
 Masquerade-0.222
 Goat-0.213
 Caps-0.199
================================================================-0.196
-0.191
Token
Token ID198
Feature activation-7.12e-03

Pos logit contributions
itton+0.165
pez+0.160
ocard+0.158
atts+0.149
ourage+0.148
Neg logit contributions
 Masquerade-0.125
 Goat-0.120
 Caps-0.113
================================================================-0.111
-0.106
Token
Token ID447
Feature activation+2.40e-01

Pos logit contributions
 Masquerade+0.012
 Goat+0.011
 Caps+0.010
================================================================+0.010
+0.010
Neg logit contributions
itton-0.012
pez-0.012
ocard-0.011
atts-0.011
ourage-0.011
Token
Token ID250
Feature activation+4.32e-02

Pos logit contributions
itton+0.560
pez+0.547
ocard+0.542
atts+0.519
ourage+0.514
Neg logit contributions
 Masquerade-0.236
 Goat-0.222
 Caps-0.199
================================================================-0.194
-0.186
TokenTr
Token ID2898
Feature activation+2.14e+00

Pos logit contributions
itton+0.074
pez+0.072
ocard+0.071
atts+0.066
ourage+0.065
Neg logit contributions
 Masquerade-0.069
 Goat-0.066
 Caps-0.063
================================================================-0.062
-0.060
Tokenuman
Token ID3778
Feature activation+2.27e-01

Pos logit contributions
itton+4.116
pez+3.972
ocard+3.940
atts+3.746
ourage+3.705
Neg logit contributions
 Masquerade-2.998
 Goat-2.865
 Caps-2.649
================================================================-2.604
-2.525
Token was
Token ID373
Feature activation+1.33e-02

Pos logit contributions
itton+0.423
pez+0.410
ocard+0.406
atts+0.384
ourage+0.380
Neg logit contributions
 Masquerade-0.329
 Goat-0.316
 Caps-0.295
================================================================-0.290
-0.282
Token g
Token ID308
Feature activation-4.50e-01

Pos logit contributions
itton+0.023
pez+0.022
ocard+0.022
atts+0.020
ourage+0.020
Neg logit contributions
 Masquerade-0.022
 Goat-0.021
 Caps-0.020
================================================================-0.019
-0.019
Tokenrieved
Token ID28130
Feature activation+6.03e-01

Pos logit contributions
 Masquerade+0.797
 Goat+0.776
 Caps+0.733
================================================================+0.725
+0.708
Neg logit contributions
itton-0.683
pez-0.657
ocard-0.649
atts-0.604
ourage-0.593
Token by
Token ID416
Feature activation+4.63e-02

Pos logit contributions
itton+1.030
pez+1.001
ocard+0.986
atts+0.928
ourage+0.919
Neg logit contributions
 Masquerade-0.963
 Goat-0.927
 Caps-0.867
================================================================-0.858
-0.836
Token-
Token ID12
Feature activation-2.22e-01

Pos logit contributions
 Masquerade+0.242
 Goat+0.232
 Caps+0.215
================================================================+0.210
+0.204
Neg logit contributions
itton-0.366
pez-0.356
ocard-0.352
atts-0.334
ourage-0.331
Tokenwife
Token ID22095
Feature activation-7.08e-01

Pos logit contributions
 Masquerade+0.371
 Goat+0.359
 Caps+0.337
================================================================+0.335
+0.326
Neg logit contributions
itton-0.366
pez-0.351
ocard-0.346
atts-0.325
ourage-0.319
Token of
Token ID286
Feature activation+6.49e-03

Pos logit contributions
 Masquerade+1.146
 Goat+1.109
 Caps+1.038
================================================================+1.020
+1.001
Neg logit contributions
itton-1.193
pez-1.157
ocard-1.140
atts-1.070
ourage-1.059
Token Right
Token ID6498
Feature activation+1.20e+00

Pos logit contributions
itton+0.012
pez+0.011
ocard+0.011
atts+0.010
ourage+0.010
Neg logit contributions
 Masquerade-0.010
 Goat-0.010
 Caps-0.009
================================================================-0.009
-0.009
Tokeneous
Token ID15303
Feature activation-1.46e-01

Pos logit contributions
itton+2.175
pez+2.111
ocard+2.093
atts+1.976
ourage+1.958
Neg logit contributions
 Masquerade-1.781
 Goat-1.703
 Caps-1.587
================================================================-1.575
-1.525
Token Brothers
Token ID16055
Feature activation+2.05e+00

Pos logit contributions
 Masquerade+0.233
 Goat+0.225
 Caps+0.210
================================================================+0.205
+0.200
Neg logit contributions
itton-0.252
pez-0.244
ocard-0.241
atts-0.227
ourage-0.224
Token singer
Token ID14015
Feature activation+2.89e-01

Pos logit contributions
itton+3.594
pez+3.486
ocard+3.448
atts+3.235
ourage+3.224
Neg logit contributions
 Masquerade-3.114
 Goat-2.967
================================================================-2.802
 Caps-2.799
-2.712
Token Bill
Token ID3941
Feature activation-4.04e-01

Pos logit contributions
itton+0.535
pez+0.519
ocard+0.513
atts+0.485
ourage+0.480
Neg logit contributions
 Masquerade-0.421
 Goat-0.404
 Caps-0.376
================================================================-0.370
-0.360
Token Med
Token ID2019
Feature activation+3.32e-02

Pos logit contributions
 Masquerade+0.548
 Goat+0.525
 Caps+0.486
================================================================+0.477
+0.463
Neg logit contributions
itton-0.789
pez-0.767
ocard-0.759
atts-0.719
ourage-0.713
Tokenley
Token ID1636
Feature activation+5.24e-01

Pos logit contributions
itton+0.064
pez+0.062
ocard+0.061
atts+0.058
ourage+0.058
Neg logit contributions
 Masquerade-0.046
 Goat-0.044
 Caps-0.041
================================================================-0.040
-0.039
Token,
Token ID11
Feature activation+2.69e-01

Pos logit contributions
itton+1.010
pez+0.982
ocard+0.971
atts+0.921
ourage+0.912
Neg logit contributions
 Masquerade-0.726
 Goat-0.694
 Caps-0.644
================================================================-0.634
-0.615
Token play
Token ID711
Feature activation+2.56e-01

Pos logit contributions
itton+0.006
pez+0.006
ocard+0.006
atts+0.006
ourage+0.006
Neg logit contributions
 Masquerade-0.005
 Goat-0.005
 Caps-0.005
================================================================-0.005
-0.005
Token physical
Token ID3518
Feature activation+4.87e-01

Pos logit contributions
itton+0.446
pez+0.431
ocard+0.428
atts+0.403
ourage+0.397
Neg logit contributions
 Masquerade-0.404
 Goat-0.388
 Caps-0.365
================================================================-0.355
-0.348
Token and
Token ID290
Feature activation+7.47e-02

Pos logit contributions
itton+0.924
pez+0.897
ocard+0.888
atts+0.841
ourage+0.832
Neg logit contributions
 Masquerade-0.689
 Goat-0.660
 Caps-0.614
================================================================-0.604
-0.587
Token re
Token ID302
Feature activation+1.51e+00

Pos logit contributions
itton+0.131
pez+0.128
ocard+0.126
atts+0.119
ourage+0.117
Neg logit contributions
 Masquerade-0.116
 Goat-0.111
 Caps-0.105
================================================================-0.102
-0.099
Token-
Token ID12
Feature activation+3.00e-01

Pos logit contributions
itton+2.833
pez+2.748
ocard+2.712
atts+2.572
ourage+2.553
Neg logit contributions
 Masquerade-2.168
 Goat-2.079
 Caps-1.930
================================================================-1.901
-1.851
Tokenroute
Token ID38629
Feature activation+2.08e+00

Pos logit contributions
itton+0.486
pez+0.470
ocard+0.464
atts+0.434
ourage+0.426
Neg logit contributions
 Masquerade-0.505
 Goat-0.483
 Caps-0.458
================================================================-0.454
mentation-0.441
Token Baldwin
Token ID26402
Feature activation-2.54e-01

Pos logit contributions
itton+3.530
pez+3.415
ocard+3.340
atts+3.174
ourage+3.150
Neg logit contributions
 Masquerade-3.296
 Goat-3.158
================================================================-2.957
 Caps-2.942
-2.881
Token to
Token ID284
Feature activation+2.55e-01

