TOP ACTIVATIONS
MAX = 2.931

. Par liament ary officers have the
t weet / <|endoftext|> Story highlights Secretary of Defense Chuck Hag
vote accordingly . <|endoftext|> Story highlights Police chief vows wanted suspect
I had rehears ed my ass off and Robert Pic ardo
website . V ital y Nem ov , owner
iff Tra x Reviewer : V the Happy L
million years . <|endoftext|> Image copyright AFP The Bank
yr ds Cover ) ( via Sound Cloud )
save lives ! <|endoftext|> Revolution ary Rac ism : Af ro
this pr imate was uniquely adapted to its environment , Dr
, 2016 W ass erman is the current chair
rage . polit ically correct o omp a lo
them fresh or in their dry state . Some people have
dumping area at the Arrow head Land fill in Union town
guy , unconditional - l oyal ty - vers us -
. <|endoftext|> Image copyright publicity Image caption The Greeks
no holds barred to the che qu ered flag ! Race
sh rooms ( fresh or dry ) and wh iz on
00 . Delivery : V aries Invalid email address Thank you
hotel room at the Hy att Reg ency Irvine , November

MIN ACTIVATIONS
MIN = -3.618

be real - life pur ges , and they
is long ; he comm ends the Monday job - seekers
the United States , dev olution of national powers to state
kinds of stories about pur ges in every major city in
Last week , he comm ended Trump for conducting military strikes
wanted to portray the conv icts playing baseball in the yard
soldiers that it granted conv icts freedom , if they would
early 1960 s , conv icts at Al cat raz had
in Sanskrit and his cons ort Rath i , they have
Today w e can d raw up the most g
approval of measures of dev olution . The Catalan
Much of the commentary rev olved around the aesthetics and design
. Most tweets about Pur ges have the refrain
Life of Christ . Sac ram ents . Bapt ism .
Patton . He 's br ash and opinion ated , and
in this market are reg aining profitability , the
- bit Hy rule Fi end , O car ina
я е т с я « в а н
by Facebook employees in Palo Alto , Calif ., and in
serves powerful corporate interests unab ashed ly , and another party

INTERVAL 1.294 - 2.931
CONTAINS 0.309%

All salary - cap figures courtesy of Over The Cap .
some extent between wet and dry seasons and the situation has
ev ic " ( m att - EE - oh -
but ultimately authorized the Smithsonian Museum of African American History and
sure to connect with Unt app d on Facebook , Twitter

INTERVAL -0.343 - 1.294
CONTAINS 84.049%

O Malley also responded to President Obama
National debt is one of many economic indicators that inter play
Shortly after Trump tweeted about his ban , he offered
for the 600 - odd channels of real - time viewing
Every year 5 lakh road accidents are reported in the

INTERVAL -1.981 - -0.343
CONTAINS 15.625%

look like someone has shouted fire in a crowded theater ,
time . <|endoftext|> The stolen bike , a 1982 V itus
the middle of the at oll . The drone
this morning . More than an hour before kick
- Frank iv sk . <|endoftext|> [ Ex clusive ] Best

INTERVAL -3.618 - -1.981
CONTAINS 0.017%

a Zel ig who trek ked to the North Pole but
He then immediately piv oted to the story of Rachel
. Sign Up You will receive emails containing news content ,
i n ā i wi o K ā n ep ō
gave 44 % of tit hes collected by churches in Brazil
Token.
Token ID13
Feature activation+1.32e-01

Pos logit contributions
Psych+0.050
issan+0.049
psych+0.045
Dex+0.045
 Psych+0.044
Neg logit contributions
rio-0.063
Ire-0.059
 Trave-0.053
-0.053
 Surviv-0.052
Token
Token ID198
Feature activation+1.23e-01

Pos logit contributions
Psych+0.078
issan+0.076
psych+0.070
Dex+0.069
 Psych+0.067
Neg logit contributions
rio-0.115
Ire-0.110
 Trave-0.100
-0.099
 Surviv-0.098
Token
Token ID198
Feature activation+1.15e-01

Pos logit contributions
Psych+0.059
issan+0.057
psych+0.051
Dex+0.050
 Psych+0.049
Neg logit contributions
rio-0.121
Ire-0.116
 Trave-0.106
-0.105
 Surviv-0.105
TokenPar
Token ID10044
Feature activation-4.31e-03

Pos logit contributions
Psych+0.084
issan+0.082
psych+0.076
Dex+0.076
 Psych+0.074
Neg logit contributions
rio-0.085
Ire-0.080
 Trave-0.071
-0.070
 Surviv-0.070
Tokenliament
Token ID5130
Feature activation+6.82e-01

Pos logit contributions
rio+0.004
Ire+0.004
 Trave+0.003
+0.003
 Surviv+0.003
Neg logit contributions
Psych-0.003
issan-0.002
psych-0.002
Dex-0.002
 Psych-0.002
Tokenary
Token ID560
Feature activation+2.93e+00

Pos logit contributions
Psych+0.452
issan+0.440
psych+0.407
Dex+0.402
 Psych+0.398
Neg logit contributions
rio-0.545
Ire-0.518
 Trave-0.463
-0.460
 Surviv-0.457
Token officers
Token ID3790
Feature activation+2.60e-01

Pos logit contributions
Psych+1.895
issan+1.812
psych+1.693
 Psych+1.692
Dex+1.682
Neg logit contributions
rio-2.385
Ire-2.268
-2.029
 Trave-1.997
 Surviv-1.994
Token have
Token ID423
Feature activation+2.92e-01

Pos logit contributions
Psych+0.163
issan+0.159
psych+0.146
Dex+0.145
 Psych+0.142
Neg logit contributions
rio-0.218
Ire-0.207
 Trave-0.186
-0.185
 Surviv-0.184
Token the
Token ID262
Feature activation+2.10e-01

Pos logit contributions
Psych+0.179
issan+0.175
psych+0.160
Dex+0.159
 Psych+0.156
Neg logit contributions
rio-0.248
Ire-0.236
 Trave-0.213
-0.211
 Surviv-0.209
Token
Token ID564
Feature activation+3.79e-01

Pos logit contributions
Psych+0.137
issan+0.133
psych+0.123
Dex+0.122
 Psych+0.120
Neg logit contributions
rio-0.170
Ire-0.161
 Trave-0.145
-0.144
 Surviv-0.143
Token
Token ID250
Feature activation+7.36e-02

Pos logit contributions
Psych+0.231
issan+0.226
psych+0.207
Dex+0.204
 Psych+0.200
Neg logit contributions
rio-0.324
Ire-0.308
 Trave-0.278
-0.275
 Surviv-0.273
Tokent
Token ID83
Feature activation-7.06e-02

Pos logit contributions
rio+0.129
Ire+0.122
 Trave+0.110
+0.109
 Surviv+0.108
Neg logit contributions
Psych-0.107
issan-0.104
psych-0.096
Dex-0.095
 Psych-0.093
Tokenweet
Token ID7277
Feature activation-2.62e-01

Pos logit contributions
rio+0.052
Ire+0.049
 Trave+0.044
+0.043
 Surviv+0.043
Neg logit contributions
Psych-0.051
issan-0.050
psych-0.047
Dex-0.046
 Psych-0.046
Token/
Token ID14
Feature activation-8.69e-02

Pos logit contributions
rio+0.229
Ire+0.217
 Trave+0.197
+0.196
 Surviv+0.194
Neg logit contributions
Psych-0.154
issan-0.150
psych-0.137
Dex-0.135
 Psych-0.132
Token<|endoftext|>
Token ID50256
Feature activation+6.91e-02

Pos logit contributions
rio+0.080
Ire+0.076
 Trave+0.069
+0.069
 Surviv+0.068
Neg logit contributions
Psych-0.047
issan-0.046
psych-0.042
Dex-0.041
 Psych-0.040
TokenStory
Token ID11605
Feature activation-6.46e-01

Pos logit contributions
Psych+0.051
issan+0.050
psych+0.046
Dex+0.046
 Psych+0.045
Neg logit contributions
rio-0.051
Ire-0.047
 Trave-0.042
-0.042
 Surviv-0.042
Token highlights
Token ID11330
Feature activation+2.66e+00

Pos logit contributions
rio+0.576
Ire+0.549
 Trave+0.498
+0.493
 Surviv+0.491
Neg logit contributions
Psych-0.370
issan-0.360
psych-0.328
Dex-0.324
 Psych-0.317
Token Secretary
Token ID4986
Feature activation+2.31e-01

Pos logit contributions
Psych+1.821
issan+1.752
 Psych+1.650
psych+1.634
Dex+1.631
Neg logit contributions
rio-2.080
Ire-1.962
-1.740
 Trave-1.705
ð-1.689
Token of
Token ID286
Feature activation+2.81e-01

Pos logit contributions
Psych+0.149
issan+0.145
psych+0.134
Dex+0.133
 Psych+0.131
Neg logit contributions
rio-0.189
Ire-0.180
 Trave-0.161
-0.160
 Surviv-0.159
Token Defense
Token ID5947
Feature activation-3.47e-01

Pos logit contributions
Psych+0.201
issan+0.196
psych+0.182
Dex+0.181
 Psych+0.180
Neg logit contributions
rio-0.211
Ire-0.200
-0.176
 Trave-0.176
 Surviv-0.173
Token Chuck
Token ID14663
Feature activation+1.03e+00

Pos logit contributions
rio+0.248
Ire+0.237
+0.206
 Trave+0.205
 Surviv+0.203
Neg logit contributions
Psych-0.259
issan-0.252
psych-0.237
Dex-0.236
 Psych-0.233
Token Hag
Token ID21375
Feature activation-5.64e-02

Pos logit contributions
Psych+0.825
issan+0.787
 Haas+0.772
 Psych+0.760
Dex+0.758
Neg logit contributions
rio-0.661
Ire-0.657
-0.543
 Trave-0.540
 Surviv-0.538
Token vote
Token ID3015
Feature activation-8.55e-01

Pos logit contributions
rio+0.253
Ire+0.240
 Trave+0.215
+0.214
 Surviv+0.212
Neg logit contributions
Psych-0.200
issan-0.194
psych-0.179
Dex-0.177
 Psych-0.176
Token accordingly
Token ID16062
Feature activation+9.95e-01

Pos logit contributions
rio+0.714
Ire+0.677
 Trave+0.612
+0.603
 Surviv+0.601
Neg logit contributions
Psych-0.537
issan-0.523
psych-0.482
Dex-0.477
 Psych-0.465
Token.
Token ID13
Feature activation-4.35e-01

Pos logit contributions
Psych+0.609
issan+0.591
psych+0.544
Dex+0.537
 Psych+0.530
Neg logit contributions
rio-0.845
Ire-0.809
 Trave-0.728
-0.721
 Surviv-0.719
Token<|endoftext|>
Token ID50256
Feature activation+6.22e-02

Pos logit contributions
rio+0.393
Ire+0.374
 Trave+0.340
+0.337
 Surviv+0.335
Neg logit contributions
Psych-0.244
issan-0.237
psych-0.216
Dex-0.213
 Psych-0.209
TokenStory
Token ID11605
Feature activation-8.12e-01

Pos logit contributions
Psych+0.046
issan+0.044
psych+0.042
Dex+0.041
 Psych+0.040
Neg logit contributions
rio-0.046
Ire-0.043
 Trave-0.038
-0.038
 Surviv-0.037
Token highlights
Token ID11330
Feature activation+2.51e+00

Pos logit contributions
rio+0.723
Ire+0.688
 Trave+0.626
+0.618
 Surviv+0.615
Neg logit contributions
Psych-0.466
issan-0.453
psych-0.413
Dex-0.408
 Psych-0.399
Token Police
Token ID4287
Feature activation-6.45e-02

Pos logit contributions
Psych+1.718
issan+1.656
 Psych+1.556
psych+1.542
Dex+1.539
Neg logit contributions
rio-1.957
Ire-1.845
-1.635
 Trave-1.603
 Surviv-1.589
Token chief
Token ID4039
Feature activation-8.86e-01

Pos logit contributions
rio+0.054
Ire+0.052
 Trave+0.047
+0.046
 Surviv+0.046
Neg logit contributions
Psych-0.040
issan-0.039
psych-0.036
Dex-0.035
 Psych-0.035
Token vows
Token ID36605
Feature activation+6.50e-01

Pos logit contributions
rio+0.722
Ire+0.685
 Trave+0.616
+0.608
 Surviv+0.605
Neg logit contributions
Psych-0.575
issan-0.561
psych-0.518
Dex-0.512
 Psych-0.503
Token wanted
Token ID2227
Feature activation+1.42e-01

Pos logit contributions
Psych+0.402
issan+0.391
psych+0.360
Dex+0.355
 Psych+0.348
Neg logit contributions
rio-0.551
Ire-0.522
 Trave-0.473
-0.467
 Surviv-0.464
Token suspect
Token ID4099
Feature activation-2.19e-01

Pos logit contributions
Psych+0.087
issan+0.084
psych+0.077
Dex+0.076
 Psych+0.075
Neg logit contributions
rio-0.122
Ire-0.115
 Trave-0.105
-0.103
 Surviv-0.103
Token I
Token ID314
Feature activation-1.02e-01

Pos logit contributions
Psych+0.191
issan+0.186
psych+0.172
Dex+0.170
 Psych+0.168
Neg logit contributions
rio-0.234
Ire-0.222
 Trave-0.199
-0.197
 Surviv-0.196
Token had
Token ID550
Feature activation-9.52e-03

Pos logit contributions
rio+0.081
Ire+0.076
 Trave+0.068
+0.067
 Surviv+0.067
Neg logit contributions
Psych-0.069
issan-0.067
psych-0.062
Dex-0.061
 Psych-0.061
Token rehears
Token ID28779
Feature activation-5.54e-01

Pos logit contributions
rio+0.008
Ire+0.008
 Trave+0.007
+0.007
 Surviv+0.007
Neg logit contributions
Psych-0.006
issan-0.006
psych-0.005
Dex-0.005
 Psych-0.005
Tokened
Token ID276
Feature activation-5.98e-01

Pos logit contributions
rio+0.391
Ire+0.367
 Trave+0.324
+0.320
 Surviv+0.318
Neg logit contributions
Psych-0.421
issan-0.412
psych-0.385
Dex-0.382
 Psych-0.376
Token my
Token ID616
Feature activation+1.42e-01

Pos logit contributions
rio+0.510
Ire+0.485
 Trave+0.436
+0.434
 Surviv+0.430
Neg logit contributions
Psych-0.367
issan-0.356
psych-0.328
Dex-0.324
 Psych-0.319
Token ass
Token ID840
Feature activation+2.39e+00

Pos logit contributions
Psych+0.090
issan+0.088
psych+0.081
Dex+0.080
 Psych+0.079
Neg logit contributions
rio-0.117
Ire-0.111
 Trave-0.100
-0.099
 Surviv-0.098
Token off
Token ID572
Feature activation-1.29e-01

Pos logit contributions
Psych+1.415
issan+1.378
psych+1.283
Dex+1.233
 Psych+1.233
Neg logit contributions
rio-2.050
Ire-1.974
 Trave-1.771
-1.758
 Surviv-1.757
Token and
Token ID290
Feature activation+3.76e-01

Pos logit contributions
rio+0.104
Ire+0.099
 Trave+0.088
+0.087
 Surviv+0.087
Neg logit contributions
Psych-0.085
issan-0.082
psych-0.076
Dex-0.076
 Psych-0.074
Token Robert
Token ID5199
Feature activation+5.18e-01

Pos logit contributions
Psych+0.232
issan+0.225
psych+0.207
Dex+0.205
 Psych+0.203
Neg logit contributions
rio-0.319
Ire-0.303
 Trave-0.273
-0.271
 Surviv-0.269
Token Pic
Token ID15085
Feature activation+3.96e-01

Pos logit contributions
Psych+0.373
issan+0.363
psych+0.339
Dex+0.335
 Psych+0.333
Neg logit contributions
rio-0.384
Ire-0.365
 Trave-0.323
-0.321
 Surviv-0.321
Tokenardo
Token ID13109
Feature activation+2.45e-01

Pos logit contributions
Psych+0.259
issan+0.255
psych+0.233
Dex+0.231
 Psych+0.226
Neg logit contributions
rio-0.315
Ire-0.305
 Trave-0.274
 Surviv-0.272
-0.269
Token website
Token ID3052
Feature activation+1.31e-02

Pos logit contributions
rio+0.141
Ire+0.133
 Trave+0.119
+0.118
 Surviv+0.117
Neg logit contributions
Psych-0.122
issan-0.119
psych-0.110
Dex-0.109
 Psych-0.107
Token.
Token ID13
Feature activation+7.30e-02

Pos logit contributions
Psych+0.008
issan+0.008
psych+0.007
Dex+0.007
 Psych+0.007
Neg logit contributions
rio-0.011
Ire-0.010
 Trave-0.009
-0.009
 Surviv-0.009
Token
Token ID198
Feature activation+2.30e-02

Pos logit contributions
Psych+0.039
issan+0.038
psych+0.034
Dex+0.034
 Psych+0.033
Neg logit contributions
rio-0.068
Ire-0.065
 Trave-0.059
-0.058
 Surviv-0.058
Token
Token ID198
Feature activation+1.17e-02

Pos logit contributions
Psych+0.011
issan+0.011
psych+0.009
Dex+0.009
 Psych+0.009
Neg logit contributions
rio-0.023
Ire-0.022
 Trave-0.020
-0.020
 Surviv-0.020
TokenV
Token ID53
Feature activation+8.42e-01

Pos logit contributions
Psych+0.008
issan+0.008
psych+0.008
Dex+0.008
 Psych+0.007
Neg logit contributions
rio-0.009
Ire-0.008
 Trave-0.007
-0.007
 Surviv-0.007
Tokenital
Token ID1287
Feature activation+2.28e+00

Pos logit contributions
Psych+0.494
issan+0.484
psych+0.441
Dex+0.434
 Psych+0.425
Neg logit contributions
rio-0.738
Ire-0.704
 Trave-0.642
-0.635
 Surviv-0.630
Tokeny
Token ID88
Feature activation+8.94e-01

Pos logit contributions
Psych+1.579
issan+1.546
psych+1.440
Dex+1.418
 Psych+1.405
Neg logit contributions
rio-1.741
Ire-1.668
-1.480
 Trave-1.473
 Surviv-1.457
Token Nem
Token ID22547
Feature activation-1.37e-01

Pos logit contributions
Psych+0.432
issan+0.417
psych+0.373
Dex+0.368
 Psych+0.359
Neg logit contributions
rio-0.879
Ire-0.842
 Trave-0.771
-0.765
 Surviv-0.760
Tokenov
Token ID709
Feature activation-7.18e-01

Pos logit contributions
rio+0.085
Ire+0.082
 Trave+0.070
+0.070
 Surviv+0.069
Neg logit contributions
Psych-0.114
issan-0.113
psych-0.106
Dex-0.104
 Psych-0.103
Token,
Token ID11
Feature activation+1.52e-01

Pos logit contributions
rio+0.556
Ire+0.527
 Trave+0.470
+0.465
 Surviv+0.463
Neg logit contributions
Psych-0.495
issan-0.483
psych-0.448
Dex-0.444
 Psych-0.437
Token owner
Token ID4870
Feature activation+5.08e-01

Pos logit contributions
Psych+0.098
issan+0.095
psych+0.088
Dex+0.087
 Psych+0.086
Neg logit contributions
rio-0.125
Ire-0.119
 Trave-0.106
-0.106
 Surviv-0.104
Tokeniff
Token ID733
Feature activation+2.12e-02

Pos logit contributions
Psych+0.276
issan+0.266
psych+0.248
Dex+0.242
 Psych+0.237
Neg logit contributions
rio-0.371
Ire-0.357
 Surviv-0.326
 Trave-0.325
-0.325
TokenTra
Token ID15721
Feature activation-4.98e-02

Pos logit contributions
Psych+0.018
issan+0.017
Dex+0.016
psych+0.016
 Psych+0.016
Neg logit contributions
rio-0.013
Ire-0.013
 Surviv-0.011
-0.011
 Trave-0.011
Tokenx
Token ID87
Feature activation+7.68e-01

Pos logit contributions
rio+0.041
Ire+0.039
 Trave+0.035
+0.035
 Surviv+0.035
Neg logit contributions
Psych-0.032
issan-0.031
psych-0.029
Dex-0.028
 Psych-0.028
Token
Token ID198
Feature activation+4.94e-02

Pos logit contributions
Psych+0.378
issan+0.361
psych+0.327
Dex+0.321
 Psych+0.316
Neg logit contributions
rio-0.749
Ire-0.718
 Trave-0.656
-0.650
 Surviv-0.648
Token
Token ID198
Feature activation+6.48e-02

Pos logit contributions
Psych+0.024
issan+0.023
psych+0.020
Dex+0.020
 Psych+0.020
Neg logit contributions
rio-0.049
Ire-0.047
 Trave-0.043
-0.042
 Surviv-0.042
TokenReviewer
Token ID35407
Feature activation+2.28e+00

Pos logit contributions
Psych+0.047
issan+0.046
psych+0.043
Dex+0.043
 Psych+0.042
Neg logit contributions
rio-0.048
Ire-0.045
 Trave-0.040
 Surviv-0.040
-0.040
Token:
Token ID25
Feature activation+6.57e-02

Pos logit contributions
Psych+1.413
issan+1.325
psych+1.248
Dex+1.245
 Psych+1.219
Neg logit contributions
rio-1.929
Ire-1.854
 Surviv-1.668
 Trave-1.658
-1.651
Token V
Token ID569
Feature activation+6.35e-01

Pos logit contributions
Psych+0.044
issan+0.042
psych+0.039
Dex+0.039
 Psych+0.038
Neg logit contributions
rio-0.053
Ire-0.050
 Trave-0.045
-0.044
 Surviv-0.044
Tokenthe
Token ID1169
Feature activation+1.94e-01

Pos logit contributions
Psych+0.432
issan+0.422
psych+0.390
Dex+0.385
 Psych+0.379
Neg logit contributions
rio-0.497
Ire-0.471
 Trave-0.426
-0.419
 Surviv-0.418
TokenHappy
Token ID25082
Feature activation+1.75e-01

Pos logit contributions
Psych+0.133
issan+0.129
psych+0.120
Dex+0.119
 Psych+0.116
Neg logit contributions
rio-0.151
Ire-0.143
 Trave-0.128
-0.126
 Surviv-0.126
TokenL
Token ID43
Feature activation+3.16e-01

Pos logit contributions
Psych+0.120
issan+0.116
psych+0.108
Dex+0.107
 Psych+0.105
Neg logit contributions
rio-0.137
Ire-0.130
 Trave-0.116
-0.115
 Surviv-0.114
Token million
Token ID1510
Feature activation-4.47e-01

Pos logit contributions
rio+0.106
Ire+0.101
 Trave+0.091
+0.090
 Surviv+0.089
Neg logit contributions
Psych-0.085
issan-0.083
psych-0.076
Dex-0.076
 Psych-0.074
Token years
Token ID812
Feature activation-6.08e-02

Pos logit contributions
rio+0.342
Ire+0.323
 Trave+0.287
+0.285
 Surviv+0.282
Neg logit contributions
Psych-0.313
issan-0.306
psych-0.284
Dex-0.281
 Psych-0.278
Token.
Token ID13
Feature activation+8.58e-02

Pos logit contributions
rio+0.052
Ire+0.049
 Trave+0.044
+0.044
 Surviv+0.043
Neg logit contributions
Psych-0.038
issan-0.037
psych-0.034
Dex-0.033
 Psych-0.033
Token<|endoftext|>
Token ID50256
Feature activation+8.69e-02

Pos logit contributions
Psych+0.050
issan+0.049
psych+0.044
Dex+0.044
 Psych+0.043
Neg logit contributions
rio-0.076
Ire-0.072
 Trave-0.065
-0.065
 Surviv-0.064
TokenImage
Token ID5159
Feature activation-1.49e-01

Pos logit contributions
Psych+0.064
issan+0.062
psych+0.058
Dex+0.058
 Psych+0.057
Neg logit contributions
rio-0.064
Ire-0.060
 Trave-0.053
-0.052
 Surviv-0.052
Token copyright
Token ID6634
Feature activation+2.27e+00

Pos logit contributions
rio+0.138
Ire+0.131
 Trave+0.120
+0.119
 Surviv+0.118
Neg logit contributions
Psych-0.081
issan-0.079
psych-0.071
Dex-0.070
 Psych-0.069
Token AFP
Token ID8916
Feature activation+4.22e-01