Pos logit contributions
 Masquerade+0.365
 Goat+0.351
 Caps+0.330
================================================================+0.319
+0.310
Neg logit contributions
itton-0.475
pez-0.460
ocard-0.460
atts-0.430
ourage-0.425
Token throw
Token ID3714
Feature activation+4.49e-01

Pos logit contributions
itton+0.447
pez+0.434
ocard+0.429
atts+0.404
ourage+0.400
Neg logit contributions
 Masquerade-0.396
 Goat-0.381
 Caps-0.357
================================================================-0.351
-0.342
Token the
Token ID262
Feature activation+3.60e-01

Pos logit contributions
itton+0.791
pez+0.766
ocard+0.760
atts+0.714
ourage+0.706
Neg logit contributions
 Masquerade-0.697
 Goat-0.671
 Caps-0.629
================================================================-0.618
-0.602
Token timing
Token ID10576
Feature activation+1.08e+00

Pos logit contributions
itton+0.715
pez+0.695
ocard+0.688
atts+0.654
ourage+0.647
Neg logit contributions
 Masquerade-0.477
 Goat-0.456
 Caps-0.421
================================================================-0.414
-0.401
Tokenhes
Token ID956
Feature activation-3.33e-02

Pos logit contributions
 Masquerade+1.440
 Goat+1.395
 Caps+1.324
================================================================+1.291
+1.271
Neg logit contributions
itton-1.355
pez-1.313
ocard-1.286
atts-1.195
ourage-1.175
Token story
Token ID1621
Feature activation+4.98e-01

Pos logit contributions
 Masquerade+0.053
 Goat+0.051
 Caps+0.048
================================================================+0.047
+0.046
Neg logit contributions
itton-0.057
pez-0.056
ocard-0.055
atts-0.052
ourage-0.051
Token"
Token ID1
Feature activation-4.31e-01

Pos logit contributions
itton+0.991
pez+0.964
ocard+0.954
atts+0.906
ourage+0.897
Neg logit contributions
 Masquerade-0.657
 Goat-0.628
 Caps-0.581
================================================================-0.570
-0.553
Token<|endoftext|>
Token ID50256
Feature activation-8.68e-01

Pos logit contributions
 Masquerade+0.594
 Goat+0.574
 Caps+0.535
================================================================+0.524
+0.511
Neg logit contributions
itton-0.828
pez-0.802
ocard-0.799
atts-0.753
ourage-0.749
Token(
Token ID7
Feature activation-1.91e-02

Pos logit contributions
 Masquerade+1.364
 Goat+1.311
================================================================+1.253
 Caps+1.234
+1.193
Neg logit contributions
itton-1.501
pez-1.444
ocard-1.430
atts-1.343
ourage-1.331
TokenPhys
Token ID43215
Feature activation+2.18e+00

Pos logit contributions
 Masquerade+0.031
 Goat+0.030
 Caps+0.029
================================================================+0.028
+0.027
Neg logit contributions
itton-0.032
pez-0.031
ocard-0.031
atts-0.029
ourage-0.028
Token.
Token ID13
Feature activation-8.51e-03

Pos logit contributions
itton+4.216
ocard+4.136
pez+4.071
atts+3.892
ourage+3.795
Neg logit contributions
 Masquerade-2.917
 Goat-2.791
 Caps-2.580
================================================================-2.572
mentation-2.465
Tokenorg
Token ID2398
Feature activation-1.99e-01

Pos logit contributions
 Masquerade+0.009
 Goat+0.008
 Caps+0.008
================================================================+0.007
+0.007
Neg logit contributions
itton-0.019
pez-0.019
ocard-0.019
atts-0.018
ourage-0.018
Token)
Token ID8
Feature activation+4.31e-02

Pos logit contributions
 Masquerade+0.284
 Goat+0.270
 Caps+0.253
================================================================+0.248
+0.241
Neg logit contributions
itton-0.374
pez-0.367
ocard-0.363
atts-0.341
ourage-0.338
Token --
Token ID1377
Feature activation-4.36e-01

Pos logit contributions
itton+0.086
pez+0.084
ocard+0.083
atts+0.079
ourage+0.078
Neg logit contributions
 Masquerade-0.056
 Goat-0.054
 Caps-0.050
================================================================-0.049
-0.048
Token An
Token ID1052
Feature activation-4.42e-01

Pos logit contributions
 Masquerade+0.659
 Goat+0.637
 Caps+0.597
================================================================+0.583
+0.565
Neg logit contributions
itton-0.791
pez-0.766
ocard-0.757
atts-0.715
ourage-0.708
Token the
Token ID262
Feature activation+2.84e-01

Pos logit contributions
itton+0.577
pez+0.559
ocard+0.553
atts+0.520
ourage+0.514
Neg logit contributions
 Masquerade-0.527
 Goat-0.509
 Caps-0.480
================================================================-0.470
-0.457
Token 73
Token ID8854
Feature activation+7.73e-01

Pos logit contributions
itton+0.486
pez+0.469
ocard+0.464
atts+0.437
ourage+0.432
Neg logit contributions
 Masquerade-0.455
 Goat-0.440
 Caps-0.414
================================================================-0.407
-0.396
Tokenrd
Token ID4372
Feature activation+2.68e-01

Pos logit contributions
itton+1.398
pez+1.356
ocard+1.340
atts+1.266
ourage+1.252
Neg logit contributions
 Masquerade-1.163
 Goat-1.116
 Caps-1.041
================================================================-1.026
-0.999
Token minute
Token ID5664
Feature activation+9.89e-01

Pos logit contributions
itton+0.435
pez+0.421
ocard+0.416
atts+0.390
ourage+0.385
Neg logit contributions
 Masquerade-0.451
 Goat-0.436
 Caps-0.411
================================================================-0.404
-0.395
Token and
Token ID290
Feature activation+5.11e-01

Pos logit contributions
itton+1.764
pez+1.711
ocard+1.690
atts+1.594
ourage+1.579
Neg logit contributions
 Masquerade-1.505
 Goat-1.446
 Caps-1.348
================================================================-1.333
-1.299
Token Ireland
Token ID7517
Feature activation+2.31e+00

Pos logit contributions
itton+0.908
pez+0.879
ocard+0.870
atts+0.822
ourage+0.810
Neg logit contributions
 Masquerade-0.788
 Goat-0.759
 Caps-0.712
================================================================-0.696
-0.678
Token also
Token ID635
Feature activation+1.93e-01

Pos logit contributions
itton+3.992
pez+3.877
ocard+3.811
atts+3.593
ourage+3.561
Neg logit contributions
 Masquerade-3.625
 Goat-3.478
 Caps-3.228
================================================================-3.216
-3.128
Token had
Token ID550
Feature activation+4.41e-01

Pos logit contributions
itton+0.333
pez+0.321
ocard+0.321
atts+0.301
ourage+0.297
Neg logit contributions
 Masquerade-0.307
 Goat-0.295
 Caps-0.279
================================================================-0.272
-0.266
Token a
Token ID257
Feature activation+4.96e-01

Pos logit contributions
itton+0.773
pez+0.749
ocard+0.740
atts+0.698
ourage+0.690
Neg logit contributions
 Masquerade-0.689
 Goat-0.665
 Caps-0.624
================================================================-0.611
-0.595
Token number
Token ID1271
Feature activation+3.87e-01

Pos logit contributions
itton+0.826
pez+0.798
ocard+0.789
atts+0.743
ourage+0.733
Neg logit contributions
 Masquerade-0.819
 Goat-0.791
 Caps-0.746
================================================================-0.729
-0.712
Token of
Token ID286
Feature activation+3.90e-01

Pos logit contributions
itton+0.644
pez+0.624
ocard+0.616
atts+0.579
ourage+0.572
Neg logit contributions
 Masquerade-0.637
 Goat-0.615
 Caps-0.577
================================================================-0.568
-0.556
Token a
Token ID257
Feature activation+3.97e-01

Pos logit contributions
itton+0.794
pez+0.772
ocard+0.764
atts+0.722
ourage+0.713
Neg logit contributions
 Masquerade-0.664
 Goat-0.641
 Caps-0.604
================================================================-0.591
-0.573
Token failed
Token ID4054
Feature activation+5.04e-01