Pos logit contributions
Psych+1.442
issan+1.399
psych+1.293
 Psych+1.286
Dex+1.281
Neg logit contributions
rio-1.874
Ire-1.786
-1.581
 Trave-1.576
 Surviv-1.556
Token
Token ID198
Feature activation+2.08e-01

Pos logit contributions
Psych+0.244
issan+0.237
psych+0.216
Dex+0.214
 Psych+0.209
Neg logit contributions
rio-0.373
Ire-0.355
 Trave-0.324
-0.319
 Surviv-0.318
Token
Token ID198
Feature activation+1.39e-01

Pos logit contributions
Psych+0.100
issan+0.096
psych+0.086
Dex+0.085
 Psych+0.083
Neg logit contributions
rio-0.205
Ire-0.196
 Trave-0.179
-0.178
 Surviv-0.177
TokenThe
Token ID464
Feature activation+6.77e-02

Pos logit contributions
Psych+0.106
issan+0.103
psych+0.096
Dex+0.096
 Psych+0.094
Neg logit contributions
rio-0.098
Ire-0.092
 Trave-0.082
-0.080
 Surviv-0.080
Token Bank
Token ID5018
Feature activation-6.42e-01

Pos logit contributions
Psych+0.046
issan+0.046
psych+0.042
Dex+0.042
 Psych+0.041
Neg logit contributions
rio-0.052
Ire-0.050
-0.044
 Trave-0.044
 Surviv-0.043
Tokenyr
Token ID2417
Feature activation+5.15e-01

Pos logit contributions
Psych+0.082
issan+0.079
psych+0.073
Dex+0.072
 Psych+0.071
Neg logit contributions
rio-0.105
Ire-0.100
 Trave-0.090
-0.089
 Surviv-0.088
Tokends
Token ID9310
Feature activation+6.68e-01

Pos logit contributions
Psych+0.356
issan+0.348
psych+0.322
Dex+0.319
 Psych+0.314
Neg logit contributions
rio-0.399
Ire-0.378
 Trave-0.337
-0.334
 Surviv-0.332
Token Cover
Token ID17546
Feature activation+1.21e+00

Pos logit contributions
Psych+0.470
issan+0.453
psych+0.426
Dex+0.423
 Psych+0.419
Neg logit contributions
rio-0.509
Ire-0.484
 Trave-0.429
-0.425
 Surviv-0.423
Token)
Token ID8
Feature activation+3.99e-01

Pos logit contributions
Psych+0.828
issan+0.798
psych+0.747
Dex+0.738
 Psych+0.735
Neg logit contributions
rio-0.943
Ire-0.900
 Trave-0.796
-0.787
 Surviv-0.786
Token (
Token ID357
Feature activation+2.10e-01

Pos logit contributions
Psych+0.216
issan+0.208
psych+0.189
Dex+0.187
 Psych+0.184
Neg logit contributions
rio-0.370
Ire-0.353
 Trave-0.321
-0.318
 Surviv-0.316
Tokenvia
Token ID8869
Feature activation+2.27e+00

Pos logit contributions
Psych+0.149
issan+0.143
psych+0.134
Dex+0.133
 Psych+0.130
Neg logit contributions
rio-0.160
Ire-0.151
 Trave-0.136
 Surviv-0.134
-0.133
Token Sound
Token ID9506
Feature activation+4.90e-02

Pos logit contributions
Psych+1.549
issan+1.486
psych+1.392
 Psych+1.386
Dex+1.381
Neg logit contributions
rio-1.769
Ire-1.689
-1.490
 Trave-1.485
 Surviv-1.464
TokenCloud
Token ID18839
Feature activation-3.44e-01

Pos logit contributions
Psych+0.037
issan+0.036
psych+0.034
Dex+0.034
 Psych+0.033
Neg logit contributions
rio-0.035
Ire-0.033
 Trave-0.029
 Surviv-0.029
-0.028
Token)
Token ID8
Feature activation+3.64e-01

Pos logit contributions
rio+0.269
Ire+0.254
 Trave+0.227
+0.225
 Surviv+0.223
Neg logit contributions
Psych-0.236
issan-0.229
psych-0.213
Dex-0.211
 Psych-0.208
Token
Token ID198
Feature activation-2.04e-01

Pos logit contributions
Psych+0.180
issan+0.173
psych+0.156
Dex+0.154
 Psych+0.151
Neg logit contributions
rio-0.353
Ire-0.339
 Trave-0.309
-0.307
 Surviv-0.305
Token
Token ID198
Feature activation-1.39e-01

Pos logit contributions
rio+0.201
Ire+0.193
 Trave+0.177
+0.175
 Surviv+0.175
Neg logit contributions
Psych-0.098
issan-0.093
psych-0.084
Dex-0.083
 Psych-0.081
Token save
Token ID3613
Feature activation-1.98e-01

Pos logit contributions
Psych+0.033
issan+0.032
psych+0.029
Dex+0.029
 Psych+0.028
Neg logit contributions
rio-0.050
Ire-0.047
 Trave-0.043
-0.042
 Surviv-0.042
Token lives
Token ID3160
Feature activation+2.50e-01

Pos logit contributions
rio+0.145
Ire+0.137
 Trave+0.121
+0.121
 Surviv+0.118
Neg logit contributions
Psych-0.145
issan-0.141
psych-0.132
Dex-0.131
 Psych-0.129
Token!
Token ID0
Feature activation-4.15e-01

Pos logit contributions
Psych+0.162
issan+0.157
psych+0.145
Dex+0.144
 Psych+0.141
Neg logit contributions
rio-0.204
Ire-0.194
 Trave-0.174
-0.172
 Surviv-0.171
Token<|endoftext|>
Token ID50256
Feature activation-1.21e-01

Pos logit contributions
rio+0.373
Ire+0.356
 Trave+0.324
+0.320
 Surviv+0.319
Neg logit contributions
Psych-0.234
issan-0.228
psych-0.207
Dex-0.205
 Psych-0.200
TokenRevolution
Token ID50237
Feature activation-2.74e-01

Pos logit contributions
rio+0.089
Ire+0.083
 Trave+0.074
+0.073
 Surviv+0.073
Neg logit contributions
Psych-0.089
issan-0.087
psych-0.081
Dex-0.080
 Psych-0.079
Tokenary
Token ID560
Feature activation+2.26e+00

Pos logit contributions
rio+0.203
Ire+0.191
 Trave+0.169
+0.168
 Surviv+0.167
Neg logit contributions
Psych-0.199
issan-0.194
psych-0.181
Dex-0.179
 Psych-0.177
Token Rac
Token ID24746
Feature activation-9.13e-02

Pos logit contributions
Psych+1.543
issan+1.491
psych+1.391
 Psych+1.384
Dex+1.367
Neg logit contributions
rio-1.765
Ire-1.670
-1.486
 Trave-1.465
 Surviv-1.455
Tokenism
Token ID1042
Feature activation+1.59e+00

Pos logit contributions
rio+0.065
Ire+0.062
 Trave+0.054
+0.054
 Surviv+0.053
Neg logit contributions
Psych-0.068
issan-0.067
psych-0.062
Dex-0.062
 Psych-0.061
Token:
Token ID25
Feature activation+2.52e-01

Pos logit contributions
Psych+1.016
issan+0.969
psych+0.907
 Psych+0.903
Dex+0.892
Neg logit contributions
rio-1.318
Ire-1.259
-1.117
 Trave-1.113
 Surviv-1.103
Token Af
Token ID2483
Feature activation+7.83e-01

Pos logit contributions
Psych+0.177
issan+0.173
psych+0.161
Dex+0.159
 Psych+0.158
Neg logit contributions
rio-0.192
Ire-0.181
 Trave-0.161
-0.160
 Surviv-0.158
Tokenro
Token ID305
Feature activation+4.30e-01

Pos logit contributions
Psych+0.496
issan+0.483
psych+0.446
Dex+0.440
 Psych+0.433
Neg logit contributions
rio-0.650
Ire-0.618
 Trave-0.556
-0.552
 Surviv-0.548
Token this
Token ID428
Feature activation+4.49e-01

Pos logit contributions
Psych+0.339
issan+0.327
psych+0.302
Dex+0.296
 Psych+0.296
Neg logit contributions
rio-0.512
Ire-0.490
-0.439
 Trave-0.438
 Surviv-0.433
Token pr
Token ID778
Feature activation+4.24e-01

Pos logit contributions
Psych+0.280
issan+0.271
psych+0.251
Dex+0.247
 Psych+0.245
Neg logit contributions
rio-0.377
Ire-0.361
-0.323
 Trave-0.322
 Surviv-0.319
Tokenimate
Token ID1920
Feature activation-4.37e-01

Pos logit contributions
Psych+0.272
issan+0.267
psych+0.247
Dex+0.239
 Psych+0.237
Neg logit contributions
rio-0.344
Ire-0.335
 Trave-0.300
-0.299
 Surviv-0.298
Token was
Token ID373
Feature activation+4.34e-01

Pos logit contributions
rio+0.348
Ire+0.331
 Trave+0.295
+0.294
 Surviv+0.291
Neg logit contributions
Psych-0.292
issan-0.284
psych-0.263
Dex-0.261
 Psych-0.257
Token uniquely
Token ID24139
Feature activation+4.74e-02

Pos logit contributions
Psych+0.300
issan+0.291
psych+0.273
Dex+0.268
 Psych+0.267
Neg logit contributions
rio-0.335
Ire-0.319
 Trave-0.282
-0.281
 Surviv-0.278
Token adapted
Token ID16573
Feature activation+2.25e+00

Pos logit contributions
Psych+0.038
issan+0.038
psych+0.035
Dex+0.035
 Psych+0.035
Neg logit contributions
rio-0.031
Ire-0.029
 Trave-0.025
-0.025
 Surviv-0.025
Token to
Token ID284
Feature activation+2.03e-01

Pos logit contributions
Psych+1.329
issan+1.280
psych+1.181
 Psych+1.158
Dex+1.157
Neg logit contributions
rio-1.967
Ire-1.887
-1.689
 Trave-1.677
 Surviv-1.666
Token its
Token ID663
Feature activation+4.33e-01

Pos logit contributions
Psych+0.124
issan+0.120
psych+0.111
Dex+0.109
 Psych+0.108
Neg logit contributions
rio-0.174
Ire-0.165
-0.148
 Trave-0.148
 Surviv-0.146
Token environment
Token ID2858
Feature activation+5.72e-01

Pos logit contributions
Psych+0.273
issan+0.266
psych+0.246
Dex+0.242
 Psych+0.240
Neg logit contributions
rio-0.361
Ire-0.343
-0.307
 Trave-0.307
 Surviv-0.303
Token,
Token ID11
Feature activation+7.99e-02

Pos logit contributions
Psych+0.392
issan+0.382
psych+0.355
Dex+0.349
 Psych+0.348
Neg logit contributions
rio-0.448
Ire-0.425
 Trave-0.376
-0.375
 Surviv-0.372
Token Dr
Token ID1583
Feature activation+1.78e-01

Pos logit contributions
Psych+0.048
issan+0.046
psych+0.043
Dex+0.042
 Psych+0.042
Neg logit contributions
rio-0.069
Ire-0.066
 Trave-0.059
-0.059
 Surviv-0.059
Token,
Token ID11
Feature activation+8.34e-02

Pos logit contributions
rio+0.221
Ire+0.210
 Trave+0.186
+0.184
 Surviv+0.184
Neg logit contributions
Psych-0.204
issan-0.198
psych-0.184
Dex-0.183
 Psych-0.180
Token 2016
Token ID1584
Feature activation+5.31e-01

Pos logit contributions
Psych+0.063
issan+0.061
psych+0.057
Dex+0.057
 Psych+0.056
Neg logit contributions
rio-0.059
Ire-0.056
 Trave-0.049
-0.049
 Surviv-0.048
Token
Token ID198
Feature activation+1.34e-01

Pos logit contributions
Psych+0.264
issan+0.256
psych+0.230
Dex+0.227
 Psych+0.221
Neg logit contributions
rio-0.513
Ire-0.490
 Trave-0.449
-0.444
 Surviv-0.442
Token
Token ID198
Feature activation+1.66e-01

Pos logit contributions
Psych+0.064
issan+0.062
psych+0.055
Dex+0.055
 Psych+0.053
Neg logit contributions
rio-0.133
Ire-0.127
 Trave-0.116
-0.115
 Surviv-0.115
TokenW
Token ID54
Feature activation+6.18e-01

Pos logit contributions
Psych+0.127
issan+0.124
psych+0.116
Dex+0.115
 Psych+0.113
Neg logit contributions
rio-0.117
Ire-0.109
 Trave-0.097
-0.095
 Surviv-0.095
Tokenass
Token ID562
Feature activation+2.22e+00

Pos logit contributions
Psych+0.094
issan+0.083
psych+0.054
Dex+0.052
 Psych+0.044
Neg logit contributions
rio-0.810
Ire-0.784
 Trave-0.733
-0.729
 Surviv-0.726
Tokenerman
Token ID2224
Feature activation+4.85e-01

Pos logit contributions
Psych+1.225
issan+1.195
psych+1.092
Dex+1.053
 Psych+1.051
Neg logit contributions
rio-2.029
Ire-1.953
 Trave-1.782
 Surviv-1.751
-1.747
Token is
Token ID318
Feature activation+3.83e-01

Pos logit contributions
Psych+0.256
issan+0.246
psych+0.225
Dex+0.221
 Psych+0.218
Neg logit contributions
rio-0.457
Ire-0.439
 Trave-0.399
-0.395
 Surviv-0.394
Token the
Token ID262
Feature activation+4.87e-01

Pos logit contributions
Psych+0.245
issan+0.239
psych+0.220
Dex+0.218
 Psych+0.215
Neg logit contributions
rio-0.316
Ire-0.300
 Trave-0.270
-0.268
 Surviv-0.266
Token current
Token ID1459
Feature activation+8.90e-01

Pos logit contributions
Psych+0.281
issan+0.272
psych+0.249
Dex+0.246
 Psych+0.244
Neg logit contributions
rio-0.431
Ire-0.411
 Trave-0.371
-0.371
 Surviv-0.366
Token chair
Token ID5118
Feature activation+4.89e-01

Pos logit contributions
Psych+0.595
issan+0.579
psych+0.538
Dex+0.532
 Psych+0.528
Neg logit contributions
rio-0.705
Ire-0.668
-0.596
 Trave-0.596
 Surviv-0.586
Token rage
Token ID14404
Feature activation-1.43e+00

Pos logit contributions
rio+0.038
Ire+0.036
 Trave+0.032
+0.032
 Surviv+0.032
Neg logit contributions
Psych-0.030
issan-0.029
psych-0.027
Dex-0.026
 Psych-0.026
Token.
Token ID13
Feature activation+1.01e-01

Pos logit contributions
rio+1.124
Ire+1.059
 Trave+0.951
+0.938
 Surviv+0.931
Neg logit contributions
Psych-0.972
issan-0.951
psych-0.878
Dex-0.871
 Psych-0.854
Token
Token ID198
Feature activation-1.13e-02

Pos logit contributions
Psych+0.062
issan+0.061
psych+0.056
Dex+0.055
 Psych+0.054
Neg logit contributions
rio-0.085
Ire-0.081
 Trave-0.073
-0.072
 Surviv-0.072
Token
Token ID198
Feature activation-7.82e-02

Pos logit contributions
rio+0.011
Ire+0.011
 Trave+0.010
+0.010
 Surviv+0.010
Neg logit contributions
Psych-0.005
issan-0.005
psych-0.005
Dex-0.005
 Psych-0.005
Tokenpolit
Token ID34470
Feature activation+2.37e-02

Pos logit contributions
rio+0.055
Ire+0.051
 Trave+0.045
 Surviv+0.045
+0.045
Neg logit contributions
Psych-0.060
issan-0.059
psych-0.055
Dex-0.055
 Psych-0.053
Tokenically
Token ID1146
Feature activation+2.17e+00

Pos logit contributions
Psych+0.014
issan+0.014
psych+0.013
Dex+0.012
 Psych+0.012
Neg logit contributions
rio-0.021
Ire-0.020
 Trave-0.018
-0.018
 Surviv-0.018
Token correct
Token ID3376
Feature activation-1.27e-01

Pos logit contributions
Psych+1.443
issan+1.402
psych+1.312
Dex+1.290
 Psych+1.280
Neg logit contributions
rio-1.729
Ire-1.647
-1.464
 Trave-1.462
 Surviv-1.459
Token o
Token ID267
Feature activation-1.60e+00

Pos logit contributions
rio+0.102
Ire+0.097
 Trave+0.087
+0.086
 Surviv+0.085
Neg logit contributions
Psych-0.084
issan-0.082
psych-0.076
Dex-0.075
 Psych-0.074
Tokenomp
Token ID3361
Feature activation-1.27e-01

Pos logit contributions
rio+1.271
Ire+1.198
 Trave+1.076
+1.061
 Surviv+1.057
Neg logit contributions
Psych-1.076
issan-1.050
psych-0.971
Dex-0.962
 Psych-0.944
Tokena
Token ID64
Feature activation-4.58e-01

Pos logit contributions
rio+0.107
Ire+0.102
 Trave+0.092
+0.091
 Surviv+0.090
Neg logit contributions
Psych-0.078
issan-0.076
psych-0.070
Dex-0.069
 Psych-0.068
Token lo
Token ID2376
Feature activation+1.67e-01

Pos logit contributions
rio+0.395
Ire+0.376
 Trave+0.340
+0.336
 Surviv+0.334
Neg logit contributions
Psych-0.276
issan-0.269
psych-0.246
Dex-0.244
 Psych-0.239
Token them
Token ID606
Feature activation-1.66e-01

Pos logit contributions
rio+0.198
Ire+0.189
 Trave+0.171
+0.169
 Surviv+0.168
Neg logit contributions
Psych-0.134
issan-0.130
psych-0.119
Dex-0.118
 Psych-0.116
Token fresh
Token ID4713
Feature activation+8.37e-01

Pos logit contributions
rio+0.139
Ire+0.132
 Trave+0.119
+0.117
 Surviv+0.117
Neg logit contributions
Psych-0.105
issan-0.102
psych-0.094
Dex-0.093
 Psych-0.091
Token or
Token ID393
Feature activation+3.43e-01

Pos logit contributions
Psych+0.519
issan+0.506
psych+0.466
Dex+0.460
 Psych+0.452
Neg logit contributions
rio-0.707
Ire-0.673
 Trave-0.606
-0.600
 Surviv-0.597
Token in
Token ID287
Feature activation+4.29e-02

Pos logit contributions
Psych+0.179
issan+0.173
psych+0.157
Dex+0.155
 Psych+0.152
Neg logit contributions
rio-0.323
Ire-0.310
 Trave-0.281
-0.279
 Surviv-0.277
Token their
Token ID511
Feature activation-9.30e-02

Pos logit contributions
Psych+0.028
issan+0.027
psych+0.025
Dex+0.025
 Psych+0.024
Neg logit contributions
rio-0.035
Ire-0.033
 Trave-0.030
-0.029
 Surviv-0.029
Token dry
Token ID5894
Feature activation+2.17e+00

Pos logit contributions
rio+0.079
Ire+0.075
 Trave+0.068
+0.068
 Surviv+0.067
Neg logit contributions
Psych-0.057
issan-0.055
psych-0.051
Dex-0.050
 Psych-0.049
Token state
Token ID1181
Feature activation+4.74e-01

Pos logit contributions
Psych+1.339
issan+1.309
psych+1.204
Dex+1.187
 Psych+1.166
Neg logit contributions
rio-1.830
Ire-1.743
 Trave-1.568
-1.553
 Surviv-1.545
Token.
Token ID13
Feature activation+8.03e-02

Pos logit contributions
Psych+0.297
issan+0.290
psych+0.267
Dex+0.264
 Psych+0.259
Neg logit contributions
rio-0.397
Ire-0.377
 Trave-0.340
-0.337
 Surviv-0.335
Token Some
Token ID2773
Feature activation+2.11e-01

Pos logit contributions
Psych+0.058
issan+0.056
psych+0.052
Dex+0.052
 Psych+0.051
Neg logit contributions
rio-0.060
Ire-0.057
 Trave-0.050
-0.050
 Surviv-0.049
Token people
Token ID661
Feature activation-2.32e-01

Pos logit contributions
Psych+0.126
issan+0.122
psych+0.112
Dex+0.111
 Psych+0.109
Neg logit contributions
rio-0.183
Ire-0.174
 Trave-0.157
-0.156
 Surviv-0.154
Token have
Token ID423
Feature activation-1.61e-01

Pos logit contributions
rio+0.183
Ire+0.174
 Trave+0.155
+0.155
 Surviv+0.153
Neg logit contributions
Psych-0.156
issan-0.152
psych-0.141
Dex-0.139
 Psych-0.137
Token dumping
Token ID30231
Feature activation+1.03e-01

Pos logit contributions
Psych+0.044
issan+0.043
psych+0.040
Dex+0.039
 Psych+0.039
Neg logit contributions
rio-0.062
Ire-0.059
 Trave-0.053
-0.053
 Surviv-0.052
Token area
Token ID1989
Feature activation-7.40e-01

Pos logit contributions
Psych+0.063
issan+0.062
psych+0.057
Dex+0.056
 Psych+0.055
Neg logit contributions
rio-0.087
Ire-0.082
 Trave-0.074
-0.074
 Surviv-0.073
Token at
Token ID379
Feature activation-5.56e-02

Pos logit contributions
rio+0.601
Ire+0.570
 Trave+0.512
+0.506
 Surviv+0.503
Neg logit contributions
Psych-0.482
issan-0.471
psych-0.434
Dex-0.430
 Psych-0.422
Token the
Token ID262
Feature activation-1.32e-01

Pos logit contributions
rio+0.045
Ire+0.043
 Trave+0.038
+0.038
 Surviv+0.038
Neg logit contributions
Psych-0.036
issan-0.035
psych-0.032
Dex-0.032
 Psych-0.032
Token Arrow
Token ID19408
Feature activation-1.36e+00

Pos logit contributions
rio+0.108
Ire+0.103
 Trave+0.091
+0.091
 Surviv+0.090
Neg logit contributions
Psych-0.085
issan-0.083
psych-0.077
Dex-0.076
 Psych-0.075
Tokenhead
Token ID2256
Feature activation+2.14e+00

Pos logit contributions
rio+1.086
Ire+1.028
 Trave+0.922
+0.911
 Surviv+0.905
Neg logit contributions
Psych-0.908
issan-0.885
psych-0.819
Dex-0.810
 Psych-0.795
Token Land
Token ID6379
Feature activation-1.80e-01

Pos logit contributions
Psych+1.468
issan+1.436
Dex+1.329
psych+1.326
 Psych+1.323
Neg logit contributions
rio-1.634
Ire-1.574
-1.380
 Trave-1.362
 Surviv-1.354
Tokenfill
Token ID20797
Feature activation-5.54e-01

Pos logit contributions
rio+0.148
Ire+0.141
 Trave+0.126
+0.125
 Surviv+0.124
Neg logit contributions
Psych-0.115
issan-0.112
psych-0.104
Dex-0.103
 Psych-0.101
Token in
Token ID287
Feature activation-4.44e-02

Pos logit contributions
rio+0.463
Ire+0.441
 Trave+0.395
+0.392
 Surviv+0.389
Neg logit contributions
Psych-0.348
issan-0.339
psych-0.312
Dex-0.310
 Psych-0.304
Token Union
Token ID4479
Feature activation-9.84e-01

Pos logit contributions
rio+0.037
Ire+0.035
 Trave+0.032
+0.032
 Surviv+0.031
Neg logit contributions
Psych-0.028
issan-0.027
psych-0.025
Dex-0.025
 Psych-0.025
Tokentown
Token ID12735
Feature activation-2.33e-01

Pos logit contributions
rio+0.831
Ire+0.793
 Trave+0.713
+0.709
 Surviv+0.704
Neg logit contributions
Psych-0.609
issan-0.593
psych-0.546
Dex-0.540
 Psych-0.530
Tokenguy
Token ID22932
Feature activation-6.01e-01

Pos logit contributions
Psych+0.067
issan+0.064
psych+0.058
Dex+0.057
 Psych+0.055
Neg logit contributions
rio-0.132
Ire-0.126
 Trave-0.116
-0.114
 Surviv-0.114
Token,
Token ID11
Feature activation+7.73e-04

Pos logit contributions
rio+0.488
Ire+0.464
 Trave+0.414
+0.412
 Surviv+0.409
Neg logit contributions
Psych-0.391
issan-0.381
psych-0.352
Dex-0.349
 Psych-0.344
Token unconditional
Token ID42423
Feature activation-1.56e-02

Pos logit contributions
Psych+0.001
issan+0.001
psych+0.000
Dex+0.000
 Psych+0.000
Neg logit contributions
rio-0.001
Ire-0.001
 Trave-0.001
 Surviv-0.001
-0.001
Token-
Token ID12
Feature activation+3.02e-03

Pos logit contributions
rio+0.012
Ire+0.012
 Trave+0.010
+0.010
 Surviv+0.010
Neg logit contributions
Psych-0.010
issan-0.010
psych-0.009
Dex-0.009
 Psych-0.009
Tokenl
Token ID75
Feature activation+9.20e-02

Pos logit contributions
Psych+0.002
issan+0.002
psych+0.002
Dex+0.002
 Psych+0.002
Neg logit contributions
rio-0.002
Ire-0.002
 Trave-0.002
 Surviv-0.002
-0.002
Tokenoyal
Token ID4815
Feature activation+2.13e+00

Pos logit contributions
Psych+0.061
issan+0.060
psych+0.056
Dex+0.055
 Psych+0.054
Neg logit contributions
rio-0.073
Ire-0.069
 Trave-0.062
-0.062
 Surviv-0.061
Tokenty
Token ID774
Feature activation+1.00e+00

Pos logit contributions
Psych+1.126
issan+1.114
psych+0.999
Dex+0.988
 Psych+0.979
Neg logit contributions
rio-1.968
Ire-1.876
 Trave-1.698
 Surviv-1.695
-1.693
Token-
Token ID12
Feature activation+1.60e-01

Pos logit contributions
Psych+0.612
issan+0.598
psych+0.549
Dex+0.546
 Psych+0.538
Neg logit contributions
rio-0.853
Ire-0.811
 Trave-0.727
-0.725
 Surviv-0.725
Tokenvers
Token ID690
Feature activation+5.29e-01

Pos logit contributions
Psych+0.116
issan+0.112
psych+0.106
Dex+0.104
 Psych+0.102
Neg logit contributions
rio-0.118
Ire-0.112
 Trave-0.100
 Surviv-0.099
-0.098
Tokenus
Token ID385
Feature activation+8.27e-01

Pos logit contributions
Psych+0.238
issan+0.231
psych+0.205
Dex+0.201
 Psych+0.196
Neg logit contributions
rio-0.534
Ire-0.513
 Trave-0.470
-0.466
 Surviv-0.465
Token-
Token ID12
Feature activation+8.01e-02

Pos logit contributions
Psych+0.486
issan+0.472
psych+0.433
Dex+0.427
 Psych+0.419
Neg logit contributions
rio-0.724
Ire-0.689
 Trave-0.624
-0.616
 Surviv-0.616
Token.
Token ID13
Feature activation-4.84e-02

Pos logit contributions
rio+0.073
Ire+0.069
 Trave+0.062
+0.061
 Surviv+0.061
Neg logit contributions
Psych-0.057
issan-0.056
psych-0.051
Dex-0.051
 Psych-0.050
Token
Token ID447
Feature activation+8.94e-02

Pos logit contributions
rio+0.042
Ire+0.040
 Trave+0.036
+0.036
 Surviv+0.035
Neg logit contributions
Psych-0.029
issan-0.028
psych-0.026
Dex-0.026
 Psych-0.025
Token
Token ID251
Feature activation-5.06e-03

Pos logit contributions
Psych+0.052
issan+0.051
psych+0.047
Dex+0.046
 Psych+0.045
Neg logit contributions
rio-0.079
Ire-0.075
 Trave-0.068
-0.067
 Surviv-0.067
Token<|endoftext|>
Token ID50256
Feature activation-2.63e-01

Pos logit contributions
rio+0.005
Ire+0.005
 Trave+0.004
+0.004
 Surviv+0.004
Neg logit contributions
Psych-0.003
issan-0.003
psych-0.002
Dex-0.002
 Psych-0.002
TokenImage
Token ID5159
Feature activation-1.96e-01

Pos logit contributions
rio+0.193
Ire+0.181
 Trave+0.161
+0.159
 Surviv+0.158
Neg logit contributions
Psych-0.193
issan-0.188
psych-0.175
Dex-0.174
 Psych-0.170
Token copyright
Token ID6634
Feature activation+2.12e+00

Pos logit contributions
rio+0.181
Ire+0.173
 Trave+0.158
+0.156
 Surviv+0.155
Neg logit contributions
Psych-0.106
issan-0.103
psych-0.093
Dex-0.092
 Psych-0.090
Token publicity
Token ID19403
Feature activation+1.35e+00

Pos logit contributions
Psych+1.349
issan+1.308
psych+1.210
 Psych+1.201
Dex+1.199
Neg logit contributions
rio-1.743
Ire-1.660
-1.470
 Trave-1.467
 Surviv-1.448
Token Image
Token ID7412
Feature activation+7.37e-01

Pos logit contributions
Psych+0.752
issan+0.725
psych+0.667
Dex+0.658
 Psych+0.642
Neg logit contributions
rio-1.222
Ire-1.166
 Trave-1.059
 Surviv-1.051
-1.048
Token caption
Token ID8305
Feature activation+1.65e+00

Pos logit contributions
Psych+0.436
issan+0.424
psych+0.388
Dex+0.384
 Psych+0.376
Neg logit contributions
rio-0.643
Ire-0.612
 Trave-0.554
-0.548
 Surviv-0.546
Token The
Token ID383
Feature activation+5.75e-01

Pos logit contributions
Psych+1.158
issan+1.123
 Psych+1.048
psych+1.046
Dex+1.041
Neg logit contributions
rio-1.256
Ire-1.187
-1.046
 Trave-1.025
 Surviv-1.019
Token Greeks
Token ID25059
Feature activation-4.04e-01

Pos logit contributions
Psych+0.376
issan+0.367
psych+0.339
Dex+0.334
 Psych+0.333
Neg logit contributions
rio-0.465
Ire-0.443
-0.394
 Trave-0.392
 Surviv-0.389
Token no
Token ID645
Feature activation+6.37e-01

Pos logit contributions
Psych+0.368
issan+0.356
psych+0.328
Dex+0.325
 Psych+0.322
Neg logit contributions
rio-0.498
Ire-0.475
 Trave-0.424
-0.423
 Surviv-0.419
Token holds
Token ID6622
Feature activation-4.93e-01

Pos logit contributions
Psych+0.356
issan+0.347
psych+0.315
Dex+0.311
 Psych+0.306
Neg logit contributions
rio-0.574
Ire-0.549
 Trave-0.498
-0.495
 Surviv-0.492
Token barred
Token ID23902
Feature activation-1.89e-01

Pos logit contributions
rio+0.396
Ire+0.375
 Trave+0.337
+0.333
 Surviv+0.330
Neg logit contributions
Psych-0.326
issan-0.319
psych-0.294
Dex-0.291
 Psych-0.286
Token to
Token ID284
Feature activation+2.93e-01

Pos logit contributions
rio+0.156
Ire+0.148
 Trave+0.134
+0.132
 Surviv+0.131
Neg logit contributions
Psych-0.121
issan-0.118
psych-0.109
Dex-0.107
 Psych-0.106
Token the
Token ID262
Feature activation+1.99e-01

Pos logit contributions
Psych+0.186
issan+0.182
psych+0.166
Dex+0.165
 Psych+0.164
Neg logit contributions
rio-0.242
Ire-0.230
-0.205
 Trave-0.205
 Surviv-0.203
Token che
Token ID1125
Feature activation+2.11e+00

Pos logit contributions
Psych+0.133
issan+0.130
psych+0.120
Dex+0.119
 Psych+0.118
Neg logit contributions
rio-0.157
Ire-0.149
 Trave-0.133
-0.133
 Surviv-0.131
Tokenqu
Token ID421
Feature activation-6.98e-01

Pos logit contributions
Psych+1.440
issan+1.436
psych+1.325
Dex+1.300
 Psych+1.275
Neg logit contributions
rio-1.612
Ire-1.563
 Trave-1.376
-1.372
 Surviv-1.358
Tokenered
Token ID1068
Feature activation-5.48e-01

Pos logit contributions
rio+0.553
Ire+0.529
 Trave+0.471
+0.469
 Surviv+0.464
Neg logit contributions
Psych-0.466
issan-0.457
psych-0.422
Dex-0.419
 Psych-0.410
Token flag
Token ID6056
Feature activation+8.69e-01

Pos logit contributions
rio+0.538
Ire+0.515
 Trave+0.472
+0.468
 Surviv+0.466
Neg logit contributions
Psych-0.264
issan-0.256
psych-0.229
Dex-0.225
 Psych-0.220
Token!
Token ID0
Feature activation-1.03e-01

Pos logit contributions
Psych+0.557
issan+0.545
psych+0.502
Dex+0.497
 Psych+0.490
Neg logit contributions
rio-0.709
Ire-0.679
 Trave-0.606
-0.602
 Surviv-0.599
Token Race
Token ID12588
Feature activation+8.26e-01

Pos logit contributions
rio+0.082
Ire+0.077
+0.069
 Trave+0.069
 Surviv+0.068
Neg logit contributions
Psych-0.069
issan-0.067
psych-0.062
Dex-0.061
 Psych-0.061
Token sh
Token ID427
Feature activation-5.31e-01

Pos logit contributions
rio+0.255
Ire+0.242
 Trave+0.218
+0.216
 Surviv+0.214
Neg logit contributions
Psych-0.199
issan-0.194
psych-0.179
Dex-0.177
 Psych-0.174
Tokenrooms
Token ID9649
Feature activation+2.53e-01

Pos logit contributions
rio+0.406
Ire+0.382
 Trave+0.341
+0.336
 Surviv+0.334
Neg logit contributions
Psych-0.372
issan-0.364
psych-0.337
Dex-0.335
 Psych-0.329
Token (
Token ID357
Feature activation-1.47e-02

Pos logit contributions
Psych+0.175
issan+0.171
psych+0.159
Dex+0.157
 Psych+0.155
Neg logit contributions
rio-0.195
Ire-0.185
 Trave-0.165
-0.163
 Surviv-0.162
Tokenfresh
Token ID48797
Feature activation+7.63e-01

Pos logit contributions
rio+0.011
Ire+0.010
 Trave+0.009
+0.009
 Surviv+0.009
Neg logit contributions
Psych-0.011
issan-0.011
psych-0.010
Dex-0.010
 Psych-0.010
Token or
Token ID393
Feature activation+1.65e-01

Pos logit contributions
Psych+0.485
issan+0.472
psych+0.438
Dex+0.432
 Psych+0.424
Neg logit contributions
rio-0.630
Ire-0.602
 Trave-0.539
-0.533
 Surviv-0.531
Token dry
Token ID5894
Feature activation+2.10e+00

Pos logit contributions
Psych+0.089
issan+0.086
psych+0.078
Dex+0.077
 Psych+0.076
Neg logit contributions
rio-0.153
Ire-0.146
 Trave-0.133
-0.132
 Surviv-0.131
Token)
Token ID8
Feature activation+2.99e-01

Pos logit contributions
Psych+1.412
issan+1.377
psych+1.282
Dex+1.262
 Psych+1.248
Neg logit contributions
rio-1.649
Ire-1.568
 Trave-1.398
-1.382
 Surviv-1.380
Token and
Token ID290
Feature activation-3.70e-02

Pos logit contributions
Psych+0.209
issan+0.205
psych+0.190
Dex+0.188
 Psych+0.185
Neg logit contributions
rio-0.229
Ire-0.217
 Trave-0.193
-0.190
 Surviv-0.189
Token wh
Token ID348
Feature activation-3.33e-01

Pos logit contributions
rio+0.030
Ire+0.029
 Trave+0.026
+0.026
 Surviv+0.025
Neg logit contributions
Psych-0.024
issan-0.023
psych-0.021
Dex-0.021
 Psych-0.021
Tokeniz
Token ID528
Feature activation+2.29e-01

Pos logit contributions
rio+0.259
Ire+0.247
 Trave+0.221
+0.218
 Surviv+0.217
Neg logit contributions
Psych-0.228
issan-0.223
psych-0.207
Dex-0.204
 Psych-0.200
Token on
Token ID319
Feature activation+1.30e-01

Pos logit contributions
Psych+0.151
issan+0.147
psych+0.136
Dex+0.134
 Psych+0.132
Neg logit contributions
rio-0.185
Ire-0.176
 Trave-0.158
-0.156
 Surviv-0.155
Token00
Token ID405
Feature activation-4.77e-01

Pos logit contributions
rio+0.066
Ire+0.063
 Trave+0.057
+0.057
 Surviv+0.057
Neg logit contributions
Psych-0.047
issan-0.045
psych-0.042
Dex-0.042
 Psych-0.040
Token.
Token ID13
Feature activation-1.49e-01

Pos logit contributions
rio+0.413
Ire+0.394
+0.354
 Trave+0.354
 Surviv+0.351
Neg logit contributions
Psych-0.285
issan-0.277
psych-0.254
Dex-0.250
 Psych-0.249
Token Delivery
Token ID28682
Feature activation-4.45e-01

Pos logit contributions
rio+0.124
Ire+0.118
+0.107
 Trave+0.105
ð+0.105
Neg logit contributions
Psych-0.093
issan-0.090
psych-0.084
 Psych-0.082
Dex-0.082
Token:
Token ID25
Feature activation-2.57e-01

Pos logit contributions
rio+0.415
Ire+0.397
 Trave+0.360
+0.360
 Surviv+0.358
Neg logit contributions
Psych-0.237
issan-0.229
psych-0.207
Dex-0.205
 Psych-0.202
Token V
Token ID569
Feature activation+5.09e-01

Pos logit contributions
rio+0.195
Ire+0.185
+0.163
 Trave+0.161
 Surviv+0.160
Neg logit contributions
Psych-0.183
issan-0.178
psych-0.166
Dex-0.164
 Psych-0.164
Tokenaries
Token ID3166
Feature activation+2.10e+00

Pos logit contributions
Psych+0.389
issan+0.381
psych+0.354
Dex+0.353
 Psych+0.348
Neg logit contributions
rio-0.353
Ire-0.336
 Trave-0.296
-0.294
 Surviv-0.291
Token Invalid
Token ID17665
Feature activation+1.01e-01

Pos logit contributions
Psych+1.306
issan+1.254
psych+1.163
 Psych+1.158
Dex+1.144
Neg logit contributions
rio-1.739
Ire-1.691
-1.513
 Trave-1.471
ð-1.465
Token email
Token ID3053
Feature activation+4.91e-01

Pos logit contributions
Psych+0.071
issan+0.069
psych+0.064
Dex+0.063
 Psych+0.063
Neg logit contributions
rio-0.077
Ire-0.073
-0.065
 Trave-0.065
 Surviv-0.064
Token address
Token ID2209
Feature activation-8.46e-01

Pos logit contributions
Psych+0.329
issan+0.319
psych+0.297
Dex+0.293
 Psych+0.289
Neg logit contributions
rio-0.390
Ire-0.372
 Trave-0.331
-0.331
 Surviv-0.328
Token Thank
Token ID6952
Feature activation+4.19e-01

Pos logit contributions
rio+0.699
Ire+0.664
+0.594
 Trave+0.592
 Surviv+0.588
Neg logit contributions
Psych-0.543
issan-0.527
psych-0.488
Dex-0.481
 Psych-0.478
Token you
Token ID345
Feature activation-2.76e-01

Pos logit contributions
Psych+0.267
issan+0.256
psych+0.239
Dex+0.237
 Psych+0.234
Neg logit contributions
rio-0.345
Ire-0.332
 Trave-0.297
-0.296
 Surviv-0.294
Token hotel
Token ID7541
Feature activation-5.78e-01

Pos logit contributions
Psych+0.089
issan+0.087
psych+0.080
Dex+0.079
 Psych+0.078
Neg logit contributions
rio-0.122
Ire-0.117
 Trave-0.104
-0.104
 Surviv-0.103
Token room
Token ID2119
Feature activation-3.97e-01

Pos logit contributions
rio+0.416
Ire+0.397
 Trave+0.346
+0.344
 Surviv+0.342
Neg logit contributions
Psych-0.430
issan-0.422
psych-0.392
Dex-0.389
 Psych-0.385
Token at
Token ID379
Feature activation+7.95e-02

Pos logit contributions
rio+0.335
Ire+0.320
 Trave+0.286
+0.283
 Surviv+0.283
Neg logit contributions
Psych-0.247
issan-0.241
psych-0.221
Dex-0.219
 Psych-0.215
Token the
Token ID262
Feature activation+2.90e-01

Pos logit contributions
Psych+0.051
issan+0.050
psych+0.045
Dex+0.045
 Psych+0.045
Neg logit contributions
rio-0.066
Ire-0.063
 Trave-0.056
-0.055
 Surviv-0.055
Token Hy
Token ID6707
Feature activation+9.92e-01

Pos logit contributions
Psych+0.190
issan+0.185
psych+0.170
 Psych+0.169
 Haas+0.169
Neg logit contributions
rio-0.234
Ire-0.223
-0.197
 Trave-0.197
 Surviv-0.195
Tokenatt
Token ID1078
Feature activation+2.08e+00

Pos logit contributions
Psych+0.452
issan+0.436
psych+0.387
Dex+0.382
 Psych+0.371
Neg logit contributions
rio-1.002
Ire-0.952
 Trave-0.881
 Surviv-0.868
-0.866
Token Reg
Token ID3310
Feature activation+1.07e+00

Pos logit contributions
Psych+1.410
issan+1.377
Dex+1.274
psych+1.266
 Psych+1.264
Neg logit contributions
rio-1.620
Ire-1.574
 Surviv-1.367
 Trave-1.364
-1.363
Tokenency
Token ID1387
Feature activation-8.81e-01

Pos logit contributions
Psych+0.504
issan+0.476
psych+0.433
Dex+0.424
 Psych+0.421
Neg logit contributions
rio-1.055
Ire-1.022
 Trave-0.934
-0.931
 Surviv-0.925
Token Irvine
Token ID37277
Feature activation-4.30e-01

Pos logit contributions
rio+0.767
Ire+0.729
 Trave+0.661
+0.654
 Surviv+0.650
Neg logit contributions
Psych-0.523
issan-0.509
psych-0.466
Dex-0.460
 Psych-0.451
Token,
Token ID11
Feature activation+1.39e-01

Pos logit contributions
rio+0.352
Ire+0.334
 Trave+0.300
+0.297
 Surviv+0.295
Neg logit contributions
Psych-0.278
issan-0.271
psych-0.250
Dex-0.247
 Psych-0.243
Token November
Token ID3389
Feature activation+3.18e-01

Pos logit contributions
Psych+0.069
issan+0.067
psych+0.060
Dex+0.059
 Psych+0.058
Neg logit contributions
rio-0.134
Ire-0.128
 Trave-0.117
-0.116
 Surviv-0.116
Token be
Token ID307
Feature activation-2.58e-01

Pos logit contributions
Psych+0.031
issan+0.030
psych+0.028
Dex+0.027
 Psych+0.027
Neg logit contributions
rio-0.043
Ire-0.041
 Trave-0.037
-0.037
 Surviv-0.036
Token real
Token ID1103
Feature activation-1.03e-01

Pos logit contributions
rio+0.218
Ire+0.207
 Trave+0.187
+0.185
 Surviv+0.184
Neg logit contributions
Psych-0.160
issan-0.156
psych-0.143
Dex-0.142
 Psych-0.138
Token-
Token ID12
Feature activation-2.68e-01

Pos logit contributions
rio+0.085
Ire+0.080
 Trave+0.072
+0.071
 Surviv+0.071
Neg logit contributions
Psych-0.066
issan-0.064
psych-0.059
Dex-0.058
 Psych-0.057
Tokenlife
Token ID6042
Feature activation-6.24e-01

Pos logit contributions
rio+0.231
Ire+0.220
 Trave+0.199
+0.197
 Surviv+0.196
Neg logit contributions
Psych-0.161
issan-0.157
psych-0.143
Dex-0.142
 Psych-0.139
Token pur
Token ID1308
Feature activation-1.60e-01

Pos logit contributions
rio+0.531
Ire+0.499
 Trave+0.459
 Surviv+0.449
+0.448
Neg logit contributions
Psych-0.382
issan-0.375
psych-0.340
Dex-0.338
 Haas-0.328
Tokenges
Token ID3212
Feature activation-3.62e+00

Pos logit contributions
rio+0.126
Ire+0.120
 Trave+0.107
+0.106
 Surviv+0.105
Neg logit contributions
Psych-0.109
issan-0.106
psych-0.098
Dex-0.097
 Psych-0.096
Token,
Token ID11
Feature activation-8.16e-02

Pos logit contributions
rio+2.806
Ire+2.594
 Trave+2.369
+2.310
 Surviv+2.288
Neg logit contributions
Psych-2.475
issan-2.448
psych-2.227
Dex-2.223
 Haas-2.154
Token and
Token ID290
Feature activation+2.26e-02

Pos logit contributions
rio+0.067
Ire+0.064
 Trave+0.058
+0.057
 Surviv+0.057
Neg logit contributions
Psych-0.052
issan-0.051
psych-0.047
Dex-0.046
 Psych-0.045
Token they
Token ID484
Feature activation-9.09e-02

Pos logit contributions
Psych+0.013
issan+0.013
psych+0.012
Dex+0.012
 Psych+0.011
Neg logit contributions
rio-0.020
Ire-0.019
 Trave-0.017
-0.017
 Surviv-0.017
Token
Token ID447
Feature activation+2.99e-01

Pos logit contributions
rio+0.077
Ire+0.073
 Trave+0.066
+0.065
 Surviv+0.065
Neg logit contributions
Psych-0.057
issan-0.055
psych-0.051
Dex-0.050
 Psych-0.049
Token
Token ID247
Feature activation-1.06e-01

Pos logit contributions
Psych+0.196
issan+0.190
psych+0.177
Dex+0.175
 Psych+0.172
Neg logit contributions
rio-0.242
Ire-0.229
 Trave-0.206
-0.205
 Surviv-0.203
Token is
Token ID318
Feature activation+4.76e-02

Pos logit contributions
Psych+0.208
issan+0.203
psych+0.188
Dex+0.186
 Psych+0.182
Neg logit contributions
rio-0.246
Ire-0.233
 Trave-0.209
-0.206
 Surviv-0.205
Token long
Token ID890
Feature activation+4.67e-01

Pos logit contributions
Psych+0.030
issan+0.029
psych+0.027
Dex+0.027
 Psych+0.026
Neg logit contributions
rio-0.039
Ire-0.037
 Trave-0.034
-0.033
 Surviv-0.033
Token;
Token ID26
Feature activation+6.32e-01

Pos logit contributions
Psych+0.301
issan+0.294
psych+0.271
Dex+0.267
 Psych+0.264
Neg logit contributions
rio-0.382
Ire-0.363
 Trave-0.326
 Surviv-0.322
-0.322
Token he
Token ID339
Feature activation+2.82e-01

Pos logit contributions
Psych+0.375
issan+0.365
psych+0.334
Dex+0.330
 Psych+0.324
Neg logit contributions
rio-0.550
Ire-0.523
 Trave-0.474
-0.469
 Surviv-0.466
Token comm
Token ID725
Feature activation+1.67e+00

Pos logit contributions
Psych+0.191
issan+0.187
psych+0.173
Dex+0.171
 Psych+0.168
Neg logit contributions
rio-0.222
Ire-0.211
 Trave-0.188
-0.186
 Surviv-0.185
Tokenends
Token ID2412
Feature activation-3.46e+00

Pos logit contributions
Psych+1.221
issan+1.192
psych+1.118
Dex+1.098
 Psych+1.085
Neg logit contributions
rio-1.216
Ire-1.155
 Trave-1.023
-1.018
 Surviv-1.011
Token the
Token ID262
Feature activation+2.45e-01

Pos logit contributions
rio+2.793
Ire+2.634
 Trave+2.430
+2.339
 Surviv+2.338
Neg logit contributions
Psych-2.237
issan-2.198
psych-2.018
Dex-1.997
 Psych-1.923
Token Monday
Token ID3321
Feature activation+5.17e-01

Pos logit contributions
Psych+0.158
issan+0.154
psych+0.143
Dex+0.141
 Psych+0.140
Neg logit contributions
rio-0.200
Ire-0.190
 Trave-0.169
-0.169
 Surviv-0.168
Token job
Token ID1693
Feature activation+3.08e-01

Pos logit contributions
Psych+0.334
issan+0.324
psych+0.300
Dex+0.296
 Psych+0.293
Neg logit contributions
rio-0.423
Ire-0.402
 Trave-0.359
-0.358
 Surviv-0.356
Token-
Token ID12
Feature activation+8.17e-02