Pos logit contributions
itton+0.676
pez+0.653
ocard+0.647
atts+0.609
ourage+0.602
Neg logit contributions
 Masquerade-0.637
 Goat-0.616
 Caps-0.580
================================================================-0.568
-0.556
Token sensor
Token ID12694
Feature activation+5.90e-01

Pos logit contributions
itton+0.812
pez+0.784
ocard+0.773
atts+0.725
ourage+0.717
Neg logit contributions
 Masquerade-0.861
 Goat-0.831
 Caps-0.787
================================================================-0.770
-0.752
Token providing
Token ID4955
Feature activation+7.98e-01

Pos logit contributions
itton+1.041
pez+1.010
ocard+0.995
atts+0.940
ourage+0.930
Neg logit contributions
 Masquerade-0.913
 Goat-0.879
 Caps-0.826
================================================================-0.812
-0.790
Token false
Token ID3991
Feature activation+5.04e-01

Pos logit contributions
itton+1.312
pez+1.264
ocard+1.251
atts+1.168
ourage+1.158
Neg logit contributions
 Masquerade-1.339
 Goat-1.295
 Caps-1.222
================================================================-1.200
-1.170
Token information
Token ID1321
Feature activation+1.90e-01

Pos logit contributions
itton+0.809
pez+0.779
ocard+0.770
atts+0.717
ourage+0.711
Neg logit contributions
 Masquerade-0.865
 Goat-0.837
 Caps-0.791
================================================================-0.776
-0.757
Token,
Token ID11
Feature activation+6.02e-01

Pos logit contributions
itton+0.353
pez+0.341
ocard+0.337
atts+0.318
ourage+0.315
Neg logit contributions
 Masquerade-0.279
 Goat-0.268
 Caps-0.251
================================================================-0.245
-0.237
Token which
Token ID543
Feature activation+9.20e-01

Pos logit contributions
itton+1.054
pez+1.021
ocard+1.008
atts+0.949
ourage+0.938
Neg logit contributions
 Masquerade-0.942
 Goat-0.910
 Caps-0.854
================================================================-0.838
-0.816
Token Remote
Token ID21520
Feature activation+1.07e+00

Pos logit contributions
itton+1.563
pez+1.513
ocard+1.494
atts+1.404
ourage+1.388
Neg logit contributions
 Masquerade-1.489
 Goat-1.436
 Caps-1.352
================================================================-1.328
-1.296
Token Agent
Token ID15906
Feature activation+7.36e-01

Pos logit contributions
itton+1.734
pez+1.676
ocard+1.662
atts+1.556
ourage+1.542
Neg logit contributions
 Masquerade-1.797
 Goat-1.725
 Caps-1.617
================================================================-1.609
-1.583
Token recognized
Token ID8018
Feature activation+6.76e-01

Pos logit contributions
itton+1.295
pez+1.255
ocard+1.244
atts+1.168
ourage+1.157
Neg logit contributions
 Masquerade-1.140
 Goat-1.099
 Caps-1.033
================================================================-1.015
-0.988
Token
Token ID198
Feature activation+5.11e-02

Pos logit contributions
itton+0.155
pez+0.150
ocard+0.149
atts+0.140
ourage+0.139
Neg logit contributions
 Masquerade-0.129
 Goat-0.124
 Caps-0.116
================================================================-0.114
-0.111
Token
Token ID198
Feature activation-5.22e-02

Pos logit contributions
itton+0.097
pez+0.094
ocard+0.093
atts+0.088
ourage+0.087
Neg logit contributions
 Masquerade-0.073
 Goat-0.070
 Caps-0.066
================================================================-0.065
-0.062
TokenThe
Token ID464
Feature activation-2.21e-01

Pos logit contributions
 Masquerade+0.083
 Goat+0.080
 Caps+0.075
================================================================+0.075
+0.072
Neg logit contributions
itton-0.091
pez-0.087
ocard-0.087
atts-0.081
ourage-0.080
Token city
Token ID1748
Feature activation-6.09e-01

Pos logit contributions
 Masquerade+0.332
 Goat+0.320
 Caps+0.299
================================================================+0.292
+0.285
Neg logit contributions
itton-0.402
pez-0.390
ocard-0.385
atts-0.363
ourage-0.360
Token is
Token ID318
Feature activation-1.70e-01

Pos logit contributions
 Masquerade+0.909
 Goat+0.875
 Caps+0.820
================================================================+0.801
+0.784
Neg logit contributions
itton-1.105
pez-1.069
ocard-1.061
atts-1.001
ourage-0.990
Token claiming
Token ID8512
Feature activation+3.86e-01

Pos logit contributions
 Masquerade+0.280
 Goat+0.271
 Caps+0.256
================================================================+0.250
+0.246
Neg logit contributions
itton-0.283
pez-0.274
ocard-0.273
atts-0.254
ourage-0.252
Token at
Token ID379
Feature activation-9.41e-01

Pos logit contributions
itton+0.724
pez+0.703
ocard+0.696
atts+0.658
ourage+0.651
Neg logit contributions
 Masquerade-0.554
 Goat-0.533
 Caps-0.495
================================================================-0.486
-0.473
Token least
Token ID1551
Feature activation+1.61e-01

Pos logit contributions
 Masquerade+1.287
 Goat+1.242
 Caps+1.148
================================================================+1.117
+1.088
Neg logit contributions
itton-1.826
pez-1.778
ocard-1.756
atts-1.665
ourage-1.651
Token short
Token ID1790
Feature activation-3.78e-01

Pos logit contributions
itton+0.274
pez+0.265
ocard+0.263
atts+0.247
ourage+0.244
Neg logit contributions
 Masquerade-0.260
 Goat-0.251
 Caps-0.235
================================================================-0.231
-0.226
Token-
Token ID12
Feature activation+4.96e-03

Pos logit contributions
 Masquerade+0.486
 Goat+0.468
 Caps+0.432
================================================================+0.419
+0.410
Neg logit contributions
itton-0.762
pez-0.744
ocard-0.736
atts-0.699
ourage-0.693
Tokenterm
Token ID4354
Feature activation+5.98e-01

Pos logit contributions
itton+0.011
pez+0.011
ocard+0.011
atts+0.010
ourage+0.010
Neg logit contributions
 Masquerade-0.005
 Goat-0.005
 Caps-0.005
================================================================-0.005
-0.004
Token we
Token ID356
Feature activation+3.87e-01

Pos logit contributions
 Masquerade+0.905
 Goat+0.878
 Caps+0.824
================================================================+0.791
+0.774
Neg logit contributions
itton-1.183
pez-1.152
ocard-1.138
atts-1.082
ourage-1.064
Token
Token ID447
Feature activation+3.58e-01

Pos logit contributions
itton+0.694
pez+0.673
ocard+0.666
atts+0.628
ourage+0.621
Neg logit contributions
 Masquerade-0.585
 Goat-0.563
 Caps-0.528
================================================================-0.519
-0.506
Token
Token ID247
Feature activation+2.14e-01

Pos logit contributions
itton+0.571
pez+0.553
ocard+0.544
atts+0.509
ourage+0.503
Neg logit contributions
 Masquerade-0.614
 Goat-0.592
 Caps-0.559
================================================================-0.549
-0.531
Tokenre
Token ID260
Feature activation+5.97e-01

Pos logit contributions
itton+0.387
pez+0.374
ocard+0.371
atts+0.350
ourage+0.346
Neg logit contributions
 Masquerade-0.322
 Goat-0.309
 Caps-0.289
================================================================-0.285
-0.278
Token learning
Token ID4673
Feature activation+2.03e-01

Pos logit contributions
itton+1.038
pez+1.004
ocard+0.997
atts+0.934
ourage+0.927
Neg logit contributions
 Masquerade-0.935
 Goat-0.902
 Caps-0.850
================================================================-0.836
-0.815
Token.
Token ID13
Feature activation+2.66e-01

Pos logit contributions
itton+0.352
pez+0.342
ocard+0.338
atts+0.318
ourage+0.314
Neg logit contributions
 Masquerade-0.320
 Goat-0.308
 Caps-0.289
================================================================-0.284
-0.277
Token We
Token ID775
Feature activation+4.91e-01