Pos logit contributions
Psych+0.196
issan+0.191
psych+0.176
Dex+0.174
 Psych+0.170
Neg logit contributions
rio-0.256
Ire-0.243
 Trave-0.219
-0.216
 Surviv-0.215
Tokenseekers
Token ID47971
Feature activation+2.96e-02

Pos logit contributions
Psych+0.060
issan+0.059
psych+0.055
Dex+0.054
 Psych+0.053
Neg logit contributions
rio-0.059
Ire-0.056
 Trave-0.050
-0.049
 Surviv-0.049
Token the
Token ID262
Feature activation-4.64e-01

Pos logit contributions
rio+0.202
Ire+0.192
 Trave+0.171
+0.170
 Surviv+0.169
Neg logit contributions
Psych-0.166
issan-0.162
psych-0.150
Dex-0.148
 Psych-0.146
Token United
Token ID1578
Feature activation+3.93e-01

Pos logit contributions
rio+0.363
Ire+0.343
 Trave+0.306
+0.304
 Surviv+0.301
Neg logit contributions
Psych-0.317
issan-0.310
psych-0.288
Dex-0.285
 Psych-0.281
Token States
Token ID1829
Feature activation+5.25e-01

Pos logit contributions
Psych+0.197
issan+0.191
psych+0.171
Dex+0.169
 Psych+0.165
Neg logit contributions
rio-0.379
Ire-0.363
 Trave-0.332
-0.329
 Surviv-0.327
Token,
Token ID11
Feature activation-6.76e-01

Pos logit contributions
Psych+0.358
issan+0.350
psych+0.324
Dex+0.321
 Psych+0.318
Neg logit contributions
rio-0.410
Ire-0.389
 Trave-0.345
-0.343
 Surviv-0.341
Token dev
Token ID1614
Feature activation+2.31e-02

Pos logit contributions
rio+0.573
Ire+0.544
 Trave+0.494
+0.486
 Surviv+0.484
Neg logit contributions
Psych-0.417
issan-0.405
psych-0.372
Dex-0.368
 Psych-0.359
Tokenolution
Token ID2122
Feature activation-3.43e+00

Pos logit contributions
Psych+0.017
issan+0.017
psych+0.015
Dex+0.015
 Psych+0.015
Neg logit contributions
rio-0.017
Ire-0.016
 Trave-0.014
-0.014
 Surviv-0.014
Token of
Token ID286
Feature activation-2.59e-01

Pos logit contributions
rio+2.624
Ire+2.479
 Trave+2.219
+2.173
 Surviv+2.143
Neg logit contributions
Psych-2.369
issan-2.318
psych-2.152
Dex-2.115
 Psych-2.081
Token national
Token ID2260
Feature activation+2.79e-01

Pos logit contributions
rio+0.222
Ire+0.211
 Trave+0.190
+0.189
 Surviv+0.187
Neg logit contributions
Psych-0.158
issan-0.154
psych-0.141
Dex-0.140
 Psych-0.137
Token powers
Token ID5635
Feature activation+2.61e-01

Pos logit contributions
Psych+0.176
issan+0.171
psych+0.158
Dex+0.156
 Psych+0.154
Neg logit contributions
rio-0.233
Ire-0.221
 Trave-0.199
-0.197
 Surviv-0.196
Token to
Token ID284
Feature activation-3.07e-01

Pos logit contributions
Psych+0.166
issan+0.161
psych+0.149
Dex+0.147
 Psych+0.145
Neg logit contributions
rio-0.216
Ire-0.206
 Trave-0.185
-0.183
 Surviv-0.182
Token state
Token ID1181
Feature activation+7.14e-01

Pos logit contributions
rio+0.277
Ire+0.264
 Trave+0.240
+0.238
 Surviv+0.237
Neg logit contributions
Psych-0.172
issan-0.167
psych-0.152
Dex-0.150
 Psych-0.147
Token kinds
Token ID6982
Feature activation-1.29e-01

Pos logit contributions
Psych+0.200
issan+0.196
psych+0.185
Dex+0.183
 Psych+0.181
Neg logit contributions
rio-0.159
Ire-0.149
 Trave-0.130
-0.128
 Surviv-0.127
Token of
Token ID286
Feature activation-8.84e-02

Pos logit contributions
rio+0.105
Ire+0.099
 Trave+0.089
+0.088
 Surviv+0.088
Neg logit contributions
Psych-0.085
issan-0.082
psych-0.076
Dex-0.075
 Psych-0.074
Token stories
Token ID3923
Feature activation+2.77e-01

Pos logit contributions
rio+0.075
Ire+0.071
 Trave+0.064
+0.064
 Surviv+0.063
Neg logit contributions
Psych-0.055
issan-0.053
psych-0.049
Dex-0.048
 Psych-0.047
Token about
Token ID546
Feature activation+6.24e-02

Pos logit contributions
Psych+0.175
issan+0.171
psych+0.157
Dex+0.156
 Psych+0.153
Neg logit contributions
rio-0.230
Ire-0.218
 Trave-0.197
-0.195
 Surviv-0.194
Token pur
Token ID1308
Feature activation-6.13e-02

Pos logit contributions
Psych+0.037
issan+0.036
psych+0.033
Dex+0.032
 Psych+0.032
Neg logit contributions
rio-0.054
Ire-0.052
 Trave-0.047
-0.046
 Surviv-0.046
Tokenges
Token ID3212
Feature activation-3.37e+00

Pos logit contributions
rio+0.065
Ire+0.062
 Trave+0.058
+0.057
 Surviv+0.057
Neg logit contributions
Psych-0.025
issan-0.024
psych-0.021
Dex-0.020
 Psych-0.020
Token in
Token ID287
Feature activation+9.68e-02

Pos logit contributions
rio+2.626
Ire+2.452
 Trave+2.208
+2.181
 Surviv+2.161
Neg logit contributions
Psych-2.297
issan-2.276
Dex-2.073
psych-2.070
 Psych-2.013
Token every
Token ID790
Feature activation+2.08e-01

Pos logit contributions
Psych+0.056
issan+0.054
psych+0.050
Dex+0.049
 Psych+0.048
Neg logit contributions
rio-0.086
Ire-0.082
 Trave-0.074
-0.074
 Surviv-0.073
Token major
Token ID1688
Feature activation+3.43e-01

Pos logit contributions
Psych+0.125
issan+0.121
psych+0.112
Dex+0.110
 Psych+0.108
Neg logit contributions
rio-0.179
Ire-0.171
 Trave-0.154
-0.153
 Surviv-0.152
Token city
Token ID1748
Feature activation-1.16e-01

Pos logit contributions
Psych+0.216
issan+0.210
psych+0.194
Dex+0.192
 Psych+0.188
Neg logit contributions
rio-0.286
Ire-0.272
 Trave-0.245
-0.242
 Surviv-0.241
Token in
Token ID287
Feature activation+3.05e-02

Pos logit contributions
rio+0.097
Ire+0.093
 Trave+0.083
+0.082
 Surviv+0.082
Neg logit contributions
Psych-0.073
issan-0.071
psych-0.066
Dex-0.065
 Psych-0.064
Token Last
Token ID4586
Feature activation-4.96e-01

Pos logit contributions
rio+0.120
Ire+0.115
 Trave+0.104
+0.103
 Surviv+0.103
Neg logit contributions
Psych-0.072
issan-0.070
psych-0.064
Dex-0.063
 Psych-0.062
Token week
Token ID1285
Feature activation-2.10e-01

Pos logit contributions
rio+0.434
Ire+0.414
 Trave+0.375
+0.371
 Surviv+0.369
Neg logit contributions
Psych-0.292
issan-0.283
psych-0.260
Dex-0.257
 Psych-0.252
Token,
Token ID11
Feature activation-1.22e-01

Pos logit contributions
rio+0.163
Ire+0.154
 Trave+0.137
+0.135
 Surviv+0.135
Neg logit contributions
Psych-0.145
issan-0.141
psych-0.131
Dex-0.129
 Psych-0.128
Token he
Token ID339
Feature activation-4.40e-02

Pos logit contributions
rio+0.097
Ire+0.092
 Trave+0.082
+0.081
 Surviv+0.081
Neg logit contributions
Psych-0.082
issan-0.080
psych-0.074
Dex-0.073
 Psych-0.072
Token comm
Token ID725
Feature activation+1.29e+00

Pos logit contributions
rio+0.037
Ire+0.035
 Trave+0.031
+0.031
 Surviv+0.031
Neg logit contributions
Psych-0.028
issan-0.027
psych-0.025
Dex-0.024
 Psych-0.024
Tokenended
Token ID1631
Feature activation-2.90e+00

Pos logit contributions
Psych+1.049
issan+1.022
psych+0.969
Dex+0.952
 Psych+0.944
Neg logit contributions
rio-0.830
Ire-0.783
 Trave-0.682
-0.674
 Surviv-0.671
Token Trump
Token ID1301
Feature activation-1.14e-01

Pos logit contributions
rio+2.249
Ire+2.126
 Trave+1.936
+1.890
 Surviv+1.869
Neg logit contributions
Psych-1.954
issan-1.913
psych-1.769
Dex-1.755
 Psych-1.707
Token for
Token ID329
Feature activation-4.42e-01

Pos logit contributions
rio+0.095
Ire+0.091
 Trave+0.082
+0.081
 Surviv+0.080
Neg logit contributions
Psych-0.072
issan-0.070
psych-0.064
Dex-0.064
 Psych-0.063
Token conducting
Token ID14523
Feature activation-5.11e-02

Pos logit contributions
rio+0.359
Ire+0.340
 Trave+0.306
+0.302
 Surviv+0.301
Neg logit contributions
Psych-0.289
issan-0.281
psych-0.260
Dex-0.257
 Psych-0.253
Token military
Token ID2422
Feature activation-9.39e-02

Pos logit contributions
rio+0.043
Ire+0.041
 Trave+0.037
+0.036
 Surviv+0.036
Neg logit contributions
Psych-0.032
issan-0.031
psych-0.029
Dex-0.028
 Psych-0.028
Token strikes
Token ID8956
Feature activation+2.49e-01

Pos logit contributions
rio+0.069
Ire+0.065
 Trave+0.058
+0.057
 Surviv+0.057
Neg logit contributions
Psych-0.068
issan-0.067
psych-0.062
Dex-0.062
 Psych-0.061
Token wanted
Token ID2227
Feature activation+5.07e-02

Pos logit contributions
rio+0.288
Ire+0.275
 Trave+0.246
+0.245
 Surviv+0.242
Neg logit contributions
Psych-0.232
issan-0.226
psych-0.209
Dex-0.207
 Psych-0.204
Token to
Token ID284
Feature activation-1.37e-01

Pos logit contributions
Psych+0.031
issan+0.030
psych+0.028
Dex+0.028
 Psych+0.027
Neg logit contributions
rio-0.043
Ire-0.041
 Trave-0.037
-0.036
 Surviv-0.036
Token portray
Token ID10993
Feature activation-5.16e-01

Pos logit contributions
rio+0.111
Ire+0.106
 Trave+0.095
+0.094
 Surviv+0.093
Neg logit contributions
Psych-0.089
issan-0.086
psych-0.080
Dex-0.079
 Psych-0.078
Token the
Token ID262
Feature activation-9.62e-02

Pos logit contributions
rio+0.426
Ire+0.404
 Trave+0.364
+0.360
 Surviv+0.358
Neg logit contributions
Psych-0.330
issan-0.322
psych-0.296
Dex-0.293
 Psych-0.288
Token conv
Token ID3063
Feature activation-4.42e-01

Pos logit contributions
rio+0.080
Ire+0.076
 Trave+0.068
+0.068
 Surviv+0.067
Neg logit contributions
Psych-0.061
issan-0.059
psych-0.055
Dex-0.054
 Psych-0.053
Tokenicts
Token ID14137
Feature activation-2.82e+00

Pos logit contributions
rio+0.329
Ire+0.307
 Trave+0.274
+0.269
 Surviv+0.268
Neg logit contributions
Psych-0.319
issan-0.312
psych-0.290
Dex-0.288
 Psych-0.283
Token playing
Token ID2712
Feature activation+2.78e-01

Pos logit contributions
rio+2.251
Ire+2.112
 Trave+1.918
+1.887
 Surviv+1.872
Neg logit contributions
Psych-1.870
issan-1.830
psych-1.681
Dex-1.667
 Psych-1.631
Token baseball
Token ID9283
Feature activation-4.76e-01

Pos logit contributions
Psych+0.187
issan+0.182
psych+0.169
Dex+0.167
 Psych+0.164
Neg logit contributions
rio-0.220
Ire-0.208
 Trave-0.186
-0.184
 Surviv-0.183
Token in
Token ID287
Feature activation+2.05e-01

Pos logit contributions
rio+0.390
Ire+0.370
 Trave+0.333
+0.329
 Surviv+0.327
Neg logit contributions
Psych-0.307
issan-0.300
psych-0.276
Dex-0.273
 Psych-0.268
Token the
Token ID262
Feature activation+2.42e-02

Pos logit contributions
Psych+0.129
issan+0.125
psych+0.115
Dex+0.114
 Psych+0.112
Neg logit contributions
rio-0.171
Ire-0.162
 Trave-0.146
-0.145
 Surviv-0.144
Token yard
Token ID12699
Feature activation-9.49e-02

Pos logit contributions
Psych+0.016
issan+0.015
psych+0.014
Dex+0.014
 Psych+0.014
Neg logit contributions
rio-0.020
Ire-0.019
 Trave-0.017
-0.017
 Surviv-0.017
Token soldiers
Token ID5795
Feature activation+1.57e-02

Pos logit contributions
rio+0.159
Ire+0.152
 Trave+0.137
+0.136
 Surviv+0.135
Neg logit contributions
Psych-0.109
issan-0.107
psych-0.098
Dex-0.096
 Psych-0.095
Token that
Token ID326
Feature activation-2.33e-01

Pos logit contributions
Psych+0.009
issan+0.009
psych+0.008
Dex+0.008
 Psych+0.008
Neg logit contributions
rio-0.014
Ire-0.013
 Trave-0.012
-0.012
 Surviv-0.012
Token it
Token ID340
Feature activation-1.91e-01

Pos logit contributions
rio+0.206
Ire+0.196
 Trave+0.178
+0.176
 Surviv+0.175
Neg logit contributions
Psych-0.136
issan-0.132
psych-0.121
Dex-0.119
 Psych-0.117
Token granted
Token ID7520
Feature activation+1.29e-01

Pos logit contributions
rio+0.154
Ire+0.146
 Trave+0.131
+0.129
 Surviv+0.129
Neg logit contributions
Psych-0.127
issan-0.123
psych-0.114
Dex-0.113
 Psych-0.111
Token conv
Token ID3063
Feature activation-2.23e-01

Pos logit contributions
Psych+0.078
issan+0.075
psych+0.069
Dex+0.068
 Psych+0.067
Neg logit contributions
rio-0.112
Ire-0.107
 Trave-0.096
-0.096
 Surviv-0.095
Tokenicts
Token ID14137
Feature activation-2.78e+00

Pos logit contributions
rio+0.209
Ire+0.198
 Trave+0.181
+0.178
 Surviv+0.178
Neg logit contributions
Psych-0.118
issan-0.114
psych-0.103
Dex-0.103
 Psych-0.100
Token freedom
Token ID4925
Feature activation+5.76e-01

Pos logit contributions
rio+2.288
Ire+2.155
 Trave+1.974
 Surviv+1.913
+1.908
Neg logit contributions
Psych-1.763
issan-1.734
psych-1.571
Dex-1.558
 Psych-1.513
Token,
Token ID11
Feature activation-3.52e-02

Pos logit contributions
Psych+0.366
issan+0.357
psych+0.330
Dex+0.325
 Psych+0.320
Neg logit contributions
rio-0.478
Ire-0.455
 Trave-0.407
-0.404
 Surviv-0.403
Token if
Token ID611
Feature activation-3.42e-02

Pos logit contributions
rio+0.029
Ire+0.027
 Trave+0.025
+0.024
 Surviv+0.024
Neg logit contributions
Psych-0.023
issan-0.022
psych-0.020
Dex-0.020
 Psych-0.020
Token they
Token ID484
Feature activation+3.07e-01

Pos logit contributions
rio+0.032
Ire+0.030
 Trave+0.028
+0.027
 Surviv+0.027
Neg logit contributions
Psych-0.018
issan-0.018
psych-0.016
Dex-0.016
 Psych-0.016
Token would
Token ID561
Feature activation+3.35e-01

Pos logit contributions
Psych+0.199
issan+0.194
psych+0.179
Dex+0.177
 Psych+0.174
Neg logit contributions
rio-0.250
Ire-0.238
 Trave-0.213
-0.211
 Surviv-0.210
Token early
Token ID1903
Feature activation-4.15e-01

Pos logit contributions
Psych+0.239
issan+0.233
psych+0.215
Dex+0.214
 Psych+0.211
Neg logit contributions
rio-0.306
Ire-0.291
 Trave-0.261
-0.259
 Surviv-0.257
Token 1960
Token ID9507
Feature activation-3.21e-01

Pos logit contributions
rio+0.355
Ire+0.337
 Trave+0.305
+0.301
 Surviv+0.300
Neg logit contributions
Psych-0.253
issan-0.247
psych-0.226
Dex-0.223
 Psych-0.219
Tokens
Token ID82
Feature activation+5.60e-01

Pos logit contributions
rio+0.232
Ire+0.221
 Trave+0.193
+0.191
 Surviv+0.190
Neg logit contributions
Psych-0.238
issan-0.232
psych-0.218
Dex-0.216
 Psych-0.213
Token,
Token ID11
Feature activation+2.64e-02

Pos logit contributions
Psych+0.387
issan+0.376
psych+0.350
Dex+0.350
 Haas+0.343
Neg logit contributions
rio-0.431
Ire-0.413
 Trave-0.364
-0.361
 Surviv-0.358
Token conv
Token ID3063
Feature activation-4.23e-01

Pos logit contributions
Psych+0.017
issan+0.017
psych+0.015
Dex+0.015
 Psych+0.015
Neg logit contributions
rio-0.021
Ire-0.020
 Trave-0.018
-0.018
 Surviv-0.018
Tokenicts
Token ID14137
Feature activation-2.76e+00

Pos logit contributions
rio+0.321
Ire+0.303
 Trave+0.270
+0.266
 Surviv+0.265
Neg logit contributions
Psych-0.298
issan-0.291
psych-0.270
Dex-0.268
 Psych-0.263
Token at
Token ID379
Feature activation+3.32e-01

Pos logit contributions
rio+2.252
Ire+2.110
 Trave+1.933
+1.886
 Surviv+1.876
Neg logit contributions
Psych-1.779
issan-1.752
psych-1.601
Dex-1.579
 Psych-1.541
Token Al
Token ID978
Feature activation+9.90e-01

Pos logit contributions
Psych+0.207
issan+0.201
psych+0.185
Dex+0.183
 Psych+0.180
Neg logit contributions
rio-0.279
Ire-0.266
 Trave-0.239
-0.237
 Surviv-0.236
Tokencat
Token ID9246
Feature activation+6.18e-01

Pos logit contributions
Psych+0.458
issan+0.444
psych+0.397
Dex+0.388
 Psych+0.377
Neg logit contributions
rio-0.985
Ire-0.962
 Trave-0.879
-0.876
 Surviv-0.869
Tokenraz
Token ID3247
Feature activation-9.89e-01

Pos logit contributions
Psych+0.438
issan+0.426
psych+0.399
Dex+0.392
 Psych+0.387
Neg logit contributions
rio-0.462
Ire-0.446
 Trave-0.396
 Surviv-0.391
-0.391
Token had
Token ID550
Feature activation+2.90e-01

Pos logit contributions
rio+0.813
Ire+0.770
 Trave+0.695
+0.686
 Surviv+0.682
Neg logit contributions
Psych-0.634
issan-0.620
psych-0.570
Dex-0.564
 Psych-0.553
Token in
Token ID287
Feature activation+2.84e-01

Pos logit contributions
rio+0.198
Ire+0.188
 Trave+0.169
+0.167
 Surviv+0.166
Neg logit contributions
Psych-0.151
issan-0.147
psych-0.135
Dex-0.134
 Psych-0.132
Token Sanskrit
Token ID46178
Feature activation-2.73e-01

Pos logit contributions
Psych+0.172
issan+0.167
psych+0.153
Dex+0.151
 Psych+0.148
Neg logit contributions
rio-0.244
Ire-0.232
 Trave-0.211
-0.209
 Surviv-0.207
Token and
Token ID290
Feature activation+1.02e-01

Pos logit contributions
rio+0.224
Ire+0.213
 Trave+0.192
+0.190
 Surviv+0.188
Neg logit contributions
Psych-0.175
issan-0.171
psych-0.157
Dex-0.156
 Psych-0.152
Token his
Token ID465
Feature activation+1.79e-01

Pos logit contributions
Psych+0.065
issan+0.063
psych+0.059
Dex+0.058
 Psych+0.057
Neg logit contributions
rio-0.084
Ire-0.079
 Trave-0.071
-0.071
 Surviv-0.070
Token cons
Token ID762
Feature activation+9.64e-01

Pos logit contributions
Psych+0.113
issan+0.111
psych+0.102
Dex+0.101
 Psych+0.099
Neg logit contributions
rio-0.148
Ire-0.141
 Trave-0.127
-0.125
 Surviv-0.125
Tokenort
Token ID419
Feature activation-2.63e+00

Pos logit contributions
Psych+0.453
issan+0.443
psych+0.396
Dex+0.382
 Psych+0.373
Neg logit contributions
rio-0.953
Ire-0.921
 Trave-0.842
-0.837
 Surviv-0.834
Token Rath
Token ID26494
Feature activation-7.12e-01

Pos logit contributions
rio+2.135
Ire+2.009
 Trave+1.836
+1.808
 Surviv+1.791
Neg logit contributions
Psych-1.702
issan-1.666
psych-1.535
Dex-1.516
 Psych-1.471
Tokeni
Token ID72
Feature activation+4.12e-01

Pos logit contributions
rio+0.610
Ire+0.578
 Trave+0.524
+0.517
 Surviv+0.515
Neg logit contributions
Psych-0.433
issan-0.420
psych-0.386
Dex-0.382
 Psych-0.374
Token,
Token ID11
Feature activation+1.83e-01

Pos logit contributions
Psych+0.257
issan+0.250
psych+0.230
Dex+0.227
 Psych+0.223
Neg logit contributions
rio-0.347
Ire-0.330
 Trave-0.298
-0.294
 Surviv-0.293
Token they
Token ID484
Feature activation+6.75e-02

Pos logit contributions
Psych+0.114
issan+0.111
psych+0.102
Dex+0.101
 Psych+0.100
Neg logit contributions
rio-0.153
Ire-0.146
 Trave-0.131
-0.130
 Surviv-0.129
Token have
Token ID423
Feature activation+9.77e-02

Pos logit contributions
Psych+0.043
issan+0.042
psych+0.038
Dex+0.038
 Psych+0.037
Neg logit contributions
rio-0.056
Ire-0.054
 Trave-0.048
-0.048
 Surviv-0.047
Token
Token ID198
Feature activation+1.44e-01

Pos logit contributions
Psych+0.109
issan+0.105
psych+0.094
Dex+0.093
 Psych+0.091
Neg logit contributions
rio-0.227
Ire-0.218
 Trave-0.199
-0.198
 Surviv-0.197
TokenToday
Token ID8888
Feature activation+1.70e-01

Pos logit contributions
Psych+0.094
issan+0.091
psych+0.084
Dex+0.084
 Psych+0.082
Neg logit contributions
rio-0.117
Ire-0.111
 Trave-0.100
-0.098
 Surviv-0.098
Token w
Token ID266
Feature activation-8.61e-01

Pos logit contributions
Psych+0.110
issan+0.108
psych+0.099
Dex+0.098
 Psych+0.097
Neg logit contributions
rio-0.139
Ire-0.132
 Trave-0.118
-0.117
 Surviv-0.116
Token e
Token ID304
Feature activation-1.37e+00

Pos logit contributions
rio+0.691
Ire+0.652
 Trave+0.587
+0.578
 Surviv+0.576
Neg logit contributions
Psych-0.570
issan-0.551
psych-0.514
Dex-0.510
 Psych-0.496
Token can
Token ID460
Feature activation-4.31e-03

Pos logit contributions
rio+1.107
Ire+1.046
 Trave+0.949
+0.932
 Surviv+0.929
Neg logit contributions
Psych-0.891
issan-0.865
psych-0.802
Dex-0.795
 Psych-0.775
Token d
Token ID288
Feature activation-2.62e+00

Pos logit contributions
rio+0.004
Ire+0.003
 Trave+0.003
+0.003
 Surviv+0.003
Neg logit contributions
Psych-0.003
issan-0.003
psych-0.002
Dex-0.002
 Psych-0.002
Token raw
Token ID8246
Feature activation-4.01e-01

Pos logit contributions
rio+2.164
Ire+2.032
 Trave+1.852
+1.813
 Surviv+1.810
Neg logit contributions
Psych-1.683
issan-1.627
psych-1.517
Dex-1.500
 Haas-1.450
Token up
Token ID510
Feature activation+5.54e-01

Pos logit contributions
rio+0.324
Ire+0.307
 Trave+0.275
+0.272
 Surviv+0.271
Neg logit contributions
Psych-0.264
issan-0.258
psych-0.238
Dex-0.235
 Psych-0.231
Token the
Token ID262
Feature activation+3.28e-01

Pos logit contributions
Psych+0.355
issan+0.350
psych+0.321
Dex+0.317
 Psych+0.312
Neg logit contributions
rio-0.452
Ire-0.432
 Trave-0.387
-0.383
 Surviv-0.381
Token most
Token ID749
Feature activation+3.60e-01

Pos logit contributions
Psych+0.214
issan+0.209
psych+0.193
Dex+0.191
 Psych+0.188
Neg logit contributions
rio-0.266
Ire-0.252
 Trave-0.226
-0.224
 Surviv-0.222
Token g
Token ID308
Feature activation-8.54e-01

Pos logit contributions
Psych+0.236
issan+0.230
psych+0.213
Dex+0.211
 Psych+0.208
Neg logit contributions
rio-0.291
Ire-0.276
 Trave-0.247
-0.246
 Surviv-0.242
Token approval
Token ID7546
Feature activation+1.11e-02

Pos logit contributions
rio+0.182
Ire+0.173
 Trave+0.156
+0.155
 Surviv+0.154
Neg logit contributions
Psych-0.136
issan-0.133
psych-0.122
Dex-0.121
 Psych-0.119
Token of
Token ID286
Feature activation+9.84e-02

Pos logit contributions
Psych+0.007
issan+0.007
psych+0.007
Dex+0.007
 Psych+0.006
Neg logit contributions
rio-0.009
Ire-0.008
 Trave-0.008
-0.007
 Surviv-0.007
Token measures
Token ID5260
Feature activation+4.70e-01

Pos logit contributions
Psych+0.063
issan+0.061
psych+0.056
Dex+0.056
 Psych+0.055
Neg logit contributions
rio-0.081
Ire-0.077
 Trave-0.069
-0.069
 Surviv-0.068
Token of
Token ID286
Feature activation+1.34e-01

Pos logit contributions
Psych+0.293
issan+0.285
psych+0.262
Dex+0.259
 Psych+0.255
Neg logit contributions
rio-0.396
Ire-0.376
 Trave-0.338
-0.335
 Surviv-0.334
Token dev
Token ID1614
Feature activation+9.49e-01

Pos logit contributions
Psych+0.084
issan+0.082
psych+0.075
Dex+0.074
 Psych+0.073
Neg logit contributions
rio-0.112
Ire-0.107
 Trave-0.096
-0.096
 Surviv-0.095
Tokenolution
Token ID2122
Feature activation-2.53e+00

Pos logit contributions
Psych+0.669
issan+0.657
psych+0.610
Dex+0.600
 Psych+0.591
Neg logit contributions
rio-0.717
Ire-0.678
 Trave-0.609
-0.602
 Surviv-0.599
Token.
Token ID13
Feature activation-4.84e-02

Pos logit contributions
rio+2.040
Ire+1.917
 Trave+1.732
+1.701
 Surviv+1.685
Neg logit contributions
Psych-1.671
issan-1.635
psych-1.507
Dex-1.489
 Psych-1.460
Token
Token ID198
Feature activation+1.58e-01

Pos logit contributions
rio+0.045
Ire+0.043
 Trave+0.039
+0.039
 Surviv+0.038
Neg logit contributions
Psych-0.026
issan-0.025
psych-0.023
Dex-0.023
 Psych-0.022
Token
Token ID198
Feature activation+1.46e-01

Pos logit contributions
Psych+0.077
issan+0.074
psych+0.066
Dex+0.065
 Psych+0.064
Neg logit contributions
rio-0.154
Ire-0.148
 Trave-0.135
-0.134
 Surviv-0.133
TokenThe
Token ID464
Feature activation+1.05e-01

Pos logit contributions
Psych+0.113
issan+0.109
psych+0.103
Dex+0.102
 Psych+0.100
Neg logit contributions
rio-0.102
Ire-0.096
 Trave-0.085
 Surviv-0.084
-0.084
Token Catalan
Token ID31066
Feature activation+6.91e-01

Pos logit contributions
Psych+0.064
issan+0.062
psych+0.057
Dex+0.056
 Psych+0.055
Neg logit contributions
rio-0.090
Ire-0.085
 Trave-0.077
-0.076
 Surviv-0.076
Token Much
Token ID13111
Feature activation-3.92e-01

Pos logit contributions
Psych+0.027
issan+0.026
psych+0.024
Dex+0.024
 Psych+0.024
Neg logit contributions
rio-0.030
Ire-0.029
-0.025
 Trave-0.025
 Surviv-0.025
Token of
Token ID286
Feature activation-2.20e-01

Pos logit contributions
rio+0.341
Ire+0.325
 Trave+0.293
+0.291
 Surviv+0.290
Neg logit contributions
Psych-0.231
issan-0.226
psych-0.206
Dex-0.204
 Psych-0.200
Token the
Token ID262
Feature activation-3.79e-01

Pos logit contributions
rio+0.184
Ire+0.175
 Trave+0.156
+0.155
 Surviv+0.154
Neg logit contributions
Psych-0.138
issan-0.135
psych-0.124
Dex-0.123
 Psych-0.121
Token commentary
Token ID14604
Feature activation-2.18e-01

Pos logit contributions
rio+0.313
Ire+0.298
 Trave+0.267
+0.266
 Surviv+0.264
Neg logit contributions
Psych-0.240
issan-0.235
psych-0.216
Dex-0.213
 Psych-0.211
Token rev
Token ID2710
Feature activation-2.83e-01

Pos logit contributions
rio+0.177
Ire+0.169
 Trave+0.150
+0.149
 Surviv+0.149
Neg logit contributions
Psych-0.142
issan-0.138
psych-0.128
Dex-0.127
 Psych-0.125
Tokenolved
Token ID5634
Feature activation-2.51e+00

Pos logit contributions
rio+0.182
Ire+0.172
 Trave+0.150
 Surviv+0.149
+0.148
Neg logit contributions
Psych-0.231
issan-0.227
psych-0.213
Dex-0.210
 Psych-0.208
Token around
Token ID1088
Feature activation-9.10e-02

Pos logit contributions
rio+1.622
Ire+1.509
 Trave+1.321
+1.289
ð+1.272
Neg logit contributions
Psych-2.060
issan-2.018
psych-1.892
Dex-1.876
 Psych-1.851
Token the
Token ID262
Feature activation-2.13e-01

Pos logit contributions
rio+0.077
Ire+0.073
 Trave+0.065
+0.065
 Surviv+0.065
Neg logit contributions
Psych-0.056
issan-0.055
psych-0.051
Dex-0.050
 Psych-0.049
Token aesthetics
Token ID35431
Feature activation-5.09e-01

Pos logit contributions
rio+0.175
Ire+0.166
 Trave+0.148
+0.148
 Surviv+0.147
Neg logit contributions
Psych-0.136
issan-0.133
psych-0.122
Dex-0.121
 Psych-0.120
Token and
Token ID290
Feature activation-1.27e-01

Pos logit contributions
rio+0.402
Ire+0.382
 Trave+0.341
+0.337
 Surviv+0.335
Neg logit contributions
Psych-0.343
issan-0.335
psych-0.310
Dex-0.307
 Psych-0.302
Token design
Token ID1486
Feature activation+5.20e-01

Pos logit contributions
rio+0.105
Ire+0.100
 Trave+0.090
+0.090
 Surviv+0.088
Neg logit contributions
Psych-0.080
issan-0.078
psych-0.072
Dex-0.072
 Psych-0.071
Token.
Token ID13
Feature activation-1.28e-02

Pos logit contributions
rio+0.239
Ire+0.227
 Trave+0.203
+0.201
 Surviv+0.200
Neg logit contributions
Psych-0.194
issan-0.189
psych-0.175
Dex-0.173
 Psych-0.171
Token Most
Token ID4042
Feature activation-1.68e-01

Pos logit contributions
rio+0.011
Ire+0.010
 Trave+0.009
+0.009
 Surviv+0.009
Neg logit contributions
Psych-0.008
issan-0.008
psych-0.007
Dex-0.007
 Psych-0.007
Token tweets
Token ID12665
Feature activation-3.21e-02

Pos logit contributions
rio+0.139
Ire+0.132
 Trave+0.118
+0.117
 Surviv+0.117
Neg logit contributions
Psych-0.107
issan-0.104
psych-0.096
Dex-0.095
 Psych-0.093
Token about
Token ID546
Feature activation+5.88e-02

Pos logit contributions
rio+0.027
Ire+0.025
 Trave+0.023
+0.023
 Surviv+0.022
Neg logit contributions
Psych-0.020
issan-0.020
psych-0.018
Dex-0.018
 Psych-0.018
Token Pur
Token ID9330
Feature activation-5.42e-02

Pos logit contributions
Psych+0.034
issan+0.033
psych+0.030
Dex+0.030
 Psych+0.029
Neg logit contributions
rio-0.052
Ire-0.050
 Trave-0.045
-0.045
 Surviv-0.045
Tokenges
Token ID3212
Feature activation-2.43e+00

Pos logit contributions
rio+0.056
Ire+0.053
 Trave+0.049
+0.049
 Surviv+0.049
Neg logit contributions
Psych-0.024
issan-0.023
psych-0.020
Dex-0.020
 Psych-0.019
Token have
Token ID423
Feature activation-5.42e-02

Pos logit contributions
rio+1.964
Ire+1.856
 Trave+1.681
+1.659
 Surviv+1.653
Neg logit contributions
Psych-1.582
issan-1.556
psych-1.424
Dex-1.410
 Psych-1.372
Token the
Token ID262
Feature activation-1.93e-01

Pos logit contributions
rio+0.046
Ire+0.043
 Trave+0.039
+0.039
 Surviv+0.039
Neg logit contributions
Psych-0.034
issan-0.033
psych-0.030
Dex-0.030
 Psych-0.029
Token refrain
Token ID25133
Feature activation-2.31e-01

Pos logit contributions
rio+0.164
Ire+0.156
 Trave+0.141
+0.139
 Surviv+0.138
Neg logit contributions
Psych-0.119
issan-0.116
psych-0.107
Dex-0.105
 Psych-0.103
Token
Token ID564
Feature activation-1.22e-01

Pos logit contributions
rio+0.194
Ire+0.184
 Trave+0.166
+0.164
 Surviv+0.163
Neg logit contributions
Psych-0.144
issan-0.141
psych-0.129
Dex-0.128
 Psych-0.125
Token
Token ID250
Feature activation-1.60e-01

Pos logit contributions
rio+0.101
Ire+0.096
 Trave+0.086
+0.085
 Surviv+0.085
Neg logit contributions
Psych-0.077
issan-0.075
psych-0.069
Dex-0.069
 Psych-0.067
Token Life
Token ID5155
Feature activation-1.26e+00

Pos logit contributions
rio+0.269
Ire+0.254
 Trave+0.225
+0.224
 Surviv+0.222
Neg logit contributions
Psych-0.248
issan-0.242
psych-0.226
Dex-0.223
 Psych-0.221
Token of
Token ID286
Feature activation-2.35e-01

Pos logit contributions
rio+0.996
Ire+0.944
 Trave+0.845
+0.835
 Surviv+0.830
Neg logit contributions
Psych-0.850
issan-0.830
psych-0.769
Dex-0.760
 Psych-0.748
Token Christ
Token ID1951
Feature activation-1.36e-01

Pos logit contributions
rio+0.170
Ire+0.161
 Trave+0.141
+0.141
 Surviv+0.139
Neg logit contributions
Psych-0.175
issan-0.171
psych-0.159
Dex-0.158
 Psych-0.157
Token.
Token ID13
Feature activation-2.33e-01

Pos logit contributions
rio+0.117
Ire+0.112
 Trave+0.100
+0.100
 Surviv+0.099
Neg logit contributions
Psych-0.083
issan-0.080
psych-0.074
Dex-0.073
 Psych-0.072
Token Sac
Token ID9295
Feature activation-4.08e-01

Pos logit contributions
rio+0.175
Ire+0.165
 Trave+0.146
+0.145
 Surviv+0.143
Neg logit contributions
Psych-0.166
issan-0.162
psych-0.151
Dex-0.150
 Psych-0.148
Tokenram
Token ID859
Feature activation-2.39e+00

Pos logit contributions
rio+0.235
Ire+0.220
 Trave+0.188
+0.185
 Surviv+0.183
Neg logit contributions
Psych-0.362
issan-0.355
psych-0.336
Dex-0.333
 Psych-0.328
Tokenents
Token ID658
Feature activation-1.09e+00

Pos logit contributions
rio+2.497
Ire+2.384
 Trave+2.204
+2.176
 Surviv+2.174
Neg logit contributions
Psych-0.991
issan-0.963
psych-0.832
Dex-0.827
 Haas-0.797
Token.
Token ID13
Feature activation-1.80e-01

Pos logit contributions
rio+0.894
Ire+0.846
 Trave+0.765
+0.754
 Surviv+0.750
Neg logit contributions
Psych-0.695
issan-0.680
psych-0.624
Dex-0.618
 Psych-0.605
Token Bapt
Token ID18226
Feature activation-8.20e-01

Pos logit contributions
rio+0.143
Ire+0.135
 Trave+0.120
+0.120
 Surviv+0.118
Neg logit contributions
Psych-0.121
issan-0.118
psych-0.109
Dex-0.109
 Psych-0.107
Tokenism
Token ID1042
Feature activation-1.20e-01

Pos logit contributions
rio+0.585
Ire+0.554
 Trave+0.491
+0.487
 Surviv+0.482
Neg logit contributions
Psych-0.613
issan-0.603
psych-0.562
Dex-0.555
 Psych-0.547
Token.
Token ID13
Feature activation-1.57e-01

Pos logit contributions
rio+0.102
Ire+0.097
 Trave+0.087
+0.086
 Surviv+0.086
Neg logit contributions
Psych-0.075
issan-0.073
psych-0.067
Dex-0.066
 Psych-0.065
Token Patton
Token ID40929
Feature activation-8.48e-01

Pos logit contributions
rio+0.096
Ire+0.090
 Trave+0.081
+0.080
 Surviv+0.080
Neg logit contributions
Psych-0.080
issan-0.078
psych-0.072
Dex-0.071
 Psych-0.070
Token.
Token ID13
Feature activation-1.99e-01

Pos logit contributions
rio+0.674
Ire+0.639
 Trave+0.572
+0.566
 Surviv+0.562
Neg logit contributions
Psych-0.569
issan-0.555
psych-0.514
Dex-0.508
 Psych-0.500
Token He
Token ID679
Feature activation-1.13e-02

Pos logit contributions
rio+0.175
Ire+0.166
 Trave+0.150
+0.149
 Surviv+0.148
Neg logit contributions
Psych-0.117
issan-0.113
psych-0.104
Dex-0.103
 Psych-0.102
Token's
Token ID338
Feature activation+1.46e-01

Pos logit contributions
rio+0.009
Ire+0.008
 Trave+0.007
+0.007
 Surviv+0.007
Neg logit contributions
Psych-0.008
issan-0.008
psych-0.007
Dex-0.007
 Psych-0.007
Token br
Token ID865
Feature activation-8.50e-01

Pos logit contributions
Psych+0.095
issan+0.092
psych+0.086
Dex+0.084
 Psych+0.084
Neg logit contributions
rio-0.119
Ire-0.114
 Trave-0.102
-0.101
 Surviv-0.100
Tokenash
Token ID1077
Feature activation-2.38e+00

Pos logit contributions
rio+0.645
Ire+0.606
 Trave+0.540
+0.532
 Surviv+0.531
Neg logit contributions
Psych-0.600
issan-0.584
psych-0.543
Dex-0.541
 Psych-0.530
Token and
Token ID290
Feature activation+3.96e-02

Pos logit contributions
rio+1.771
Ire+1.656
 Trave+1.483
+1.457
 Surviv+1.451
Neg logit contributions
Psych-1.716
issan-1.680
psych-1.555
Dex-1.548
 Psych-1.515
Token opinion
Token ID4459
Feature activation-5.00e-01

Pos logit contributions
Psych+0.025
issan+0.025
psych+0.023
Dex+0.023
 Psych+0.022
Neg logit contributions
rio-0.032
Ire-0.031
 Trave-0.028
-0.027
 Surviv-0.027
Tokenated
Token ID515
Feature activation+7.98e-02

Pos logit contributions
rio+0.432
Ire+0.411
 Trave+0.372
+0.368
 Surviv+0.366
Neg logit contributions
Psych-0.300
issan-0.292
psych-0.268
Dex-0.264
 Psych-0.259
Token,
Token ID11
Feature activation+1.59e-02

Pos logit contributions
Psych+0.054
issan+0.053
psych+0.049
Dex+0.048
 Psych+0.048
Neg logit contributions
rio-0.063
Ire-0.060
 Trave-0.053
-0.053
 Surviv-0.052
Token and
Token ID290
Feature activation+1.62e-01

Pos logit contributions
Psych+0.010
issan+0.010
psych+0.009
Dex+0.009
 Psych+0.009
Neg logit contributions
rio-0.013
Ire-0.013
 Trave-0.011
-0.011
 Surviv-0.011
Token in
Token ID287
Feature activation-2.98e-01

Pos logit contributions
rio+1.067
Ire+1.009
 Trave+0.913
+0.901
 Surviv+0.901
Neg logit contributions
Psych-0.832
issan-0.809
psych-0.748
Dex-0.738
 Psych-0.722
Token this
Token ID428
Feature activation-4.33e-01

Pos logit contributions
rio+0.249
Ire+0.237
 Trave+0.213
+0.211
 Surviv+0.210
Neg logit contributions
Psych-0.187
issan-0.183
psych-0.168
Dex-0.166
 Psych-0.163
Token market
Token ID1910
Feature activation-5.49e-01

Pos logit contributions
rio+0.336
Ire+0.318
 Trave+0.283
+0.280
 Surviv+0.279
Neg logit contributions
Psych-0.299
issan-0.292
psych-0.271
Dex-0.268
 Psych-0.264
Token are
Token ID389
Feature activation-1.72e-01

Pos logit contributions
rio+0.459
Ire+0.436
 Trave+0.393
+0.389
 Surviv+0.386
Neg logit contributions
Psych-0.345
issan-0.337
psych-0.310
Dex-0.306
 Psych-0.300
Token reg
Token ID842
Feature activation+5.20e-01

Pos logit contributions
rio+0.136
Ire+0.129
 Trave+0.116
+0.114
 Surviv+0.114
Neg logit contributions
Psych-0.115
issan-0.112
psych-0.104
Dex-0.103
 Psych-0.101
Tokenaining
Token ID1397
Feature activation-2.37e+00

Pos logit contributions
Psych+0.251
issan+0.243
psych+0.218
Dex+0.214
 Psych+0.209
Neg logit contributions
rio-0.510
Ire-0.488
 Trave-0.448
-0.443
 Surviv-0.441
Token profitability
Token ID37129
Feature activation-5.83e-01

Pos logit contributions
rio+1.929
Ire+1.831
 Trave+1.656
 Surviv+1.630
+1.626
Neg logit contributions
Psych-1.541
issan-1.498
psych-1.385
Dex-1.366
 Psych-1.337
Token,
Token ID11
Feature activation-6.42e-02

Pos logit contributions
rio+0.475
Ire+0.450
 Trave+0.405
+0.400
 Surviv+0.398
Neg logit contributions
Psych-0.379
issan-0.370
psych-0.341
Dex-0.338
 Psych-0.331
Token
Token ID447
Feature activation+1.21e-01

Pos logit contributions
rio+0.053
Ire+0.050
 Trave+0.045
+0.045
 Surviv+0.044
Neg logit contributions
Psych-0.041
issan-0.040
psych-0.037
Dex-0.037
 Psych-0.036
Token
Token ID251
Feature activation-2.48e-01

Pos logit contributions
Psych+0.081
issan+0.079
psych+0.073
Dex+0.072
 Psych+0.071
Neg logit contributions
rio-0.096
Ire-0.091
 Trave-0.081
-0.080
 Surviv-0.079
Token the
Token ID262
Feature activation-3.12e-01

Pos logit contributions
rio+0.207
Ire+0.197
 Trave+0.177
+0.176
 Surviv+0.174
Neg logit contributions
Psych-0.156
issan-0.152
psych-0.140
Dex-0.138
 Psych-0.136
Token-
Token ID12
Feature activation-2.05e-01

Pos logit contributions
rio+0.407
Ire+0.388
 Trave+0.347
+0.342
 Surviv+0.341
Neg logit contributions
Psych-0.334
issan-0.325
psych-0.302
Dex-0.299
 Psych-0.294
Tokenbit
Token ID2545
Feature activation-5.16e-03

Pos logit contributions
rio+0.183
Ire+0.175
 Trave+0.159
 Surviv+0.157
+0.157
Neg logit contributions
Psych-0.117
issan-0.112
psych-0.105
Dex-0.103
 Psych-0.100
Token Hy
Token ID6707
Feature activation+7.25e-01

Pos logit contributions
rio+0.004
Ire+0.004
 Trave+0.004
+0.004
 Surviv+0.004
Neg logit contributions
Psych-0.003
issan-0.003
psych-0.003
Dex-0.003
 Psych-0.003
Tokenrule
Token ID25135
Feature activation+1.09e+00

Pos logit contributions
Psych+0.497
issan+0.484
psych+0.449
Dex+0.444
 Psych+0.438
Neg logit contributions
rio-0.564
Ire-0.538
 Trave-0.479
-0.476
 Surviv-0.473
Token Fi
Token ID23238
Feature activation+1.10e+00

Pos logit contributions
Psych+0.741
issan+0.721
psych+0.670
Dex+0.667
 Psych+0.656
Neg logit contributions
rio-0.849
Ire-0.808
 Trave-0.717
-0.713
 Surviv-0.710
Tokenend
Token ID437
Feature activation-2.36e+00

Pos logit contributions
Psych+0.760
issan+0.743
psych+0.686
Dex+0.684
 Psych+0.669
Neg logit contributions
rio-0.850
Ire-0.807
 Trave-0.717
-0.711
 Surviv-0.707
Token,
Token ID11
Feature activation-2.74e-01

Pos logit contributions
rio+1.809
Ire+1.699
 Trave+1.524
+1.495
 Surviv+1.489
Neg logit contributions
Psych-1.649
issan-1.617
psych-1.496
Dex-1.473
 Psych-1.449
Token O
Token ID440
Feature activation-6.70e-01

Pos logit contributions
rio+0.224
Ire+0.212
 Trave+0.190
+0.188
 Surviv+0.187
Neg logit contributions
Psych-0.177
issan-0.172
psych-0.159
Dex-0.157
 Psych-0.156
Tokencar
Token ID7718
Feature activation-6.06e-01

Pos logit contributions
rio+0.593
Ire+0.569
 Trave+0.516
+0.512
 Surviv+0.510
Neg logit contributions
Psych-0.386
issan-0.376
psych-0.343
Dex-0.338
 Psych-0.330
Tokenina
Token ID1437
Feature activation-5.79e-01

Pos logit contributions
rio+0.453
Ire+0.428
 Trave+0.381
+0.376
 Surviv+0.374
Neg logit contributions
Psych-0.435
issan-0.425
psych-0.396
Dex-0.391
 Psych-0.385
Token
Token ID447
Feature activation+2.07e-01

Pos logit contributions
rio+0.463
Ire+0.438
 Trave+0.393
+0.388
 Surviv+0.386
Neg logit contributions
Psych-0.386
issan-0.376
psych-0.348
Dex-0.344
 Psych-0.339
Tokenя
Token ID40623
Feature activation+4.92e-01

Pos logit contributions
Psych+0.011
issan+0.010
psych+0.009
Dex+0.009
 Psych+0.009
Neg logit contributions
rio-0.016
Ire-0.016
 Trave-0.014
-0.014
 Surviv-0.014
Tokenе
Token ID16843
Feature activation-1.35e-01