Pos logit contributions
itton+0.491
pez+0.477
ocard+0.471
atts+0.446
ourage+0.441
Neg logit contributions
 Masquerade-0.390
 Goat-0.375
 Caps-0.349
================================================================-0.343
-0.334
Token learned
Token ID4499
Feature activation+4.91e-01

Pos logit contributions
itton+0.890
pez+0.864
ocard+0.855
atts+0.807
ourage+0.798
Neg logit contributions
 Masquerade-0.735
 Goat-0.706
 Caps-0.661
================================================================-0.650
-0.634
Token a
Token ID257
Feature activation+4.98e-01

Pos logit contributions
itton+0.860
pez+0.835
ocard+0.829
atts+0.781
ourage+0.767
Neg logit contributions
 Masquerade-0.768
 Goat-0.740
 Caps-0.695
================================================================-0.679
-0.661
Token lot
Token ID1256
Feature activation-6.15e-01

Pos logit contributions
itton+0.915
pez+0.889
ocard+0.879
atts+0.832
ourage+0.822
Neg logit contributions
 Masquerade-0.734
 Goat-0.705
 Caps-0.657
================================================================-0.645
-0.629
Token once
Token ID1752
Feature activation-4.94e-01

Pos logit contributions
 Masquerade+0.934
 Goat+0.899
 Caps+0.847
================================================================+0.825
+0.798
Neg logit contributions
itton-1.100
pez-1.068
ocard-1.059
atts-0.997
ourage-0.985
Token and
Token ID290
Feature activation+2.67e-01

Pos logit contributions
itton+0.383
pez+0.372
ocard+0.367
atts+0.347
ourage+0.345
Neg logit contributions
 Masquerade-0.283
 Goat-0.272
 Caps-0.253
================================================================-0.248
-0.241
Token scar
Token ID10153
Feature activation-1.33e+00

Pos logit contributions
itton+0.485
pez+0.470
ocard+0.462
atts+0.439
ourage+0.433
Neg logit contributions
 Masquerade-0.402
 Goat-0.388
 Caps-0.362
================================================================-0.354
-0.346
Tokenring
Token ID1806
Feature activation-8.17e-01

Pos logit contributions
 Masquerade+1.545
 Goat+1.468
 Caps+1.338
================================================================+1.315
mentation+1.271
Neg logit contributions
itton-2.861
pez-2.782
ocard-2.754
atts-2.633
ourage-2.608
Token if
Token ID611
Feature activation+5.71e-01

Pos logit contributions
 Masquerade+1.165
 Goat+1.124
 Caps+1.044
================================================================+1.028
+0.987
Neg logit contributions
itton-1.535
pez-1.491
ocard-1.467
atts-1.385
ourage-1.377
Token she
Token ID673
Feature activation+1.22e-02

Pos logit contributions
itton+1.033
pez+1.002
ocard+0.992
atts+0.938
ourage+0.928
Neg logit contributions
 Masquerade-0.854
 Goat-0.819
 Caps-0.763
================================================================-0.755
-0.735
Token didn
Token ID1422
Feature activation+9.07e-01

Pos logit contributions
itton+0.021
pez+0.021
ocard+0.020
atts+0.019
ourage+0.019
Neg logit contributions
 Masquerade-0.019
 Goat-0.018
 Caps-0.017
================================================================-0.017
-0.017
Token't
Token ID470
Feature activation-1.97e-01

Pos logit contributions
itton+1.550
pez+1.500
ocard+1.483
atts+1.395
ourage+1.379
Neg logit contributions
 Masquerade-1.454
 Goat-1.401
 Caps-1.315
================================================================-1.297
-1.263
Token act
Token ID719
Feature activation+1.33e-02

Pos logit contributions
 Masquerade+0.294
 Goat+0.284
 Caps+0.265
================================================================+0.260
+0.252
Neg logit contributions
itton-0.356
pez-0.345
ocard-0.342
atts-0.322
ourage-0.318
Token right
Token ID826
Feature activation+1.00e+00

Pos logit contributions
itton+0.022
pez+0.021
ocard+0.021
atts+0.020
ourage+0.019
Neg logit contributions
 Masquerade-0.022
 Goat-0.021
 Caps-0.020
================================================================-0.020
-0.019
Token away
Token ID1497
Feature activation+3.72e-01

Pos logit contributions
itton+1.831
pez+1.778
ocard+1.760
atts+1.664
ourage+1.647
Neg logit contributions
 Masquerade-1.480
 Goat-1.420
 Caps-1.323
================================================================-1.305
-1.270
Token'
Token ID6
Feature activation+1.56e-01

Pos logit contributions
itton+0.698
pez+0.677
ocard+0.670
atts+0.635
ourage+0.628
Neg logit contributions
 Masquerade-0.533
 Goat-0.510
 Caps-0.474
================================================================-0.467
-0.455
Token**
Token ID1174
Feature activation+2.49e-01

Pos logit contributions
 Masquerade+0.412
 Goat+0.396
================================================================+0.373
 Caps+0.372
+0.358
Neg logit contributions
itton-0.467
pez-0.451
ocard-0.446
atts-0.420
ourage-0.415
Token In
Token ID554
Feature activation-5.49e-01

Pos logit contributions
itton+0.441
pez+0.428
ocard+0.423
atts+0.399
ourage+0.394
Neg logit contributions
 Masquerade-0.384
 Goat-0.369
 Caps-0.346
================================================================-0.341
-0.331
Token many
Token ID867
Feature activation-7.26e-01

Pos logit contributions
 Masquerade+0.845
 Goat+0.816
 Caps+0.765
================================================================+0.750
+0.731
Neg logit contributions
itton-0.975
pez-0.943
ocard-0.933
atts-0.878
ourage-0.870
Token banks
Token ID6341
Feature activation+1.76e-01

Pos logit contributions
 Masquerade+1.200
 Goat+1.155
 Caps+1.094
================================================================+1.069
+1.040
Neg logit contributions
itton-1.211
pez-1.162
ocard-1.149
atts-1.087
ourage-1.075
Token one
Token ID530
Feature activation+1.67e-01

Pos logit contributions
itton+0.322
pez+0.312
ocard+0.310
atts+0.293
ourage+0.289
Neg logit contributions
 Masquerade-0.262
 Goat-0.251
 Caps-0.235
================================================================-0.231
-0.225
Token doesn
Token ID1595
Feature activation+3.79e-01

Pos logit contributions
itton+0.308
pez+0.298
ocard+0.295
atts+0.279
ourage+0.277
Neg logit contributions
 Masquerade-0.247
 Goat-0.238
 Caps-0.222
================================================================-0.218
-0.212
Token't
Token ID470
Feature activation-2.86e-01

Pos logit contributions
itton+0.664
pez+0.642
ocard+0.637
atts+0.598
ourage+0.592
Neg logit contributions
 Masquerade-0.591
 Goat-0.569
 Caps-0.535
================================================================-0.530
-0.511
Token need
Token ID761
Feature activation-1.69e-01

Pos logit contributions
 Masquerade+0.392
 Goat+0.375
 Caps+0.351
================================================================+0.341
+0.327
Neg logit contributions
itton-0.554
pez-0.539
ocard-0.534
atts-0.506
ourage-0.501
Token to
Token ID284
Feature activation+1.01e-01

Pos logit contributions
 Masquerade+0.244
 Goat+0.235
 Caps+0.218
================================================================+0.215
+0.209
Neg logit contributions
itton-0.317
pez-0.308
ocard-0.304
atts-0.287
ourage-0.285
Token take
Token ID1011
Feature activation+7.72e-01

Pos logit contributions
itton+0.177
pez+0.172
ocard+0.170
atts+0.160
ourage+0.158
Neg logit contributions
 Masquerade-0.158
 Goat-0.152
 Caps-0.143
================================================================-0.139
-0.135
Token any
Token ID597
Feature activation-6.69e-01

Pos logit contributions
itton+1.365
pez+1.321
ocard+1.305
atts+1.232
ourage+1.217
Neg logit contributions
 Masquerade-1.194
 Goat-1.150
 Caps-1.077
================================================================-1.056
-1.032
Token went
Token ID1816
Feature activation+1.50e-01

Pos logit contributions
itton+0.009
pez+0.009
ocard+0.008
atts+0.008
ourage+0.008
Neg logit contributions
 Masquerade-0.008
 Goat-0.008
 Caps-0.007
================================================================-0.007
-0.007
Token to
Token ID284
Feature activation-9.73e-03

Pos logit contributions
itton+0.278
pez+0.269
ocard+0.268
atts+0.252
ourage+0.249
Neg logit contributions
 Masquerade-0.218
 Goat-0.210
 Caps-0.196
================================================================-0.192
-0.187
Token bat
Token ID7365
Feature activation-7.83e-01

Pos logit contributions
 Masquerade+0.015
 Goat+0.015
 Caps+0.014
================================================================+0.013
+0.013
Neg logit contributions
itton-0.017
pez-0.017
ocard-0.017
atts-0.016
ourage-0.015
Token for
Token ID329
Feature activation+3.03e-01

Pos logit contributions
 Masquerade+1.213
 Goat+1.185
 Caps+1.104
================================================================+1.082
+1.050
Neg logit contributions
itton-1.366
pez-1.318
ocard-1.298
atts-1.214
ourage-1.201
Token a
Token ID257
Feature activation+3.51e-01

Pos logit contributions
itton+0.549
pez+0.532
ocard+0.527
atts+0.497
ourage+0.491
Neg logit contributions
 Masquerade-0.455
 Goat-0.440
 Caps-0.410
================================================================-0.400
-0.392
Token community
Token ID2055
Feature activation-5.52e-01

Pos logit contributions
itton+0.624
pez+0.604
ocard+0.598
atts+0.564
ourage+0.557
Neg logit contributions
 Masquerade-0.539
 Goat-0.518
 Caps-0.485
================================================================-0.477
-0.465
Token resident
Token ID6623
Feature activation+9.56e-01

Pos logit contributions
 Masquerade+0.849
 Goat+0.824
 Caps+0.768
================================================================+0.754
+0.733
Neg logit contributions
itton-0.970
pez-0.942
ocard-0.933
atts-0.880
ourage-0.866
Token after
Token ID706
Feature activation-2.83e-01

Pos logit contributions
itton+1.714
pez+1.660
ocard+1.645
atts+1.553
ourage+1.538
Neg logit contributions
 Masquerade-1.445
 Goat-1.378
 Caps-1.294
================================================================-1.281
-1.247
Token the
Token ID262
Feature activation+3.70e-02

Pos logit contributions
 Masquerade+0.436
 Goat+0.421
 Caps+0.392
================================================================+0.382
+0.375
Neg logit contributions
itton-0.501
pez-0.486
ocard-0.481
atts-0.453
ourage-0.448
Token D
Token ID360
Feature activation-3.57e-01

Pos logit contributions
itton+0.066
pez+0.064
ocard+0.063
atts+0.059
ourage+0.059
Neg logit contributions
 Masquerade-0.057
 Goat-0.055
 Caps-0.051
================================================================-0.050
-0.049
TokenNR
Token ID24723
Feature activation+1.38e+00

Pos logit contributions
 Masquerade+0.610
 Goat+0.594
 Caps+0.559
================================================================+0.553
+0.538
Neg logit contributions
itton-0.560
pez-0.544
ocard-0.537
atts-0.501
ourage-0.495
Token Barron
Token ID47412
Feature activation-9.89e-01

Pos logit contributions
itton+3.169
pez+3.083
ocard+3.050
atts+2.899
ourage+2.861
Neg logit contributions
 Masquerade-2.172
 Goat-2.056
================================================================-1.920
 Caps-1.910
-1.860
Token,
Token ID11
Feature activation-2.68e-01

Pos logit contributions
 Masquerade+1.387
 Goat+1.344
 Caps+1.247
================================================================+1.213
+1.191
Neg logit contributions
itton-1.856
pez-1.816
ocard-1.795
atts-1.695
ourage-1.677
Token director
Token ID3437
Feature activation+6.24e-01

Pos logit contributions
 Masquerade+0.382
 Goat+0.368
 Caps+0.343
================================================================+0.335
+0.326
Neg logit contributions
itton-0.505
pez-0.490
ocard-0.485
atts-0.459
ourage-0.453
Token of
Token ID286
Feature activation-1.00e-01

Pos logit contributions
itton+1.006
pez+0.974
ocard+0.963
atts+0.906
ourage+0.894
Neg logit contributions
 Masquerade-1.056
 Goat-1.018
 Caps-0.959
================================================================-0.946
-0.923
Token the
Token ID262
Feature activation-1.44e-01

Pos logit contributions
 Masquerade+0.155
 Goat+0.149
 Caps+0.140
================================================================+0.138
+0.134
Neg logit contributions
itton-0.177
pez-0.171
ocard-0.169
atts-0.159
ourage-0.158
Token new
Token ID649
Feature activation+7.70e-02

Pos logit contributions
 Masquerade+0.198
 Goat+0.190
 Caps+0.176
================================================================+0.172
+0.166
Neg logit contributions
itton-0.281
pez-0.273
ocard-0.270
atts-0.255
ourage-0.253
Token law
Token ID1099
Feature activation-7.00e-01

Pos logit contributions
itton+0.140
pez+0.135
ocard+0.134
atts+0.127
ourage+0.125
Neg logit contributions
 Masquerade-0.115
 Goat-0.110
 Caps-0.103
================================================================-0.102
-0.099
Token center
Token ID3641
Feature activation+6.37e-01

Pos logit contributions
 Masquerade+1.101
 Goat+1.060
 Caps+0.996
================================================================+0.977
+0.955
Neg logit contributions
itton-1.211
pez-1.176
ocard-1.159
atts-1.091
ourage-1.076
Token.
Token ID13
Feature activation+1.35e-01

Pos logit contributions
itton+1.239
pez+1.203
ocard+1.192
atts+1.132
ourage+1.122
Neg logit contributions
 Masquerade-0.868
 Goat-0.830
 Caps-0.769
================================================================-0.757
-0.735
Token
Token ID564
Feature activation-5.98e-01

Pos logit contributions
itton+0.242
pez+0.235
ocard+0.232
atts+0.219
ourage+0.217
Neg logit contributions
 Masquerade-0.206
 Goat-0.197
 Caps-0.184
================================================================-0.182
-0.177
Token
Token ID250
Feature activation-1.69e-01

Pos logit contributions
 Masquerade+0.578
 Goat+0.545
 Caps+0.487
================================================================+0.481
+0.469
Neg logit contributions
itton-1.400
pez-1.366
ocard-1.357
atts-1.299
ourage-1.288
Token the
Token ID262
Feature activation+1.30e-01

Pos logit contributions
 Masquerade+0.016
 Goat+0.015
 Caps+0.014
================================================================+0.014
+0.014
Neg logit contributions
itton-0.019
pez-0.018
ocard-0.018
atts-0.017
ourage-0.017
Token asteroid
Token ID27460
Feature activation-5.80e-01

Pos logit contributions
itton+0.227
pez+0.220
ocard+0.217
atts+0.205
ourage+0.203
Neg logit contributions
 Masquerade-0.204
 Goat-0.197
 Caps-0.184
================================================================-0.181
-0.177
Token 99
Token ID7388
Feature activation+4.04e-01

Pos logit contributions
 Masquerade+0.942
 Goat+0.917
 Caps+0.863
================================================================+0.842
+0.820
Neg logit contributions
itton-0.975
pez-0.946
ocard-0.937
atts-0.881
ourage-0.869
Token69
Token ID3388
Feature activation+1.04e+00

Pos logit contributions
itton+0.734
pez+0.712
ocard+0.704
atts+0.664
ourage+0.658
Neg logit contributions
 Masquerade-0.602
 Goat-0.577
 Caps-0.539
================================================================-0.531
-0.517
Token Bra
Token ID9718
Feature activation-4.51e-01

Pos logit contributions
itton+1.837
pez+1.776
ocard+1.756
atts+1.657
ourage+1.642
Neg logit contributions
 Masquerade-1.589
 Goat-1.519
 Caps-1.415
================================================================-1.406
-1.368
Tokenille
Token ID8270
Feature activation-8.54e-01

Pos logit contributions
 Masquerade+0.523
 Goat+0.495
================================================================+0.453
 Caps+0.451
+0.432
Neg logit contributions
itton-0.955
pez-0.931
ocard-0.928
atts-0.885
ourage-0.876
Token was
Token ID373
Feature activation+1.76e-01