Pos logit contributions
Psych+0.266
issan+0.258
psych+0.234
Dex+0.231
 Psych+0.226
Neg logit contributions
rio-0.454
Ire-0.434
 Trave-0.395
-0.391
 Surviv-0.389
Tokenт
Token ID20375
Feature activation+1.88e-01

Pos logit contributions
rio+0.114
Ire+0.108
 Trave+0.098
+0.097
 Surviv+0.096
Neg logit contributions
Psych-0.084
issan-0.082
psych-0.075
Dex-0.075
 Psych-0.073
Tokenс
Token ID21727
Feature activation+1.01e-02

Pos logit contributions
Psych+0.111
issan+0.107
psych+0.098
Dex+0.097
 Psych+0.095
Neg logit contributions
rio-0.165
Ire-0.157
 Trave-0.143
-0.141
 Surviv-0.140
Tokenя
Token ID40623
Feature activation+4.18e-01

Pos logit contributions
Psych+0.006
issan+0.006
psych+0.005
Dex+0.005
 Psych+0.005
Neg logit contributions
rio-0.009
Ire-0.008
 Trave-0.008
-0.008
 Surviv-0.007
Token «
Token ID21110
Feature activation-2.31e+00

Pos logit contributions
Psych+0.229
issan+0.221
psych+0.202
Dex+0.199
 Psych+0.196
Neg logit contributions
rio-0.383
Ire-0.366
 Trave-0.332
-0.329
 Surviv-0.328
Tokenв
Token ID38857
Feature activation-1.09e-02

Pos logit contributions
rio+1.908
Ire+1.809
 Trave+1.627
+1.624
 Surviv+1.594
Neg logit contributions
Psych-1.451
issan-1.435
psych-1.303
Dex-1.295
 Psych-1.272
Tokenа
Token ID16142
Feature activation+5.03e-01

Pos logit contributions
rio+0.010
Ire+0.009
 Trave+0.008
+0.008
 Surviv+0.008
Neg logit contributions
Psych-0.006
issan-0.006
psych-0.006
Dex-0.005
 Psych-0.005
Token
Token ID140
Feature activation-4.00e-01

Pos logit contributions
Psych+0.297
issan+0.286
psych+0.264
Dex+0.260
 Psych+0.256
Neg logit contributions
rio-0.440
Ire-0.419
 Trave-0.379
-0.375
 Surviv-0.374
Token
Token ID111
Feature activation-4.04e-01

Pos logit contributions
rio+0.381
Ire+0.365
 Trave+0.333
+0.330
 Surviv+0.328
Neg logit contributions
Psych-0.205
issan-0.197
psych-0.179
Dex-0.176
 Psych-0.172
Tokenн
Token ID22177
Feature activation+1.18e-01

Pos logit contributions
rio+0.345
Ire+0.329
 Trave+0.297
+0.293
 Surviv+0.292
Neg logit contributions
Psych-0.247
issan-0.240
psych-0.221
Dex-0.218
 Psych-0.214
Token by
Token ID416
Feature activation-1.92e-01

Pos logit contributions
rio+0.086
Ire+0.082
 Trave+0.073
+0.072
 Surviv+0.072
Neg logit contributions
Psych-0.071
issan-0.069
psych-0.064
Dex-0.063
 Psych-0.062
Token Facebook
Token ID3203
Feature activation-2.11e-01

Pos logit contributions
rio+0.163
Ire+0.155
 Trave+0.140
+0.138
 Surviv+0.138
Neg logit contributions
Psych-0.118
issan-0.116
psych-0.106
Dex-0.105
 Psych-0.102
Token employees
Token ID4409
Feature activation-8.16e-01

Pos logit contributions
rio+0.165
Ire+0.156
 Trave+0.139
+0.138
 Surviv+0.137
Neg logit contributions
Psych-0.145
issan-0.141
psych-0.131
Dex-0.130
 Psych-0.128
Token in
Token ID287
Feature activation-2.81e-01

Pos logit contributions
rio+0.631
Ire+0.594
 Trave+0.534
+0.526
 Surviv+0.521
Neg logit contributions
Psych-0.563
issan-0.552
psych-0.509
Dex-0.507
 Psych-0.495
Token Palo
Token ID44878
Feature activation-1.33e+00

Pos logit contributions
rio+0.235
Ire+0.223
 Trave+0.202
+0.199
 Surviv+0.198
Neg logit contributions
Psych-0.177
issan-0.173
psych-0.158
Dex-0.156
 Psych-0.153
Token Alto
Token ID34317
Feature activation-2.30e+00

Pos logit contributions
rio+1.180
Ire+1.118
 Trave+1.018
+1.005
 Surviv+0.998
Neg logit contributions
Psych-0.764
issan-0.745
psych-0.676
Dex-0.671
 Psych-0.653
Token,
Token ID11
Feature activation-3.88e-01

Pos logit contributions
rio+1.662
Ire+1.549
 Trave+1.392
+1.367
 Surviv+1.341
Neg logit contributions
Psych-1.677
issan-1.660
Dex-1.537
psych-1.530
 Haas-1.487
Token Calif
Token ID3192
Feature activation-1.08e+00

Pos logit contributions
rio+0.310
Ire+0.293
 Trave+0.264
+0.260
 Surviv+0.258
Neg logit contributions
Psych-0.258
issan-0.253
psych-0.233
Dex-0.231
 Psych-0.226
Token.,
Token ID1539
Feature activation-5.36e-02

Pos logit contributions
rio+0.779
Ire+0.729
 Trave+0.647
+0.638
 Surviv+0.632
Neg logit contributions
Psych-0.807
issan-0.788
psych-0.735
Dex-0.733
 Psych-0.719
Token and
Token ID290
Feature activation-2.31e-01

Pos logit contributions
rio+0.042
Ire+0.039
 Trave+0.035
+0.035
 Surviv+0.035
Neg logit contributions
Psych-0.037
issan-0.036
psych-0.033
Dex-0.033
 Psych-0.032
Token in
Token ID287
Feature activation-2.50e-01

Pos logit contributions
rio+0.190
Ire+0.180
 Trave+0.163
+0.160
 Surviv+0.159
Neg logit contributions
Psych-0.147
issan-0.144
psych-0.133
Dex-0.132
 Psych-0.128
Token serves
Token ID9179
Feature activation+2.32e-01

Pos logit contributions
rio+0.137
Ire+0.130
 Trave+0.115
+0.114
 Surviv+0.114
Neg logit contributions
Psych-0.122
issan-0.119
psych-0.110
Dex-0.109
 Psych-0.108
Token powerful
Token ID3665
Feature activation-4.47e-01

Pos logit contributions
Psych+0.149
issan+0.146
psych+0.134
Dex+0.133
 Psych+0.131
Neg logit contributions
rio-0.190
Ire-0.181
 Trave-0.162
-0.161
 Surviv-0.160
Token corporate
Token ID6355
Feature activation+1.36e-01

Pos logit contributions
rio+0.356
Ire+0.338
 Trave+0.302
+0.299
 Surviv+0.297
Neg logit contributions
Psych-0.298
issan-0.291
psych-0.269
Dex-0.266
 Psych-0.263
Token interests
Token ID5353
Feature activation-2.72e-01

Pos logit contributions
Psych+0.091
issan+0.089
psych+0.082
Dex+0.081
 Psych+0.080
Neg logit contributions
rio-0.107
Ire-0.102
 Trave-0.091
-0.090
 Surviv-0.090
Token unab
Token ID40986
Feature activation-1.19e+00

Pos logit contributions
rio+0.214
Ire+0.203
 Trave+0.181
+0.179
 Surviv+0.178
Neg logit contributions
Psych-0.185
issan-0.180
psych-0.167
Dex-0.165
 Psych-0.163
Tokenashed
Token ID5263
Feature activation-2.30e+00

Pos logit contributions
rio+1.134
Ire+1.072
 Trave+0.986
+0.975
 Surviv+0.970
Neg logit contributions
Psych-0.616
issan-0.601
psych-0.536
Dex-0.532
 Psych-0.519
Tokenly
Token ID306
Feature activation+3.65e-02

Pos logit contributions
rio+1.555
Ire+1.452
 Trave+1.277
+1.262
 Surviv+1.247
Neg logit contributions
Psych-1.804
issan-1.768
psych-1.652
Dex-1.642
 Psych-1.613
Token,
Token ID11
Feature activation-1.17e-01

Pos logit contributions
Psych+0.025
issan+0.025
psych+0.023
Dex+0.023
 Psych+0.023
Neg logit contributions
rio-0.028
Ire-0.026
 Trave-0.024
-0.023
 Surviv-0.023
Token and
Token ID290
Feature activation-5.54e-02

Pos logit contributions
rio+0.093
Ire+0.088
 Trave+0.079
+0.078
 Surviv+0.078
Neg logit contributions
Psych-0.079
issan-0.077
psych-0.071
Dex-0.070
 Psych-0.069
Token another
Token ID1194
Feature activation-4.25e-01

Pos logit contributions
rio+0.047
Ire+0.045
 Trave+0.041
+0.040
 Surviv+0.040
Neg logit contributions
Psych-0.034
issan-0.033
psych-0.030
Dex-0.030
 Psych-0.029
Token party
Token ID2151
Feature activation+6.17e-01

Pos logit contributions
rio+0.377
Ire+0.359
 Trave+0.326
+0.323
 Surviv+0.321
Neg logit contributions
Psych-0.246
issan-0.239
psych-0.218
Dex-0.216
 Psych-0.211
Token All
Token ID1439
Feature activation+8.52e-02

Pos logit contributions
Psych+0.028
issan+0.027
psych+0.025
Dex+0.024
 Psych+0.024
Neg logit contributions
rio-0.051
Ire-0.048
 Trave-0.044
-0.044
 Surviv-0.044
Token salary
Token ID9588
Feature activation+3.06e-01

Pos logit contributions
Psych+0.053
issan+0.052
psych+0.048
Dex+0.047
 Psych+0.047
Neg logit contributions
rio-0.071
Ire-0.068
 Trave-0.061
-0.060
 Surviv-0.060
Token-
Token ID12
Feature activation-4.05e-02

Pos logit contributions
Psych+0.200
issan+0.194
psych+0.181
Dex+0.180
 Psych+0.176
Neg logit contributions
rio-0.248
Ire-0.235
 Trave-0.210
-0.208
 Surviv-0.206
Tokencap
Token ID11128
Feature activation+7.42e-01

Pos logit contributions
rio+0.029
Ire+0.027
 Trave+0.024
+0.024
 Surviv+0.023
Neg logit contributions
Psych-0.031
issan-0.030
psych-0.028
Dex-0.028
 Psych-0.027
Token figures
Token ID5538
Feature activation+2.15e-01

Pos logit contributions
Psych+0.521
issan+0.507
psych+0.475
Dex+0.470
 Psych+0.464
Neg logit contributions
rio-0.565
Ire-0.534
 Trave-0.476
-0.469
 Surviv-0.469
Token courtesy
Token ID12537
Feature activation+1.40e+00

Pos logit contributions
Psych+0.132
issan+0.128
psych+0.118
Dex+0.117
 Psych+0.116
Neg logit contributions
rio-0.182
Ire-0.175
 Trave-0.157
-0.155
 Surviv-0.154
Token of
Token ID286
Feature activation-7.67e-02

Pos logit contributions
Psych+0.912
issan+0.887
psych+0.822
Dex+0.816
 Psych+0.800
Neg logit contributions
rio-1.136
Ire-1.076
 Trave-0.966
-0.957
 Surviv-0.951
Token Over
Token ID3827
Feature activation-2.80e-01

Pos logit contributions
rio+0.056
Ire+0.052
 Trave+0.046
+0.046
 Surviv+0.046
Neg logit contributions
Psych-0.057
issan-0.055
psych-0.052
Dex-0.051
 Psych-0.050
TokenThe
Token ID464
Feature activation+2.29e-01

Pos logit contributions
rio+0.226
Ire+0.214
 Trave+0.192
+0.190
 Surviv+0.188
Neg logit contributions
Psych-0.182
issan-0.180
psych-0.164
Dex-0.162
 Haas-0.160
TokenCap
Token ID15610
Feature activation+1.03e+00

Pos logit contributions
Psych+0.149
issan+0.143
psych+0.133
Dex+0.132
 Psych+0.129
Neg logit contributions
rio-0.188
Ire-0.178
 Trave-0.161
-0.159
 Surviv-0.159
Token.
Token ID13
Feature activation-1.28e-01

Pos logit contributions
Psych+0.647
issan+0.624
psych+0.577
Dex+0.574
 Psych+0.558
Neg logit contributions
rio-0.870
Ire-0.827
 Trave-0.750
-0.740
 Surviv-0.737
Token some
Token ID617
Feature activation-4.05e-02

Pos logit contributions
Psych+0.000
issan+0.000
psych+0.000
Dex+0.000
 Psych+0.000
Neg logit contributions
rio-0.000
Ire-0.000
 Trave-0.000
-0.000
 Surviv-0.000
Token extent
Token ID6287
Feature activation+4.41e-01

Pos logit contributions
rio+0.036
Ire+0.034
 Trave+0.031
+0.031
 Surviv+0.031
Neg logit contributions
Psych-0.023
issan-0.023
psych-0.021
Dex-0.020
 Psych-0.020
Token between
Token ID1022
Feature activation+2.14e-01

Pos logit contributions
Psych+0.289
issan+0.281
psych+0.261
Dex+0.257
 Psych+0.254
Neg logit contributions
rio-0.356
Ire-0.339
 Trave-0.302
-0.300
 Surviv-0.299
Token wet
Token ID9583
Feature activation+7.28e-01

Pos logit contributions
Psych+0.142
issan+0.138
psych+0.128
Dex+0.127
 Psych+0.125
Neg logit contributions
rio-0.172
Ire-0.163
 Trave-0.145
-0.144
 Surviv-0.143
Token and
Token ID290
Feature activation-1.24e-01

Pos logit contributions
Psych+0.512
issan+0.501
psych+0.465
Dex+0.459
 Psych+0.453
Neg logit contributions
rio-0.555
Ire-0.525
 Trave-0.466
-0.462
 Surviv-0.458
Token dry
Token ID5894
Feature activation+1.60e+00

Pos logit contributions
rio+0.112
Ire+0.107
 Trave+0.097
+0.096
 Surviv+0.096
Neg logit contributions
Psych-0.069
issan-0.067
psych-0.061
Dex-0.061
 Psych-0.059
Token seasons
Token ID7028
Feature activation-1.53e-01

Pos logit contributions
Psych+1.030
issan+1.007
psych+0.928
Dex+0.915
 Psych+0.907
Neg logit contributions
rio-1.313
Ire-1.249
 Trave-1.116
-1.106
 Surviv-1.098
Token and
Token ID290
Feature activation-5.17e-02

Pos logit contributions
rio+0.121
Ire+0.114
 Trave+0.102
+0.101
 Surviv+0.100
Neg logit contributions
Psych-0.103
issan-0.100
psych-0.093
Dex-0.092
 Psych-0.090
Token the
Token ID262
Feature activation-1.50e-01

Pos logit contributions
rio+0.042
Ire+0.040
 Trave+0.036
+0.035
 Surviv+0.035
Neg logit contributions
Psych-0.034
issan-0.033
psych-0.030
Dex-0.030
 Psych-0.030
Token situation
Token ID3074
Feature activation+2.08e-01

Pos logit contributions
rio+0.124
Ire+0.118
 Trave+0.106
+0.105
 Surviv+0.104
Neg logit contributions
Psych-0.095
issan-0.093
psych-0.086
Dex-0.085
 Psych-0.083
Token has
Token ID468
Feature activation-4.81e-02

Pos logit contributions
Psych+0.136
issan+0.133
psych+0.123
Dex+0.122
 Psych+0.119
Neg logit contributions
rio-0.168
Ire-0.160
 Trave-0.143
-0.142
 Surviv-0.141
Tokenev
Token ID1990
Feature activation+1.46e-01

Pos logit contributions
rio+0.387
Ire+0.372
 Trave+0.333
+0.332
 Surviv+0.328
Neg logit contributions
Psych-0.290
issan-0.284
psych-0.262
Dex-0.257
 Psych-0.254
Tokenic
Token ID291
Feature activation-1.85e-01

Pos logit contributions
Psych+0.104
issan+0.102
psych+0.095
Dex+0.094
 Psych+0.093
Neg logit contributions
rio-0.109
Ire-0.103
 Trave-0.092
-0.091
 Surviv-0.090
Token"
Token ID1
Feature activation+2.03e-01

Pos logit contributions
rio+0.149
Ire+0.142
 Trave+0.127
+0.126
 Surviv+0.125
Neg logit contributions
Psych-0.122
issan-0.119
psych-0.110
Dex-0.109
 Psych-0.107
Token (
Token ID357
Feature activation+1.12e-01

Pos logit contributions
Psych+0.128
issan+0.125
psych+0.115
Dex+0.114
 Psych+0.112
Neg logit contributions
rio-0.168
Ire-0.161
 Trave-0.144
-0.142
 Surviv-0.142
Tokenm
Token ID76
Feature activation-3.51e-02

Pos logit contributions
Psych+0.077
issan+0.075
psych+0.070
Dex+0.069
 Psych+0.068
Neg logit contributions
rio-0.087
Ire-0.083
 Trave-0.074
-0.073
 Surviv-0.073
Tokenatt
Token ID1078
Feature activation+1.58e+00

Pos logit contributions
rio+0.028
Ire+0.027
 Trave+0.024
+0.024
 Surviv+0.024
Neg logit contributions
Psych-0.023
issan-0.023
psych-0.021
Dex-0.021
 Psych-0.020
Token-
Token ID12
Feature activation+1.29e-01

Pos logit contributions
Psych+1.044
issan+1.031
psych+0.949
Dex+0.924
 Psych+0.912
Neg logit contributions
rio-1.242
Ire-1.199
 Trave-1.082
 Surviv-1.070
-1.062
TokenEE
Token ID6500
Feature activation-7.63e-01

Pos logit contributions
Psych+0.088
issan+0.086
psych+0.079
Dex+0.078
 Psych+0.077
Neg logit contributions
rio-0.101
Ire-0.096
 Trave-0.087
-0.086
 Surviv-0.085
Token-
Token ID12
Feature activation+1.21e-01

Pos logit contributions
rio+0.608
Ire+0.578
 Trave+0.517
+0.511
 Surviv+0.510
Neg logit contributions
Psych-0.510
issan-0.495
psych-0.459
Dex-0.455
 Psych-0.447
Tokenoh
Token ID1219
Feature activation-8.39e-01

Pos logit contributions
Psych+0.077
issan+0.075
psych+0.069
Dex+0.069
 Psych+0.067
Neg logit contributions
rio-0.099
Ire-0.094
 Trave-0.085
-0.084
 Surviv-0.084
Token-
Token ID12
Feature activation+1.39e-01

Pos logit contributions
rio+0.661
Ire+0.626
 Trave+0.561
+0.554
 Surviv+0.551
Neg logit contributions
Psych-0.567
issan-0.553
psych-0.513
Dex-0.507
 Psych-0.499
Token but
Token ID475
Feature activation-6.53e-02

Pos logit contributions
rio+0.008
Ire+0.007
 Trave+0.007
+0.007
 Surviv+0.007
Neg logit contributions
Psych-0.006
issan-0.006
psych-0.005
Dex-0.005
 Psych-0.005
Token ultimately
Token ID6165
Feature activation-1.89e-01

Pos logit contributions
rio+0.054
Ire+0.051
 Trave+0.046
+0.045
 Surviv+0.045
Neg logit contributions
Psych-0.042
issan-0.041
psych-0.038
Dex-0.037
 Psych-0.037
Token authorized
Token ID10435
Feature activation-1.32e-01

Pos logit contributions
rio+0.151
Ire+0.144
 Trave+0.128
+0.127
 Surviv+0.126
Neg logit contributions
Psych-0.126
issan-0.123
psych-0.113
Dex-0.112
 Psych-0.111
Token the
Token ID262
Feature activation-2.71e-01

Pos logit contributions
rio+0.105
Ire+0.100
 Trave+0.089
+0.088
 Surviv+0.088
Neg logit contributions
Psych-0.088
issan-0.086
psych-0.079
Dex-0.079
 Psych-0.078
Token Smithsonian
Token ID40131
Feature activation+1.09e+00

Pos logit contributions
rio+0.223
Ire+0.212
 Trave+0.190
+0.188
 Surviv+0.187
Neg logit contributions
Psych-0.174
issan-0.169
psych-0.156
Dex-0.155
 Psych-0.153
Token Museum
Token ID9594
Feature activation+1.35e+00

Pos logit contributions
Psych+0.696
issan+0.673
psych+0.620
Dex+0.617
 Psych+0.612
Neg logit contributions
rio-0.891
Ire-0.857
 Trave-0.759
-0.753
 Surviv-0.752
Token of
Token ID286
Feature activation+9.16e-02

Pos logit contributions
Psych+0.853
issan+0.822
psych+0.760
Dex+0.756
 Psych+0.751
Neg logit contributions
rio-1.104
Ire-1.067
 Trave-0.950
-0.941
 Surviv-0.935
Token African
Token ID5510
Feature activation+7.44e-02

Pos logit contributions
Psych+0.062
issan+0.061
psych+0.056
Dex+0.055
 Psych+0.054
Neg logit contributions
rio-0.072
Ire-0.068
 Trave-0.062
 Surviv-0.060
-0.060
Token American
Token ID1605
Feature activation-1.86e-01

Pos logit contributions
Psych+0.051
issan+0.050
psych+0.046
Dex+0.045
 Psych+0.044
Neg logit contributions
rio-0.058
Ire-0.055
 Trave-0.049
 Surviv-0.048
-0.048
Token History
Token ID7443
Feature activation-1.08e+00

Pos logit contributions
rio+0.132
Ire+0.124
 Trave+0.109
+0.108
 Surviv+0.107
Neg logit contributions
Psych-0.141
issan-0.137
psych-0.129
Dex-0.127
 Psych-0.126
Token and
Token ID290
Feature activation-8.62e-02

Pos logit contributions
rio+0.843
Ire+0.795
 Trave+0.712
+0.703
 Surviv+0.699
Neg logit contributions
Psych-0.744
issan-0.728
psych-0.674
Dex-0.667
 Psych-0.654
Token sure
Token ID1654
Feature activation-3.24e-01

Pos logit contributions
rio+0.162
Ire+0.154
 Trave+0.138
+0.137
 Surviv+0.136
Neg logit contributions
Psych-0.136
issan-0.132
psych-0.123
Dex-0.122
 Psych-0.120
Token to
Token ID284
Feature activation+1.19e-01

Pos logit contributions
rio+0.282
Ire+0.269
 Trave+0.243
+0.241
 Surviv+0.240
Neg logit contributions
Psych-0.192
issan-0.186
psych-0.171
Dex-0.169
 Psych-0.166
Token connect
Token ID2018
Feature activation+6.64e-01

Pos logit contributions
Psych+0.076
issan+0.074
psych+0.068
Dex+0.068
 Psych+0.067
Neg logit contributions
rio-0.097
Ire-0.093
-0.083
 Trave-0.082
 Surviv-0.081
Token with
Token ID351
Feature activation-3.59e-01

Pos logit contributions
Psych+0.400
issan+0.387
psych+0.356
Dex+0.353
 Psych+0.347
Neg logit contributions
rio-0.571
Ire-0.546
 Trave-0.491
-0.488
 Surviv-0.485
Token Unt
Token ID26970
Feature activation-1.54e+00

Pos logit contributions
rio+0.265
Ire+0.250
 Trave+0.221
+0.219
 Surviv+0.217
Neg logit contributions
Psych-0.261
issan-0.255
psych-0.237
Dex-0.235
 Psych-0.232
Tokenapp
Token ID1324
Feature activation+1.38e+00

Pos logit contributions
rio+1.435
Ire+1.360
 Trave+1.245
+1.231
 Surviv+1.224
Neg logit contributions
Psych-0.820
issan-0.794
psych-0.717
Dex-0.710
 Psych-0.694
Tokend
Token ID67
Feature activation-6.01e-03

Pos logit contributions
Psych+0.933
issan+0.896
Dex+0.848
psych+0.847
 Psych+0.820
Neg logit contributions
rio-1.091
Ire-1.049
 Trave-0.930
-0.922
 Surviv-0.920
Token on
Token ID319
Feature activation-1.32e-01

Pos logit contributions
rio+0.005
Ire+0.005
 Trave+0.004
+0.004
 Surviv+0.004
Neg logit contributions
Psych-0.004
issan-0.004
psych-0.003
Dex-0.003
 Psych-0.003
Token Facebook
Token ID3203
Feature activation+5.23e-01