Pos logit contributions
 Masquerade+1.269
 Goat+1.223
 Caps+1.155
================================================================+1.117
+1.083
Neg logit contributions
itton-1.561
pez-1.511
ocard-1.503
atts-1.412
ourage-1.395
Token only
Token ID691
Feature activation+6.43e-01

Pos logit contributions
itton+0.297
pez+0.286
ocard+0.286
atts+0.267
ourage+0.265
Neg logit contributions
 Masquerade-0.283
 Goat-0.275
 Caps-0.260
================================================================-0.253
-0.246
Token a
Token ID257
Feature activation+2.42e-01

Pos logit contributions
itton+1.105
pez+1.066
ocard+1.062
atts+0.995
ourage+0.984
Neg logit contributions
 Masquerade-1.026
 Goat-0.991
 Caps-0.934
================================================================-0.911
-0.891
Token partial
Token ID13027
Feature activation+3.88e-02

Pos logit contributions
itton+0.421
pez+0.407
ocard+0.404
atts+0.381
ourage+0.377
Neg logit contributions
 Masquerade-0.383
 Goat-0.370
 Caps-0.347
================================================================-0.337
-0.331
Token success
Token ID1943
Feature activation+3.35e-01

Pos logit contributions
itton+0.071
pez+0.069
ocard+0.068
atts+0.064
ourage+0.064
Neg logit contributions
 Masquerade-0.057
 Goat-0.055
 Caps-0.051
================================================================-0.051
-0.049
Token fully
Token ID3938
Feature activation-1.44e+00

Pos logit contributions
itton+0.132
pez+0.128
ocard+0.126
atts+0.118
ourage+0.117
Neg logit contributions
 Masquerade-0.126
 Goat-0.122
 Caps-0.115
================================================================-0.113
-0.110
Token aware
Token ID3910
Feature activation-8.20e-01

Pos logit contributions
 Masquerade+1.963
 Goat+1.874
 Caps+1.764
================================================================+1.705
+1.658
Neg logit contributions
itton-2.784
pez-2.721
ocard-2.676
atts-2.525
ourage-2.509
Token that
Token ID326
Feature activation+6.03e-03

Pos logit contributions
 Masquerade+1.231
 Goat+1.183
 Caps+1.115
================================================================+1.092
+1.068
Neg logit contributions
itton-1.478
pez-1.428
ocard-1.414
atts-1.334
ourage-1.321
Token more
Token ID517
Feature activation-1.59e-01

Pos logit contributions
itton+0.011
pez+0.011
ocard+0.010
atts+0.010
ourage+0.010
Neg logit contributions
 Masquerade-0.009
 Goat-0.009
 Caps-0.008
================================================================-0.008
-0.008
Token subsidies
Token ID16230
Feature activation+2.87e-01

Pos logit contributions
 Masquerade+0.222
 Goat+0.213
 Caps+0.198
================================================================+0.195
+0.189
Neg logit contributions
itton-0.304
pez-0.295
ocard-0.292
atts-0.276
ourage-0.274
Token will
Token ID481
Feature activation-2.64e-01

Pos logit contributions
itton+0.521
pez+0.504
ocard+0.499
atts+0.472
ourage+0.466
Neg logit contributions
 Masquerade-0.431
 Goat-0.415
 Caps-0.388
================================================================-0.381
-0.371
Token only
Token ID691
Feature activation+4.40e-01

Pos logit contributions
 Masquerade+0.391
 Goat+0.378
 Caps+0.357
================================================================+0.345
+0.335
Neg logit contributions
itton-0.480
pez-0.463
ocard-0.460
atts-0.437
ourage-0.430
Token exacerbate
Token ID49522
Feature activation+6.29e-01

Pos logit contributions
itton+0.797
pez+0.766
ocard+0.762
atts+0.720
ourage+0.710
Neg logit contributions
 Masquerade-0.663
 Goat-0.640
 Caps-0.600
================================================================-0.583
-0.568
Token their
Token ID511
Feature activation+5.49e-01

Pos logit contributions
itton+1.074
pez+1.039
ocard+1.028
atts+0.967
ourage+0.956
Neg logit contributions
 Masquerade-1.007
 Goat-0.970
 Caps-0.909
================================================================-0.897
-0.875
Token pain
Token ID2356
Feature activation-2.76e-01

Pos logit contributions
itton+0.867
pez+0.835
ocard+0.818
atts+0.769
ourage+0.762
Neg logit contributions
 Masquerade-0.958
 Goat-0.925
 Caps-0.879
================================================================-0.863
-0.840
Token.
Token ID13
Feature activation-2.58e-01

Pos logit contributions
 Masquerade+0.378
 Goat+0.363
 Caps+0.337
================================================================+0.332
+0.321
Neg logit contributions
itton-0.536
pez-0.519
ocard-0.514
atts-0.488
ourage-0.483
Token received
Token ID2722
Feature activation+1.03e-01

Pos logit contributions
itton+0.376
pez+0.363
ocard+0.359
atts+0.338
ourage+0.334
Neg logit contributions
 Masquerade-0.357
 Goat-0.344
 Caps-0.323
================================================================-0.317
-0.309
Token.
Token ID13
Feature activation+6.34e-02

Pos logit contributions
itton+0.183
pez+0.176
ocard+0.174
atts+0.164
ourage+0.162
Neg logit contributions
 Masquerade-0.160
 Goat-0.154
 Caps-0.144
================================================================-0.142
-0.138
Token I
Token ID314
Feature activation-1.10e-01

Pos logit contributions
itton+0.116
pez+0.113
ocard+0.111
atts+0.105
ourage+0.104
Neg logit contributions
 Masquerade-0.095
 Goat-0.091
 Caps-0.085
================================================================-0.084
-0.081
Token wanted
Token ID2227
Feature activation-3.79e-01

Pos logit contributions
 Masquerade+0.172
 Goat+0.167
 Caps+0.156
================================================================+0.153
+0.148
Neg logit contributions
itton-0.192
pez-0.186
ocard-0.183
atts-0.173
ourage-0.171
Token to
Token ID284
Feature activation+6.13e-02

Pos logit contributions
 Masquerade+0.526
 Goat+0.506
 Caps+0.470
================================================================+0.461
+0.446
Neg logit contributions
itton-0.728
pez-0.707
ocard-0.698
atts-0.662
ourage-0.656
Token learn
Token ID2193
Feature activation-5.36e-02

Pos logit contributions
itton+0.109
pez+0.106
ocard+0.104
atts+0.099
ourage+0.098
Neg logit contributions
 Masquerade-0.093
 Goat-0.090
 Caps-0.084
================================================================-0.083
-0.080
Token more
Token ID517
Feature activation+3.58e-01

Pos logit contributions
 Masquerade+0.076
 Goat+0.073
 Caps+0.067
================================================================+0.066
+0.064
Neg logit contributions
itton-0.102
pez-0.099
ocard-0.098
atts-0.093
ourage-0.092
Token about
Token ID546
Feature activation+4.18e-01

Pos logit contributions
itton+0.678
pez+0.659
ocard+0.652
atts+0.617
ourage+0.611
Neg logit contributions
 Masquerade-0.506
 Goat-0.485
 Caps-0.451
================================================================-0.444
-0.431
Token social
Token ID1919
Feature activation-7.12e-02

Pos logit contributions
itton+0.760
pez+0.736
ocard+0.728
atts+0.688
ourage+0.680
Neg logit contributions
 Masquerade-0.625
 Goat-0.601
 Caps-0.561
================================================================-0.551
-0.536
Token justice
Token ID5316
Feature activation-1.05e+00

Pos logit contributions
 Masquerade+0.116
 Goat+0.112
 Caps+0.105
================================================================+0.103
+0.101
Neg logit contributions
itton-0.120
pez-0.116
ocard-0.115
atts-0.108
ourage-0.106
Token from
Token ID422
Feature activation+2.53e-01

Pos logit contributions
 Masquerade+1.495
 Goat+1.447
 Caps+1.341
================================================================+1.310
mentation+1.264
Neg logit contributions
itton-1.953
pez-1.897
ocard-1.883
atts-1.766
ourage-1.748
Token thing
Token ID1517
Feature activation-1.47e-01

Pos logit contributions
 Masquerade+0.822
 Goat+0.791
 Caps+0.733
================================================================+0.715
+0.692
Neg logit contributions
itton-1.142
pez-1.102
ocard-1.094
atts-1.037
ourage-1.026
Token I
Token ID314
Feature activation+2.22e-01

Pos logit contributions
 Masquerade+0.214
 Goat+0.206
 Caps+0.192
================================================================+0.189
+0.183
Neg logit contributions
itton-0.272
pez-0.264
ocard-0.261
atts-0.247
ourage-0.244
Token knew
Token ID2993
Feature activation-1.32e-01

Pos logit contributions
itton+0.455
pez+0.443
ocard+0.439
atts+0.417
ourage+0.414
Neg logit contributions
 Masquerade-0.281
 Goat-0.268
 Caps-0.246
================================================================-0.242
-0.234
Token you
Token ID345
Feature activation+5.13e-01

Pos logit contributions
 Masquerade+0.193
 Goat+0.186
 Caps+0.173
================================================================+0.170
+0.165
Neg logit contributions
itton-0.243
pez-0.236
ocard-0.233
atts-0.220
ourage-0.218
Token were
Token ID547
Feature activation+6.66e-01

Pos logit contributions
itton+0.907
pez+0.878
ocard+0.869
atts+0.819
ourage+0.810
Neg logit contributions
 Masquerade-0.791
 Goat-0.761
 Caps-0.711
================================================================-0.701
-0.683
Token melting
Token ID24203
Feature activation-1.71e+00

Pos logit contributions
itton+1.123
pez+1.087
ocard+1.074
atts+1.010
ourage+0.998
Neg logit contributions
 Masquerade-1.082
 Goat-1.043
 Caps-0.979
================================================================-0.966
-0.942
Token me
Token ID502
Feature activation-2.74e-01

Pos logit contributions
 Masquerade+2.536
 Goat+2.471
 Caps+2.315
================================================================+2.227
+2.157
Neg logit contributions
itton-3.102
pez-2.999
ocard-2.959
ourage-2.798
atts-2.793
Token from
Token ID422
Feature activation+1.82e-01

Pos logit contributions
 Masquerade+0.425
 Goat+0.409
 Caps+0.383
================================================================+0.377
+0.367
Neg logit contributions
itton-0.482
pez-0.467
ocard-0.461
atts-0.435
ourage-0.430
Token the
Token ID262
Feature activation-2.26e-02

Pos logit contributions
itton+0.318
pez+0.308
ocard+0.304
atts+0.287
ourage+0.284
Neg logit contributions
 Masquerade-0.285
 Goat-0.274
 Caps-0.257
================================================================-0.253
-0.247
Token ice
Token ID4771
Feature activation-1.92e+00

Pos logit contributions
 Masquerade+0.034
 Goat+0.033
 Caps+0.031
================================================================+0.030
+0.030
Neg logit contributions
itton-0.040
pez-0.039
ocard-0.039
atts-0.037
ourage-0.036
Token
Token ID198
Feature activation+8.48e-01

Pos logit contributions
 Masquerade+2.776
 Goat+2.688
 Caps+2.523
================================================================+2.436
+2.374
Neg logit contributions
itton-3.569
pez-3.443
ocard-3.409
atts-3.239
ourage-3.190
Token many
Token ID867
Feature activation-4.35e-01

Pos logit contributions
itton+0.510
pez+0.492
ocard+0.484
atts+0.455
ourage+0.448
Neg logit contributions
 Masquerade-0.529
 Goat-0.511
 Caps-0.483
================================================================-0.471
-0.461
Token friends
Token ID2460
Feature activation+8.56e-02

Pos logit contributions
 Masquerade+0.721
 Goat+0.694
 Caps+0.657
================================================================+0.641
+0.625
Neg logit contributions
itton-0.726
pez-0.700
ocard-0.691
atts-0.649
ourage-0.638
Token,
Token ID11
Feature activation+3.59e-01

Pos logit contributions
itton+0.163
pez+0.158
ocard+0.157
atts+0.148
ourage+0.147
Neg logit contributions
 Masquerade-0.121
 Goat-0.116
 Caps-0.107
================================================================-0.105
-0.102
Token who
Token ID508
Feature activation+3.28e-01

Pos logit contributions
itton+0.602
pez+0.583
ocard+0.576
atts+0.541
ourage+0.533
Neg logit contributions
 Masquerade-0.588
 Goat-0.568
 Caps-0.534
================================================================-0.523
-0.511
Token affection
Token ID17696
Feature activation-1.82e-02

Pos logit contributions
itton+0.560
pez+0.541
ocard+0.536
atts+0.504
ourage+0.496
Neg logit contributions
 Masquerade-0.528
 Goat-0.510
 Caps-0.480
================================================================-0.469
-0.457
Tokenately
Token ID1286
Feature activation-1.77e+00

Pos logit contributions
 Masquerade+0.030
 Goat+0.029
 Caps+0.027
================================================================+0.027
+0.026
Neg logit contributions
itton-0.031
pez-0.030
ocard-0.029
atts-0.027
ourage-0.027
Token called
Token ID1444
Feature activation+3.88e-01

Pos logit contributions
 Masquerade+2.975
 Goat+2.911
 Caps+2.741
================================================================+2.634
mentation+2.603
Neg logit contributions
itton-2.814
pez-2.735
ocard-2.701
atts-2.524
ourage-2.453
Token him
Token ID683
Feature activation-7.87e-01

Pos logit contributions
itton+0.711
pez+0.690
ocard+0.682
atts+0.645
ourage+0.638
Neg logit contributions
 Masquerade-0.574
 Goat-0.551
 Caps-0.514
================================================================-0.505
-0.492
Token "
Token ID366
Feature activation+4.99e-01

Pos logit contributions
 Masquerade+1.163
 Goat+1.131
 Caps+1.046
================================================================+1.022
+0.996
Neg logit contributions
itton-1.446
pez-1.399
ocard-1.383
atts-1.306
ourage-1.289
TokenShort
Token ID16438
Feature activation-5.09e-01

Pos logit contributions
itton+0.919
pez+0.892
ocard+0.882
atts+0.835
ourage+0.826
Neg logit contributions
 Masquerade-0.733
 Goat-0.701
 Caps-0.655
================================================================-0.643
-0.626
Tokeny
Token ID88
Feature activation+1.88e-01

Pos logit contributions
 Masquerade+0.723
 Goat+0.697
 Caps+0.649
================================================================+0.630
+0.620
Neg logit contributions
itton-0.960
pez-0.934
ocard-0.923
atts-0.872
ourage-0.865
Token technology
Token ID3037
Feature activation-7.14e-01

Pos logit contributions
 Masquerade+0.869
 Goat+0.838
 Caps+0.778
================================================================+0.759
+0.730
Neg logit contributions
itton-1.215
pez-1.175
ocard-1.164
atts-1.097
ourage-1.086
Token to
Token ID284
Feature activation-1.60e-01

Pos logit contributions
 Masquerade+0.987
 Goat+0.952
 Caps+0.889
================================================================+0.869
+0.836
Neg logit contributions
itton-1.381
pez-1.328
ocard-1.323
atts-1.242
ourage-1.229
Token what
Token ID644
Feature activation-2.70e-01

Pos logit contributions
 Masquerade+0.212
 Goat+0.203
 Caps+0.188
================================================================+0.183
+0.178
Neg logit contributions
itton-0.320
pez-0.311
ocard-0.308
atts-0.292
ourage-0.289
Token Snap
Token ID16026
Feature activation-7.58e-01

Pos logit contributions
 Masquerade+0.359
 Goat+0.344
 Caps+0.318
================================================================+0.310
+0.301
Neg logit contributions
itton-0.536
pez-0.520
ocard-0.515
atts-0.489
ourage-0.484
Token and
Token ID290
Feature activation+9.92e-03

Pos logit contributions
 Masquerade+1.072
 Goat+1.031
 Caps+0.962
================================================================+0.939
+0.909
Neg logit contributions
itton-1.437
pez-1.390
ocard-1.383
atts-1.300
ourage-1.290
Token Flat
Token ID21939
Feature activation-2.07e+00