Pos logit contributions
rio+0.115
Ire+0.110
 Trave+0.100
+0.098
 Surviv+0.098
Neg logit contributions
Psych-0.078
issan-0.076
psych-0.069
Dex-0.068
 Psych-0.067
Token,
Token ID11
Feature activation-1.30e-01

Pos logit contributions
Psych+0.362
issan+0.353
psych+0.327
Dex+0.324
 Psych+0.320
Neg logit contributions
rio-0.404
Ire-0.383
 Trave-0.342
-0.338
 Surviv-0.335
Token Twitter
Token ID3009
Feature activation+5.32e-01

Pos logit contributions
rio+0.104
Ire+0.098
 Trave+0.088
+0.087
 Surviv+0.086
Neg logit contributions
Psych-0.087
issan-0.085
psych-0.079
Dex-0.078
 Psych-0.076
TokenO
Token ID46
Feature activation-5.60e-01

Pos logit contributions
rio+0.033
Ire+0.031
 Trave+0.028
+0.028
 Surviv+0.028
Neg logit contributions
Psych-0.033
issan-0.032
psych-0.030
Dex-0.030
 Psych-0.029
Token
Token ID447
Feature activation-3.78e-02

Pos logit contributions
rio+0.455
Ire+0.433
 Trave+0.389
+0.385
 Surviv+0.382
Neg logit contributions
Psych-0.364
issan-0.355
psych-0.328
Dex-0.324
 Psych-0.318
Token
Token ID247
Feature activation+3.57e-01

Pos logit contributions
rio+0.033
Ire+0.031
 Trave+0.028
+0.028
 Surviv+0.028
Neg logit contributions
Psych-0.023
issan-0.022
psych-0.020
Dex-0.020
 Psych-0.019
TokenMalley
Token ID33776
Feature activation-5.81e-01

Pos logit contributions
Psych+0.238
issan+0.231
psych+0.214
Dex+0.212
 Psych+0.208
Neg logit contributions
rio-0.285
Ire-0.270
 Trave-0.243
-0.240
 Surviv-0.239
Token also
Token ID635
Feature activation+5.77e-01

Pos logit contributions
rio+0.459
Ire+0.436
 Trave+0.389
+0.385
 Surviv+0.383
Neg logit contributions
Psych-0.391
issan-0.379
psych-0.352
Dex-0.349
 Psych-0.344
Token responded
Token ID7082
Feature activation+2.73e-01

Pos logit contributions
Psych+0.368
issan+0.359
psych+0.331
Dex+0.327
 Psych+0.323
Neg logit contributions
rio-0.473
Ire-0.453
 Trave-0.405
-0.402
 Surviv-0.401
Token to
Token ID284
Feature activation+7.57e-02

Pos logit contributions
Psych+0.167
issan+0.163
psych+0.149
Dex+0.148
 Psych+0.145
Neg logit contributions
rio-0.233
Ire-0.221
 Trave-0.200
-0.198
 Surviv-0.197
Token President
Token ID1992
Feature activation-4.26e-02

Pos logit contributions
Psych+0.049
issan+0.048
psych+0.044
Dex+0.043
 Psych+0.043
Neg logit contributions
rio-0.062
Ire-0.059
 Trave-0.053
-0.052
 Surviv-0.052
Token Obama
Token ID2486
Feature activation+3.32e-01

Pos logit contributions
rio+0.029
Ire+0.027
 Trave+0.024
+0.024
 Surviv+0.024
Neg logit contributions
Psych-0.033
issan-0.032
psych-0.030
Dex-0.030
 Psych-0.030
Token
Token ID447
Feature activation+8.29e-02

Pos logit contributions
Psych+0.238
issan+0.231
psych+0.216
Dex+0.213
 Psych+0.211
Neg logit contributions
rio-0.249
Ire-0.236
 Trave-0.209
 Surviv-0.206
-0.206
Token
Token ID247
Feature activation+2.15e-01

Pos logit contributions
Psych+0.041
issan+0.039
psych+0.035
Dex+0.035
 Psych+0.034
Neg logit contributions
rio-0.081
Ire-0.077
 Trave-0.071
-0.070
 Surviv-0.070
Token National
Token ID2351
Feature activation+9.45e-02

Pos logit contributions
rio+0.096
Ire+0.092
+0.083
 Trave+0.083
 Surviv+0.082
Neg logit contributions
Psych-0.057
issan-0.055
psych-0.050
Dex-0.050
 Psych-0.049
Token debt
Token ID5057
Feature activation+4.18e-02

Pos logit contributions
Psych+0.070
issan+0.068
psych+0.064
Dex+0.063
 Psych+0.062
Neg logit contributions
rio-0.068
Ire-0.064
 Trave-0.057
-0.056
 Surviv-0.056
Token is
Token ID318
Feature activation+1.52e-01

Pos logit contributions
Psych+0.027
issan+0.026
psych+0.024
Dex+0.024
 Psych+0.023
Neg logit contributions
rio-0.034
Ire-0.033
 Trave-0.029
-0.029
 Surviv-0.029
Token one
Token ID530
Feature activation+7.42e-02

Pos logit contributions
Psych+0.098
issan+0.095
psych+0.088
Dex+0.087
 Psych+0.086
Neg logit contributions
rio-0.124
Ire-0.118
 Trave-0.106
-0.105
 Surviv-0.104
Token of
Token ID286
Feature activation+2.50e-01

Pos logit contributions
Psych+0.049
issan+0.048
psych+0.044
Dex+0.044
 Psych+0.043
Neg logit contributions
rio-0.060
Ire-0.057
 Trave-0.051
-0.050
 Surviv-0.050
Token many
Token ID867
Feature activation+3.06e-02

Pos logit contributions
Psych+0.160
issan+0.155
psych+0.144
Dex+0.142
 Psych+0.140
Neg logit contributions
rio-0.206
Ire-0.195
 Trave-0.175
-0.174
 Surviv-0.173
Token economic
Token ID3034
Feature activation+1.67e-01

Pos logit contributions
Psych+0.020
issan+0.019
psych+0.018
Dex+0.018
 Psych+0.017
Neg logit contributions
rio-0.025
Ire-0.024
 Trave-0.021
-0.021
 Surviv-0.021
Token indicators
Token ID21337
Feature activation+1.24e-01

Pos logit contributions
Psych+0.104
issan+0.101
psych+0.093
Dex+0.092
 Psych+0.090
Neg logit contributions
rio-0.142
Ire-0.134
 Trave-0.121
-0.120
 Surviv-0.120
Token that
Token ID326
Feature activation-4.84e-02

Pos logit contributions
Psych+0.072
issan+0.070
psych+0.064
Dex+0.064
 Psych+0.062
Neg logit contributions
rio-0.110
Ire-0.105
 Trave-0.095
-0.094
 Surviv-0.093
Token inter
Token ID987
Feature activation+1.01e-01

Pos logit contributions
rio+0.041
Ire+0.039
 Trave+0.035
+0.034
 Surviv+0.034
Neg logit contributions
Psych-0.030
issan-0.030
psych-0.027
Dex-0.027
 Psych-0.026
Tokenplay
Token ID1759
Feature activation-7.42e-01

Pos logit contributions
Psych+0.072
issan+0.070
psych+0.066
Dex+0.065
 Psych+0.064
Neg logit contributions
rio-0.075
Ire-0.071
 Trave-0.063
-0.063
 Surviv-0.062
Token
Token ID198
Feature activation-1.12e-01

Pos logit contributions
rio+0.169
Ire+0.162
 Trave+0.148
+0.147
 Surviv+0.147
Neg logit contributions
Psych-0.082
issan-0.079
psych-0.071
Dex-0.070
 Psych-0.068
TokenShortly
Token ID30513
Feature activation-7.49e-02

Pos logit contributions
rio+0.076
Ire+0.071
 Trave+0.063
 Surviv+0.062
+0.062
Neg logit contributions
Psych-0.089
issan-0.086
psych-0.081
Dex-0.081
 Psych-0.079
Token after
Token ID706
Feature activation-4.23e-01

Pos logit contributions
rio+0.057
Ire+0.054
 Trave+0.047
+0.047
 Surviv+0.047
Neg logit contributions
Psych-0.053
issan-0.052
psych-0.048
Dex-0.048
 Psych-0.047
Token Trump
Token ID1301
Feature activation-1.02e-01

Pos logit contributions
rio+0.337
Ire+0.321
 Trave+0.284
+0.283
 Surviv+0.282
Neg logit contributions
Psych-0.282
issan-0.275
psych-0.255
Dex-0.252
 Psych-0.249
Token tweeted
Token ID10830
Feature activation-2.41e-01

Pos logit contributions
rio+0.077
Ire+0.074
 Trave+0.064
 Surviv+0.064
+0.064
Neg logit contributions
Psych-0.072
issan-0.070
psych-0.066
Dex-0.065
 Psych-0.064
Token about
Token ID546
Feature activation-2.58e-01

Pos logit contributions
rio+0.200
Ire+0.190
 Trave+0.171
+0.170
 Surviv+0.169
Neg logit contributions
Psych-0.153
issan-0.149
psych-0.137
Dex-0.135
 Psych-0.133
Token his
Token ID465
Feature activation-1.83e-01

Pos logit contributions
rio+0.214
Ire+0.203
 Trave+0.181
+0.181
 Surviv+0.180
Neg logit contributions
Psych-0.165
issan-0.161
psych-0.148
Dex-0.146
 Psych-0.144
Token ban
Token ID3958
Feature activation+1.97e-01

Pos logit contributions
rio+0.143
Ire+0.135
+0.120
 Trave+0.119
 Surviv+0.119
Neg logit contributions
Psych-0.125
issan-0.122
psych-0.113
Dex-0.112
 Psych-0.111
Token,
Token ID11
Feature activation-2.04e-02

Pos logit contributions
Psych+0.134
issan+0.131
psych+0.122
Dex+0.121
 Psych+0.119
Neg logit contributions
rio-0.155
Ire-0.147
 Trave-0.131
-0.130
 Surviv-0.129
Token he
Token ID339
Feature activation-1.63e-01

Pos logit contributions
rio+0.017
Ire+0.016
 Trave+0.015
+0.014
 Surviv+0.014
Neg logit contributions
Psych-0.013
issan-0.013
psych-0.012
Dex-0.011
 Psych-0.011
Token offered
Token ID4438
Feature activation+1.97e-01

Pos logit contributions
rio+0.127
Ire+0.121
 Trave+0.107
+0.106
 Surviv+0.106
Neg logit contributions
Psych-0.111
issan-0.109
psych-0.101
Dex-0.100
 Psych-0.098
Token for
Token ID329
Feature activation+5.55e-02

Pos logit contributions
rio+0.397
Ire+0.378
 Trave+0.341
+0.338
 Surviv+0.336
Neg logit contributions
Psych-0.277
issan-0.269
psych-0.247
Dex-0.244
 Psych-0.239
Token the
Token ID262
Feature activation+1.32e-01

Pos logit contributions
Psych+0.032
issan+0.032
psych+0.029
Dex+0.029
 Psych+0.028
Neg logit contributions
rio-0.049
Ire-0.047
 Trave-0.042
-0.042
 Surviv-0.041
Token 600
Token ID10053
Feature activation+1.02e-01

Pos logit contributions
Psych+0.075
issan+0.073
psych+0.066
Dex+0.066
 Psych+0.064
Neg logit contributions
rio-0.118
Ire-0.113
 Trave-0.102
-0.102
 Surviv-0.100
Token-
Token ID12
Feature activation-1.06e-01

Pos logit contributions
Psych+0.066
issan+0.064
psych+0.059
Dex+0.059
 Psych+0.057
Neg logit contributions
rio-0.083
Ire-0.080
 Trave-0.071
-0.071
 Surviv-0.070
Tokenodd
Token ID5088
Feature activation-1.19e+00

Pos logit contributions
rio+0.081
Ire+0.077
 Trave+0.069
+0.068
 Surviv+0.067
Neg logit contributions
Psych-0.074
issan-0.072
psych-0.067
Dex-0.067
 Psych-0.065
Token channels
Token ID9619
Feature activation+5.45e-01

Pos logit contributions
rio+1.034
Ire+0.981
 Trave+0.891
 Surviv+0.878
+0.877
Neg logit contributions
Psych-0.709
issan-0.689
psych-0.632
Dex-0.620
 Psych-0.607
Token of
Token ID286
Feature activation-7.28e-02

Pos logit contributions
Psych+0.340
issan+0.330
psych+0.304
Dex+0.303
 Psych+0.298
Neg logit contributions
rio-0.457
Ire-0.437
 Trave-0.390
-0.388
 Surviv-0.384
Token real
Token ID1103
Feature activation+1.50e-02

Pos logit contributions
rio+0.060
Ire+0.057
 Trave+0.051
+0.051
 Surviv+0.051
Neg logit contributions
Psych-0.046
issan-0.045
psych-0.042
Dex-0.041
 Psych-0.040
Token-
Token ID12
Feature activation-2.83e-01

Pos logit contributions
Psych+0.009
issan+0.009
psych+0.008
Dex+0.008
 Psych+0.008
Neg logit contributions
rio-0.013
Ire-0.012
 Trave-0.011
-0.011
 Surviv-0.011
Tokentime
Token ID2435
Feature activation-8.30e-01

Pos logit contributions
rio+0.238
Ire+0.226
 Trave+0.204
+0.202
 Surviv+0.201
Neg logit contributions
Psych-0.177
issan-0.172
psych-0.158
Dex-0.156
 Psych-0.154
Token viewing
Token ID11681
Feature activation-6.42e-01

Pos logit contributions
rio+0.707
Ire+0.672
 Trave+0.607
+0.600
 Surviv+0.597
Neg logit contributions
Psych-0.509
issan-0.496
psych-0.455
Dex-0.450
 Psych-0.441
Token
Token ID198
Feature activation-1.60e-01

Pos logit contributions
rio+0.066
Ire+0.063
 Trave+0.058
+0.057
 Surviv+0.057
Neg logit contributions
Psych-0.033
issan-0.032
psych-0.029
Dex-0.028
 Psych-0.027
TokenEvery
Token ID6109
Feature activation+1.03e-01

Pos logit contributions
rio+0.126
Ire+0.119
 Trave+0.107
+0.106
 Surviv+0.105
Neg logit contributions
Psych-0.108
issan-0.106
psych-0.098
Dex-0.097
 Psych-0.095
Token year
Token ID614
Feature activation+1.10e-01

Pos logit contributions
Psych+0.062
issan+0.060
psych+0.055
Dex+0.054
 Psych+0.054
Neg logit contributions
rio-0.089
Ire-0.085
 Trave-0.076
-0.076
 Surviv-0.075
Token 5
Token ID642
Feature activation+6.35e-01

Pos logit contributions
Psych+0.074
issan+0.073
psych+0.067
Dex+0.066
 Psych+0.065
Neg logit contributions
rio-0.086
Ire-0.082
 Trave-0.073
-0.072
 Surviv-0.072
Token lakh
Token ID29002
Feature activation-2.56e-01

Pos logit contributions
Psych+0.398
issan+0.389
psych+0.357
Dex+0.351
 Psych+0.347
Neg logit contributions
rio-0.531
Ire-0.505
 Trave-0.452
-0.450
 Surviv-0.447
Token road
Token ID2975
Feature activation-9.09e-02

Pos logit contributions
rio+0.220
Ire+0.209
 Trave+0.188
+0.187
 Surviv+0.186
Neg logit contributions
Psych-0.155
issan-0.151
psych-0.138
Dex-0.136
 Psych-0.134
Token accidents
Token ID17390
Feature activation-6.26e-01

Pos logit contributions
rio+0.070
Ire+0.067
 Trave+0.059
+0.059
 Surviv+0.058
Neg logit contributions
Psych-0.062
issan-0.061
psych-0.057
Dex-0.056
 Psych-0.055
Token are
Token ID389
Feature activation+2.06e-02

Pos logit contributions
rio+0.509
Ire+0.478
 Trave+0.434
+0.425
 Surviv+0.425
Neg logit contributions
Psych-0.410
issan-0.399
psych-0.369
Dex-0.365
 Psych-0.358
Token reported
Token ID2098
Feature activation+3.27e-01

Pos logit contributions
Psych+0.012
issan+0.012
psych+0.011
Dex+0.011
 Psych+0.010
Neg logit contributions
rio-0.018
Ire-0.017
 Trave-0.016
-0.015
 Surviv-0.015
Token in
Token ID287
Feature activation-1.40e-02

Pos logit contributions
Psych+0.209
issan+0.203
psych+0.187
Dex+0.185
 Psych+0.182
Neg logit contributions
rio-0.270
Ire-0.257
 Trave-0.231
-0.229
 Surviv-0.228
Token the
Token ID262
Feature activation-1.01e-01

Pos logit contributions
rio+0.011
Ire+0.010
 Trave+0.009
+0.009
 Surviv+0.009
Neg logit contributions
Psych-0.010
issan-0.009
psych-0.009
Dex-0.009
 Psych-0.009
Token look
Token ID804
Feature activation-7.92e-01

Pos logit contributions
rio+0.068
Ire+0.064
 Trave+0.058
+0.057
 Surviv+0.057
Neg logit contributions
Psych-0.051
issan-0.050
psych-0.046
Dex-0.045
 Psych-0.045
Token like
Token ID588
Feature activation+2.98e-01

Pos logit contributions
rio+0.651
Ire+0.617
 Trave+0.556
+0.550
 Surviv+0.546
Neg logit contributions
Psych-0.508
issan-0.496
psych-0.457
Dex-0.452
 Psych-0.443
Token someone
Token ID2130
Feature activation+2.73e-02

Pos logit contributions
Psych+0.185
issan+0.180
psych+0.166
Dex+0.164
 Psych+0.161
Neg logit contributions
rio-0.252
Ire-0.240
 Trave-0.216
-0.214
 Surviv-0.213
Token has
Token ID468
Feature activation+2.28e-01

Pos logit contributions
Psych+0.018
issan+0.018
psych+0.016
Dex+0.016
 Psych+0.016
Neg logit contributions
rio-0.022
Ire-0.021
 Trave-0.019
-0.019
 Surviv-0.018
Token shouted
Token ID17293
Feature activation+1.64e-01

Pos logit contributions
Psych+0.147
issan+0.143
psych+0.132
Dex+0.131
 Psych+0.129
Neg logit contributions
rio-0.187
Ire-0.178
 Trave-0.160
-0.158
 Surviv-0.157
Token fire
Token ID2046
Feature activation-4.21e-01

Pos logit contributions
Psych+0.102
issan+0.099
psych+0.091
Dex+0.090
 Psych+0.089
Neg logit contributions
rio-0.139
Ire-0.133
 Trave-0.119
-0.118
 Surviv-0.117
Token in
Token ID287
Feature activation+1.11e-02

Pos logit contributions
rio+0.340
Ire+0.322
 Trave+0.290
+0.286
 Surviv+0.285
Neg logit contributions
Psych-0.277
issan-0.269
psych-0.250
Dex-0.246
 Psych-0.243
Token a
Token ID257
Feature activation+7.19e-02

Pos logit contributions
Psych+0.007
issan+0.007
psych+0.006
Dex+0.006
 Psych+0.006
Neg logit contributions
rio-0.009
Ire-0.009
 Trave-0.008
-0.008
 Surviv-0.008
Token crowded
Token ID18012
Feature activation-3.35e-01

Pos logit contributions
Psych+0.047
issan+0.045
psych+0.042
Dex+0.041
 Psych+0.041
Neg logit contributions
rio-0.059
Ire-0.056
 Trave-0.050
-0.050
 Surviv-0.050
Token theater
Token ID13766
Feature activation+2.57e-01

Pos logit contributions
rio+0.257
Ire+0.244
 Trave+0.216
+0.214
 Surviv+0.213
Neg logit contributions
Psych-0.233
issan-0.227
psych-0.212
Dex-0.210
 Psych-0.207
Token,
Token ID11
Feature activation-4.48e-02

Pos logit contributions
Psych+0.164
issan+0.159
psych+0.147
Dex+0.145
 Psych+0.143
Neg logit contributions
rio-0.213
Ire-0.203
 Trave-0.183
-0.181
 Surviv-0.180
Token time
Token ID640
Feature activation-1.70e-01

Pos logit contributions
rio+0.576
Ire+0.548
 Trave+0.498
+0.492
 Surviv+0.489
Neg logit contributions
Psych-0.387
issan-0.376
psych-0.344
Dex-0.340
 Psych-0.332
Token.
Token ID13
Feature activation-1.42e-02

Pos logit contributions
rio+0.136
Ire+0.129
 Trave+0.116
+0.115
 Surviv+0.114
Neg logit contributions
Psych-0.113
issan-0.110
psych-0.102
Dex-0.101
 Psych-0.099
Token<|endoftext|>
Token ID50256
Feature activation-1.88e-01

Pos logit contributions
rio+0.013
Ire+0.013
 Trave+0.012
+0.012
 Surviv+0.011
Neg logit contributions
Psych-0.007
issan-0.007
psych-0.007
Dex-0.006
 Psych-0.006
TokenThe
Token ID464
Feature activation-2.56e-01

Pos logit contributions
rio+0.138
Ire+0.130
 Trave+0.116
+0.114
 Surviv+0.113
Neg logit contributions
Psych-0.138
issan-0.134
psych-0.125
Dex-0.124
 Psych-0.122
Token stolen
Token ID9909
Feature activation+3.87e-02

Pos logit contributions
rio+0.207
Ire+0.196
 Trave+0.175
+0.175
 Surviv+0.173
Neg logit contributions
Psych-0.168
issan-0.164
psych-0.151
Dex-0.149
 Psych-0.148
Token bike
Token ID7161
Feature activation-6.03e-01

Pos logit contributions
Psych+0.025
issan+0.024
psych+0.022
Dex+0.022
 Psych+0.022
Neg logit contributions
rio-0.032
Ire-0.030
 Trave-0.027
-0.027
 Surviv-0.027
Token,
Token ID11
Feature activation+2.19e-01

Pos logit contributions
rio+0.476
Ire+0.452
 Trave+0.403
+0.400
 Surviv+0.397
Neg logit contributions
Psych-0.406
issan-0.397
psych-0.367
Dex-0.365
 Psych-0.358
Token a
Token ID257
Feature activation+3.24e-01

Pos logit contributions
Psych+0.140
issan+0.136
psych+0.125
Dex+0.125
 Psych+0.122
Neg logit contributions
rio-0.181
Ire-0.172
 Trave-0.154
-0.153
 Surviv-0.152
Token 1982
Token ID14489
Feature activation-1.37e-01

Pos logit contributions
Psych+0.213
issan+0.208
psych+0.191
Dex+0.190
 Psych+0.187
Neg logit contributions
rio-0.261
Ire-0.248
 Trave-0.221
-0.220
 Surviv-0.219
Token V
Token ID569
Feature activation+6.72e-01

Pos logit contributions
rio+0.111
Ire+0.106
 Trave+0.094
+0.094
 Surviv+0.094
Neg logit contributions
Psych-0.089
issan-0.087
psych-0.080
Dex-0.079
 Psych-0.078
Tokenitus
Token ID17506
Feature activation+9.06e-01

Pos logit contributions
Psych+0.417
issan+0.407
psych+0.372
Dex+0.369
 Psych+0.362
Neg logit contributions
rio-0.563
Ire-0.539
 Trave-0.487
-0.482
 Surviv-0.480
Token the
Token ID262
Feature activation-2.97e-01

Pos logit contributions
Psych+0.041
issan+0.040
psych+0.036
Dex+0.036
 Psych+0.035
Neg logit contributions
rio-0.059
Ire-0.057
 Trave-0.051
-0.051
 Surviv-0.050
Token middle
Token ID3504
Feature activation+5.45e-01

Pos logit contributions
rio+0.219
Ire+0.208
 Trave+0.183
+0.182
 Surviv+0.181
Neg logit contributions
Psych-0.215
issan-0.210
psych-0.196
Dex-0.194
 Psych-0.192
Token of
Token ID286
Feature activation-1.56e-01

Pos logit contributions
Psych+0.348
issan+0.340
psych+0.314
Dex+0.309
 Psych+0.306
Neg logit contributions
rio-0.446
Ire-0.428
 Trave-0.382
 Surviv-0.378
-0.378
Token the
Token ID262
Feature activation-3.14e-01

Pos logit contributions
rio+0.129
Ire+0.123
 Trave+0.110
+0.109
 Surviv+0.108
Neg logit contributions
Psych-0.098
issan-0.096
psych-0.088
Dex-0.087
 Psych-0.087
Token at
Token ID379
Feature activation-2.72e-01