Pos logit contributions
itton+0.020
pez+0.020
ocard+0.019
atts+0.018
ourage+0.018
Neg logit contributions
 Masquerade-0.013
 Goat-0.012
 Caps-0.011
================================================================-0.011
-0.011
Tokenpak
Token ID41091
Feature activation-9.33e-01

Pos logit contributions
 Masquerade+1.344
 Goat+1.277
 Caps+1.131
================================================================+1.044
ppa+0.991
Neg logit contributions
itton-5.353
ocard-5.210
pez-5.169
 horm-4.993
atts-4.955
Token offer
Token ID2897
Feature activation+4.78e-01

Pos logit contributions
 Masquerade+1.315
 Goat+1.262
 Caps+1.182
================================================================+1.140
+1.100
Neg logit contributions
itton-1.777
ocard-1.711
pez-1.703
atts-1.597
ourage-1.588
Token,
Token ID11
Feature activation-1.46e-02

Pos logit contributions
itton+0.923
pez+0.899
ocard+0.889
atts+0.843
ourage+0.835
Neg logit contributions
 Masquerade-0.658
 Goat-0.629
 Caps-0.583
================================================================-0.573
-0.557
Token so
Token ID523
Feature activation-2.94e-01

Pos logit contributions
 Masquerade+0.018
 Goat+0.017
 Caps+0.016
================================================================+0.015
+0.015
Neg logit contributions
itton-0.031
pez-0.030
ocard-0.030
atts-0.028
ourage-0.028
Token I
Token ID314
Feature activation-4.42e-01

Pos logit contributions
 Masquerade+0.441
 Goat+0.426
 Caps+0.398
================================================================+0.388
+0.378
Neg logit contributions
itton-0.532
pez-0.516
ocard-0.510
atts-0.481
ourage-0.475
Token goes
Token ID2925
Feature activation-3.31e-01

Pos logit contributions
 Masquerade+0.661
 Goat+0.637
 Caps+0.594
================================================================+0.582
+0.568
Neg logit contributions
itton-0.859
pez-0.833
ocard-0.822
atts-0.781
ourage-0.771
Token:
Token ID25
Feature activation-2.29e-01

Pos logit contributions
 Masquerade+0.489
 Goat+0.472
 Caps+0.440
================================================================+0.431
+0.421
Neg logit contributions
itton-0.606
pez-0.586
ocard-0.582
atts-0.549
ourage-0.544
Token
Token ID198
Feature activation+1.50e-03

Pos logit contributions
 Masquerade+0.334
 Goat+0.322
 Caps+0.302
================================================================+0.295
+0.287
Neg logit contributions
itton-0.426
pez-0.413
ocard-0.409
atts-0.387
ourage-0.381
Token
Token ID198
Feature activation+2.72e-03

Pos logit contributions
itton+0.003
pez+0.003
ocard+0.003
atts+0.003
ourage+0.003
Neg logit contributions
 Masquerade-0.002
 Goat-0.002
 Caps-0.002
================================================================-0.002
-0.002
TokenAbout
Token ID8585
Feature activation+6.38e-01

Pos logit contributions
itton+0.005
pez+0.005
ocard+0.005
atts+0.004
ourage+0.004
Neg logit contributions
 Masquerade-0.004
 Goat-0.004
 Caps-0.004
================================================================-0.004
-0.004
Token Aleppo
Token ID18593
Feature activation-1.90e+00

Pos logit contributions
itton+1.175
pez+1.140
ocard+1.128
atts+1.066
ourage+1.054
Neg logit contributions
 Masquerade-0.939
 Goat-0.902
 Caps-0.842
================================================================-0.828
-0.806
Token and
Token ID290
Feature activation-3.85e-01

Pos logit contributions
 Masquerade+2.635
 Goat+2.539
 Caps+2.384
================================================================+2.322
+2.222
Neg logit contributions
itton-3.590
pez-3.507
ocard-3.483
atts-3.314
ourage-3.239
Token Syria
Token ID4392
Feature activation-4.43e-01

Pos logit contributions
 Masquerade+0.525
 Goat+0.504
 Caps+0.472
================================================================+0.460
+0.447
Neg logit contributions
itton-0.751
pez-0.730
ocard-0.723
atts-0.686
ourage-0.675
Token,
Token ID11
Feature activation+2.61e-02

Pos logit contributions
 Masquerade+0.639
 Goat+0.614
 Caps+0.576
================================================================+0.565
+0.546
Neg logit contributions
itton-0.828
pez-0.804
ocard-0.798
atts-0.755
ourage-0.743
Token I
Token ID314
Feature activation-2.06e-01

Pos logit contributions
itton+0.050
pez+0.048
ocard+0.048
atts+0.045
ourage+0.045
Neg logit contributions
 Masquerade-0.037
 Goat-0.036
 Caps-0.033
================================================================-0.033
-0.032
Token truly
Token ID4988
Feature activation+2.33e-01

Pos logit contributions
 Masquerade+0.313
 Goat+0.302
 Caps+0.283
================================================================+0.279
+0.272
Neg logit contributions
itton-0.367
pez-0.355
ocard-0.351
atts-0.332
ourage-0.327
TokenMake
Token ID12050
Feature activation-4.61e-02

Pos logit contributions
 Masquerade+0.038
 Goat+0.036
 Caps+0.034
================================================================+0.034
+0.033
Neg logit contributions
itton-0.042
pez-0.041
ocard-0.040
atts-0.038
ourage-0.037
Token a
Token ID257
Feature activation+1.92e-01

Pos logit contributions
 Masquerade+0.073
 Goat+0.070
 Caps+0.066
================================================================+0.065
+0.063
Neg logit contributions
itton-0.080
pez-0.078
ocard-0.076
atts-0.072
ourage-0.071
Token file
Token ID2393
Feature activation+1.11e+00

Pos logit contributions
itton+0.333
pez+0.322
ocard+0.318
atts+0.301
ourage+0.297
Neg logit contributions
 Masquerade-0.305
 Goat-0.293
 Caps-0.275
================================================================-0.270
-0.264
Token now
Token ID783
Feature activation-3.73e-01

Pos logit contributions
itton+1.883
pez+1.823
ocard+1.804
atts+1.694
ourage+1.674
Neg logit contributions
 Masquerade-1.784
 Goat-1.718
 Caps-1.611
================================================================-1.589
-1.551
Token with
Token ID351
Feature activation+1.42e-02

Pos logit contributions
 Masquerade+0.548
 Goat+0.528
 Caps+0.492
================================================================+0.485
+0.468
Neg logit contributions
itton-0.686
pez-0.666
ocard-0.659
atts-0.624
ourage-0.615
Token proof
Token ID6617
Feature activation-2.08e+00

Pos logit contributions
itton+0.025
pez+0.024
ocard+0.024
atts+0.022
ourage+0.022
Neg logit contributions
 Masquerade-0.022
 Goat-0.022
 Caps-0.020
================================================================-0.020
-0.019
Token of
Token ID286
Feature activation+2.66e-02

Pos logit contributions
 Masquerade+3.022
 Goat+2.923
 Caps+2.731
================================================================+2.676
+2.632
Neg logit contributions
itton-3.776
pez-3.696
ocard-3.584
atts-3.411
ourage-3.395
Token your
Token ID534
Feature activation+5.67e-01

Pos logit contributions
itton+0.043
pez+0.042
ocard+0.041
atts+0.039
ourage+0.038
Neg logit contributions
 Masquerade-0.045
 Goat-0.043
 Caps-0.041
================================================================-0.040
-0.039
Token presence
Token ID4931
Feature activation-9.31e-02

Pos logit contributions
itton+0.925
pez+0.893
ocard+0.872
atts+0.826
ourage+0.818
Neg logit contributions
 Masquerade-0.959
 Goat-0.926
 Caps-0.871
================================================================-0.858
-0.835
Token [
Token ID685
Feature activation-1.50e-01

Pos logit contributions
 Masquerade+0.146
 Goat+0.141
 Caps+0.132
================================================================+0.130
+0.126
Neg logit contributions
itton-0.163
pez-0.157
ocard-0.155
atts-0.147
ourage-0.145
Tokenand
Token ID392
Feature activation+2.53e-01

Pos logit contributions
 Masquerade+0.234
 Goat+0.225
 Caps+0.211
================================================================+0.210
+0.204
Neg logit contributions
itton-0.261
pez-0.254
ocard-0.251
atts-0.236
ourage-0.233