Pos logit contributions
rio+0.213
Ire+0.200
 Trave+0.175
+0.173
 Surviv+0.172
Neg logit contributions
Psych-0.246
issan-0.241
psych-0.226
Dex-0.224
 Psych-0.223
Tokenoll
Token ID692
Feature activation-6.02e-01

Pos logit contributions
rio+0.220
Ire+0.209
 Trave+0.188
+0.186
 Surviv+0.185
Neg logit contributions
Psych-0.179
issan-0.174
psych-0.161
Dex-0.159
 Psych-0.156
Token.
Token ID13
Feature activation-1.50e-02

Pos logit contributions
rio+0.500
Ire+0.477
 Trave+0.428
+0.424
 Surviv+0.421
Neg logit contributions
Psych-0.381
issan-0.372
psych-0.342
Dex-0.338
 Psych-0.333
Token
Token ID198
Feature activation-7.63e-02

Pos logit contributions
rio+0.014
Ire+0.013
 Trave+0.012
+0.012
 Surviv+0.012
Neg logit contributions
Psych-0.008
issan-0.008
psych-0.007
Dex-0.007
 Psych-0.007
Token
Token ID198
Feature activation-1.31e-01

Pos logit contributions
rio+0.075
Ire+0.072
 Trave+0.066
+0.065
 Surviv+0.065
Neg logit contributions
Psych-0.037
issan-0.036
psych-0.032
Dex-0.032
 Psych-0.031
TokenThe
Token ID464
Feature activation-1.16e-01

Pos logit contributions
rio+0.096
Ire+0.090
 Trave+0.081
 Surviv+0.079
+0.079
Neg logit contributions
Psych-0.097
issan-0.094
psych-0.088
Dex-0.088
 Psych-0.085
Token drone
Token ID12170
Feature activation-5.72e-01

Pos logit contributions
rio+0.092
Ire+0.087
+0.078
 Trave+0.078
 Surviv+0.076
Neg logit contributions
Psych-0.077
issan-0.076
psych-0.070
Dex-0.069
 Psych-0.069
Token this
Token ID428
Feature activation+6.41e-02

Pos logit contributions
Psych+0.287
issan+0.280
psych+0.258
Dex+0.255
 Psych+0.251
Neg logit contributions
rio-0.375
Ire-0.357
 Trave-0.320
-0.318
 Surviv-0.316
Token morning
Token ID3329
Feature activation+9.29e-01

Pos logit contributions
Psych+0.037
issan+0.036
psych+0.033
Dex+0.033
 Psych+0.032
Neg logit contributions
rio-0.057
Ire-0.054
 Trave-0.049
-0.049
 Surviv-0.048
Token.
Token ID13
Feature activation-2.08e-02

Pos logit contributions
Psych+0.568
issan+0.553
psych+0.508
Dex+0.501
 Psych+0.494
Neg logit contributions
rio-0.792
Ire-0.755
 Trave-0.678
-0.673
 Surviv-0.671
Token
Token ID198
Feature activation-2.32e-01

Pos logit contributions
rio+0.019
Ire+0.018
 Trave+0.017
+0.017
 Surviv+0.016
Neg logit contributions
Psych-0.011
issan-0.011
psych-0.010
Dex-0.010
 Psych-0.010
Token
Token ID198
Feature activation-2.98e-01

Pos logit contributions
rio+0.225
Ire+0.215
 Trave+0.198
+0.195
 Surviv+0.194
Neg logit contributions
Psych-0.114
issan-0.111
psych-0.099
Dex-0.097
 Psych-0.095
TokenMore
Token ID5167
Feature activation-3.65e-01

Pos logit contributions
rio+0.218
Ire+0.205
 Trave+0.182
+0.179
 Surviv+0.178
Neg logit contributions
Psych-0.220
issan-0.214
psych-0.200
Dex-0.198
 Psych-0.195
Token than
Token ID621
Feature activation+1.37e-01

Pos logit contributions
rio+0.308
Ire+0.292
 Trave+0.264
+0.261
 Surviv+0.259
Neg logit contributions
Psych-0.227
issan-0.221
psych-0.203
Dex-0.201
 Psych-0.197
Token an
Token ID281
Feature activation+7.36e-02

Pos logit contributions
Psych+0.081
issan+0.079
psych+0.072
Dex+0.071
 Psych+0.070
Neg logit contributions
rio-0.120
Ire-0.114
 Trave-0.103
-0.102
 Surviv-0.102
Token hour
Token ID1711
Feature activation+2.13e-01

Pos logit contributions
Psych+0.042
issan+0.041
psych+0.037
Dex+0.036
 Psych+0.036
Neg logit contributions
rio-0.066
Ire-0.063
 Trave-0.057
 Surviv-0.056
-0.056
Token before
Token ID878
Feature activation+6.28e-01

Pos logit contributions
Psych+0.142
issan+0.139
psych+0.128
Dex+0.126
 Psych+0.125
Neg logit contributions
rio-0.170
Ire-0.162
 Trave-0.144
-0.143
 Surviv-0.143
Token kick
Token ID4829
Feature activation+1.87e-01

Pos logit contributions
Psych+0.403
issan+0.392
psych+0.361
Dex+0.357
 Psych+0.354
Neg logit contributions
rio-0.519
Ire-0.493
 Trave-0.440
-0.439
 Surviv-0.436
Token-
Token ID12
Feature activation+4.96e-01

Pos logit contributions
rio+0.818
Ire+0.779
 Trave+0.705
+0.698
 Surviv+0.694
Neg logit contributions
Psych-0.559
issan-0.543
psych-0.497
Dex-0.492
 Psych-0.482
TokenFrank
Token ID17439
Feature activation+2.36e-01

Pos logit contributions
Psych+0.212
issan+0.205
psych+0.180
Dex+0.177
 Psych+0.172
Neg logit contributions
rio-0.514
Ire-0.493
 Trave-0.454
-0.450
 Surviv-0.448
Tokeniv
Token ID452
Feature activation+4.49e-02

Pos logit contributions
Psych+0.192
issan+0.188
psych+0.178
Dex+0.175
 Psych+0.172
Neg logit contributions
rio-0.153
Ire-0.146
 Trave-0.125
-0.125
 Surviv-0.124
Tokensk
Token ID8135
Feature activation-2.72e-02

Pos logit contributions
Psych+0.029
issan+0.029
psych+0.026
Dex+0.026
 Psych+0.026
Neg logit contributions
rio-0.036
Ire-0.034
 Trave-0.031
-0.031
 Surviv-0.030
Token.
Token ID13
Feature activation+6.83e-02

Pos logit contributions
rio+0.022
Ire+0.021
 Trave+0.019
+0.018
 Surviv+0.018
Neg logit contributions
Psych-0.018
issan-0.017
psych-0.016
Dex-0.016
 Psych-0.016
Token<|endoftext|>
Token ID50256
Feature activation-4.07e-01

Pos logit contributions
Psych+0.049
issan+0.047
psych+0.044
Dex+0.044
 Psych+0.043
Neg logit contributions
rio-0.052
Ire-0.049
 Trave-0.043
-0.043
 Surviv-0.042
Token[
Token ID58
Feature activation-1.28e+00

Pos logit contributions
rio+0.299
Ire+0.281
 Trave+0.250
+0.247
 Surviv+0.245
Neg logit contributions
Psych-0.297
issan-0.290
psych-0.271
Dex-0.268
 Psych-0.263
TokenEx
Token ID3109
Feature activation+9.58e-02

Pos logit contributions
rio+1.005
Ire+0.952
 Trave+0.852
+0.842
 Surviv+0.837
Neg logit contributions
Psych-0.869
issan-0.847
psych-0.786
Dex-0.778
 Psych-0.764
Tokenclusive
Token ID5731
Feature activation+5.83e-01

Pos logit contributions
Psych+0.070
issan+0.068
psych+0.063
Dex+0.063
 Psych+0.062
Neg logit contributions
rio-0.071
Ire-0.068
 Trave-0.060
-0.059
 Surviv-0.059
Token]
Token ID60
Feature activation+2.58e-01

Pos logit contributions
Psych+0.393
issan+0.381
psych+0.355
Dex+0.352
 Psych+0.349
Neg logit contributions
rio-0.461
Ire-0.438
 Trave-0.388
-0.386
 Surviv-0.383
Token Best
Token ID6705
Feature activation-3.64e-01

Pos logit contributions
Psych+0.176
issan+0.172
psych+0.159
Dex+0.158
 Psych+0.156
Neg logit contributions
rio-0.202
Ire-0.191
 Trave-0.170
-0.169
 Surviv-0.167
Token a
Token ID257
Feature activation-2.55e-01

Pos logit contributions
rio+0.370
Ire+0.351
 Trave+0.313
+0.311
 Surviv+0.309
Neg logit contributions
Psych-0.306
issan-0.298
psych-0.276
Dex-0.273
 Psych-0.269
Token Zel
Token ID40071
Feature activation-2.68e-01

Pos logit contributions
rio+0.208
Ire+0.197
 Trave+0.177
+0.175
 Surviv+0.174
Neg logit contributions
Psych-0.165
issan-0.161
psych-0.149
Dex-0.147
 Psych-0.145
Tokenig
Token ID328
Feature activation-3.71e-01

Pos logit contributions
rio+0.210
Ire+0.198
 Trave+0.177
+0.175
 Surviv+0.174
Neg logit contributions
Psych-0.182
issan-0.178
psych-0.164
Dex-0.163
 Psych-0.160
Token who
Token ID508
Feature activation-3.41e-01

Pos logit contributions
rio+0.305
Ire+0.286
 Trave+0.261
+0.255
 Surviv+0.254
Neg logit contributions
Psych-0.239
issan-0.233
psych-0.214
Dex-0.212
 Psych-0.207
Token trek
Token ID30784
Feature activation-2.19e-01

Pos logit contributions
rio+0.265
Ire+0.252
 Trave+0.223
+0.222
 Surviv+0.220
Neg logit contributions
Psych-0.233
issan-0.228
psych-0.211
Dex-0.209
 Psych-0.206
Tokenked
Token ID9091
Feature activation-2.17e+00

Pos logit contributions
rio+0.170
Ire+0.162
 Trave+0.143
+0.142
 Surviv+0.141
Neg logit contributions
Psych-0.151
issan-0.148
psych-0.137
Dex-0.136
 Psych-0.133
Token to
Token ID284
Feature activation-3.64e-01

Pos logit contributions
rio+1.716
Ire+1.619
 Trave+1.465
+1.439
 Surviv+1.431
Neg logit contributions
Psych-1.456
issan-1.424
psych-1.312
Dex-1.299
 Psych-1.271
Token the
Token ID262
Feature activation-4.57e-01

Pos logit contributions
rio+0.288
Ire+0.272
 Trave+0.243
+0.241
 Surviv+0.239
Neg logit contributions
Psych-0.245
issan-0.239
psych-0.222
Dex-0.219
 Psych-0.216
Token North
Token ID2258
Feature activation-1.75e-01

Pos logit contributions
rio+0.361
Ire+0.341
 Trave+0.305
+0.302
 Surviv+0.300
Neg logit contributions
Psych-0.309
issan-0.301
psych-0.279
Dex-0.276
 Psych-0.272
Token Pole
Token ID29385
Feature activation-2.72e-01

Pos logit contributions
rio+0.126
Ire+0.118
 Trave+0.105
+0.103
 Surviv+0.102
Neg logit contributions
Psych-0.131
issan-0.128
psych-0.119
Dex-0.118
 Psych-0.116
Token but
Token ID475
Feature activation-5.21e-01

Pos logit contributions
rio+0.222
Ire+0.211
 Trave+0.189
+0.187
 Surviv+0.186
Neg logit contributions
Psych-0.177
issan-0.172
psych-0.159
Dex-0.157
 Psych-0.155
Token
Token ID198
Feature activation+3.92e-01

Pos logit contributions
Psych+0.209
issan+0.200
psych+0.180
Dex+0.178
 Psych+0.173
Neg logit contributions
rio-0.435
Ire-0.417
 Trave-0.382
-0.379
 Surviv-0.378
TokenHe
Token ID1544
Feature activation+4.46e-01

Pos logit contributions
Psych+0.290
issan+0.279
psych+0.262
Dex+0.261
 Psych+0.255
Neg logit contributions
rio-0.286
Ire-0.268
 Trave-0.240
 Surviv-0.236
-0.236
Token then
Token ID788
Feature activation+5.62e-01

Pos logit contributions
Psych+0.273
issan+0.265
psych+0.244
Dex+0.241
 Psych+0.236
Neg logit contributions
rio-0.379
Ire-0.362
 Trave-0.326
-0.323
 Surviv-0.322
Token immediately
Token ID3393
Feature activation+2.45e-01

Pos logit contributions
Psych+0.338
issan+0.328
psych+0.302
Dex+0.298
 Psych+0.293
Neg logit contributions
rio-0.483
Ire-0.462
 Trave-0.416
-0.412
 Surviv-0.410
Token piv
Token ID16767
Feature activation-2.56e-01

Pos logit contributions
Psych+0.151
issan+0.147
psych+0.135
Dex+0.134
 Psych+0.132
Neg logit contributions
rio-0.206
Ire-0.197
 Trave-0.177
-0.175
 Surviv-0.174
Tokenoted
Token ID5191
Feature activation-2.16e+00

Pos logit contributions
rio+0.126
Ire+0.121
+0.099
 Surviv+0.098
 Trave+0.098
Neg logit contributions
Psych-0.247
issan-0.244
psych-0.232
Dex-0.227
 Psych-0.224
Token to
Token ID284
Feature activation+1.86e-01

Pos logit contributions
rio+1.814
Ire+1.720
 Trave+1.555
+1.537
 Surviv+1.526
Neg logit contributions
Psych-1.343
issan-1.308
psych-1.202
Dex-1.189
 Psych-1.165
Token the
Token ID262
Feature activation+1.31e-01

Pos logit contributions
Psych+0.116
issan+0.112
psych+0.104
Dex+0.102
 Psych+0.101
Neg logit contributions
rio-0.156
Ire-0.149
 Trave-0.134
-0.133
 Surviv-0.132
Token story
Token ID1621
Feature activation+6.15e-01

Pos logit contributions
Psych+0.085
issan+0.083
psych+0.076
Dex+0.075
 Psych+0.075
Neg logit contributions
rio-0.107
Ire-0.101
 Trave-0.091
-0.090
 Surviv-0.090
Token of
Token ID286
Feature activation-6.22e-02

Pos logit contributions
Psych+0.395
issan+0.384
psych+0.355
Dex+0.352
 Psych+0.346
Neg logit contributions
rio-0.504
Ire-0.481
 Trave-0.431
-0.427
 Surviv-0.424
Token Rachel
Token ID15984
Feature activation-1.67e-01

Pos logit contributions
rio+0.052
Ire+0.050
 Trave+0.045
+0.044
 Surviv+0.044
Neg logit contributions
Psych-0.039
issan-0.038
psych-0.035
Dex-0.034
 Psych-0.034
Token.
Token ID13
Feature activation-7.45e-01

Pos logit contributions
rio+0.858
Ire+0.817
 Trave+0.736
+0.729
 Surviv+0.725
Neg logit contributions
Psych-0.619
issan-0.601
psych-0.553
Dex-0.547
 Psych-0.537
Token Sign
Token ID5865
Feature activation-1.02e+00

Pos logit contributions
rio+0.586
Ire+0.555
+0.492
 Trave+0.491
 Surviv+0.485
Neg logit contributions
Psych-0.510
issan-0.491
psych-0.460
Dex-0.456
 Psych-0.452
Token Up
Token ID3205
Feature activation-9.52e-01

Pos logit contributions
rio+0.645
Ire+0.606
 Trave+0.520
+0.519
 Surviv+0.512
Neg logit contributions
Psych-0.849
issan-0.827
psych-0.782
Dex-0.776
 Psych-0.770
Token You
Token ID921
Feature activation-6.27e-01

Pos logit contributions
rio+0.699
Ire+0.657
 Trave+0.586
+0.575
 Surviv+0.572
Neg logit contributions
Psych-0.694
issan-0.681
psych-0.633
Dex-0.626
 Psych-0.614
Token will
Token ID481
Feature activation-1.00e+00

Pos logit contributions
rio+0.448
Ire+0.420
 Trave+0.372
+0.366
 Surviv+0.364
Neg logit contributions
Psych-0.471
issan-0.461
psych-0.430
Dex-0.426
 Psych-0.419
Token receive
Token ID3328
Feature activation-1.99e+00

Pos logit contributions
rio+0.788
Ire+0.746
 Trave+0.667
+0.660
 Surviv+0.656
Neg logit contributions
Psych-0.683
issan-0.666
psych-0.618
Dex-0.611
 Psych-0.601
Token emails
Token ID7237
Feature activation-8.44e-01

Pos logit contributions
rio+1.261
Ire+1.175
 Trave+1.023
+1.004
 Surviv+0.996
Neg logit contributions
Psych-1.651
issan-1.620
psych-1.521
Dex-1.510
 Psych-1.487
Token containing
Token ID7268
Feature activation-1.06e+00

Pos logit contributions
rio+0.551
Ire+0.515
 Trave+0.450
+0.443
 Surviv+0.439
Neg logit contributions
Psych-0.685
issan-0.671
psych-0.630
Dex-0.624
 Psych-0.616
Token news
Token ID1705
Feature activation-6.77e-01

Pos logit contributions
rio+0.966
Ire+0.922
 Trave+0.839
+0.831
 Surviv+0.827
Neg logit contributions
Psych-0.585
issan-0.567
psych-0.516
Dex-0.509
 Psych-0.499
Token content
Token ID2695
Feature activation-1.57e+00

Pos logit contributions
rio+0.585
Ire+0.558
 Trave+0.505
+0.501
 Surviv+0.499
Neg logit contributions
Psych-0.405
issan-0.394
psych-0.362
Dex-0.358
 Psych-0.351
Token,
Token ID837
Feature activation-1.71e+00

Pos logit contributions
rio+1.232
Ire+1.160
 Trave+1.044
+1.028
 Surviv+1.021
Neg logit contributions
Psych-1.064
issan-1.042
psych-0.963
Dex-0.954
 Psych-0.933
Token i
Token ID1312
Feature activation-1.20e+00

Pos logit contributions
Psych+0.054
issan+0.053
psych+0.049
Dex+0.048
 Psych+0.047
Neg logit contributions
rio-0.068
Ire-0.064
 Trave-0.058
-0.057
 Surviv-0.057
Token n
Token ID299
Feature activation-1.77e+00

Pos logit contributions
rio+0.975
Ire+0.923
 Trave+0.830
+0.821
 Surviv+0.815
Neg logit contributions
Psych-0.779
issan-0.759
psych-0.700
Dex-0.693
 Psych-0.680
Tokenā
Token ID10235
Feature activation-3.31e-01

Pos logit contributions
rio+1.357
Ire+1.283
 Trave+1.144
+1.130
 Surviv+1.123
Neg logit contributions
Psych-1.242
issan-1.214
psych-1.127
Dex-1.116
 Psych-1.097
Token i
Token ID1312
Feature activation-1.22e+00

Pos logit contributions
rio+0.269
Ire+0.255
 Trave+0.229
+0.227
 Surviv+0.225
Neg logit contributions
Psych-0.215
issan-0.210
psych-0.194
Dex-0.192
 Psych-0.188
Tokenwi
Token ID37686
Feature activation+1.63e-01

Pos logit contributions
rio+0.996
Ire+0.942
 Trave+0.848
+0.840
 Surviv+0.833
Neg logit contributions
Psych-0.788
issan-0.768
psych-0.708
Dex-0.701
 Psych-0.687
Token o
Token ID267
Feature activation-2.19e+00

Pos logit contributions
Psych+0.104
issan+0.102
psych+0.094
Dex+0.093
 Psych+0.091
Neg logit contributions
rio-0.135
Ire-0.128
 Trave-0.115
-0.114
 Surviv-0.113
Token K
Token ID509
Feature activation-4.37e-01

Pos logit contributions
rio+1.843
Ire+1.739
 Trave+1.579
+1.558
 Surviv+1.547
Neg logit contributions
Psych-1.365
issan-1.331
psych-1.221
Dex-1.208
 Psych-1.178
Tokenā
Token ID10235
Feature activation-1.30e-01

Pos logit contributions
rio+0.325
Ire+0.308
 Trave+0.274
+0.270
 Surviv+0.269
Neg logit contributions
Psych-0.314
issan-0.307
psych-0.286
Dex-0.282
 Psych-0.278
Tokenn
Token ID77
Feature activation+1.17e-01

Pos logit contributions
rio+0.099
Ire+0.094
 Trave+0.084
+0.082
 Surviv+0.082
Neg logit contributions
Psych-0.091
issan-0.089
psych-0.082
Dex-0.082
 Psych-0.080
Tokenep
Token ID538
Feature activation-7.01e-02

Pos logit contributions
Psych+0.064
issan+0.062
psych+0.056
Dex+0.055
 Psych+0.054
Neg logit contributions
rio-0.107
Ire-0.103
 Trave-0.094
-0.093
 Surviv-0.093
Tokenō
Token ID13090
Feature activation-3.93e-01

Pos logit contributions
rio+0.035
Ire+0.033
 Trave+0.028
 Surviv+0.028
+0.027
Neg logit contributions
Psych-0.066
issan-0.066
psych-0.062
Dex-0.061
 Psych-0.061
Token gave
Token ID2921
Feature activation-1.53e-01

Pos logit contributions
rio+0.296
Ire+0.281
 Trave+0.250
+0.247
 Surviv+0.246
Neg logit contributions
Psych-0.259
issan-0.253
psych-0.235
Dex-0.232
 Psych-0.229
Token 44
Token ID5846
Feature activation-3.44e-01

Pos logit contributions
rio+0.126
Ire+0.119
 Trave+0.107
+0.106
 Surviv+0.105
Neg logit contributions
Psych-0.099
issan-0.096
psych-0.089
Dex-0.088
 Psych-0.087
Token%
Token ID4
Feature activation+5.18e-01

Pos logit contributions
rio+0.320
Ire+0.306
 Trave+0.279
+0.276
 Surviv+0.275
Neg logit contributions
Psych-0.183
issan-0.178
psych-0.161
Dex-0.159
 Psych-0.155
Token of
Token ID286
Feature activation-4.23e-01

Pos logit contributions
Psych+0.338
issan+0.329
psych+0.305
Dex+0.301
 Psych+0.296
Neg logit contributions
rio-0.420
Ire-0.398
 Trave-0.358
-0.354
 Surviv-0.352
Token tit
Token ID5259
Feature activation+8.09e-01

Pos logit contributions
rio+0.362
Ire+0.344
 Trave+0.311
+0.308
 Surviv+0.307
Neg logit contributions
Psych-0.258
issan-0.251
psych-0.230
Dex-0.227
 Psych-0.224
Tokenhes
Token ID956
Feature activation-2.11e+00

Pos logit contributions
Psych+0.597
issan+0.584
psych+0.545
Dex+0.539
 Psych+0.531
Neg logit contributions
rio-0.583
Ire-0.553
 Trave-0.490
-0.484
 Surviv-0.480
Token collected
Token ID7723
Feature activation+1.10e-01

Pos logit contributions
rio+1.712
Ire+1.617
 Trave+1.466
+1.444
 Surviv+1.427
Neg logit contributions
Psych-1.385
issan-1.353
psych-1.239
Dex-1.231
 Psych-1.200
Token by
Token ID416
Feature activation-1.32e-01

Pos logit contributions
Psych+0.070
issan+0.068
psych+0.062
Dex+0.062
 Psych+0.061
Neg logit contributions
rio-0.092
Ire-0.087
 Trave-0.079
-0.078
 Surviv-0.077
Token churches
Token ID14422
Feature activation-8.14e-02

Pos logit contributions
rio+0.110
Ire+0.105
 Trave+0.094
+0.094
 Surviv+0.093
Neg logit contributions
Psych-0.082
issan-0.080
psych-0.074
Dex-0.073
 Psych-0.072
Token in
Token ID287
Feature activation-1.86e-01

Pos logit contributions
rio+0.068
Ire+0.064
 Trave+0.058
+0.057
 Surviv+0.057
Neg logit contributions
Psych-0.052
issan-0.050
psych-0.046
Dex-0.046
 Psych-0.045
Token Brazil
Token ID7595
Feature activation-6.80e-01

Pos logit contributions
rio+0.152
Ire+0.144
 Trave+0.129
+0.128
 Surviv+0.127
Neg logit contributions
Psych-0.121
issan-0.118
psych-0.109
Dex-0.108
 Psych-0.106