TOP ACTIVATIONS
MAX = 2.381

2000 ), my biography of the great libertarian thinker , here
in our city and state for free . Any contribution to
this season , with Brian H oyer and Winston held under
Trump House committee believes it has evidence Trump requested putting ally
. See more Virtual Console games for Wii U . <|endoftext|>
Donald Trump Donald John Trump House committee believes it has evidence
O . J . Simpson : American Crime Story on Tuesday
2010 The Associated Press . All Rights Reserved . This material
best record , Caps coach Barry Tro tz reminded DC fans
Enemy of the State : The Life of Murray N .
Donald Trump Donald John Trump House committee believes it has evidence
Nation , check out our latest issue Subscribe now
by its Editorial Board , a dem ographically and ideologically diverse
Nations Educational , Scientific and Cultural Organisation ) designated Lake Ur
- off between Gu iller mo L asso and Lenin Moreno
MORE and Hillary Clinton Hillary Diane Rodham Clinton Sanders : '
Please turn on JavaScript . Media requires JavaScript to play .
President Trump Donald John Trump House committee believes it has evidence
The Life of Murray N . Roth bard ( Prom etheus
' I 'll make the large corporations pay ' fair share

MIN ACTIVATIONS
MIN = -2.756

and deep balls to Stef on D iggs .
their play enough . Brad en Holt by lacks the stamina
newspaper J yll ands - Post en in 2005 . It
30 . After I joined Pf izer Pharmaceutical s , and
. At G f inity 3 r ai N
You can check out my Twitter feed by going here .
seems the United States Conference of Catholic B ishops ( US
- econom ics - and - f inance , aust ral
PA K files in Win R AR , then tweak certain
per use . Here is the link for buying the second
3 , and could upset Na ` Vi in some universe
Fox Julia Louis - D rey f us Ve ep HBO
by cutting or restructuring Brand en Albert ($ 10 . 6
t . Franklin Del ano Roosevelt was credited as
go over some basic dos and don 't s , using
OP P European Politics and Policy or the London School
while CBS ' anchor Scott Pel ley is leading his network
E - mail this to a friend Print able version <|endoftext|>
Facebook St umble Upon What are these ?
Over the C uck oo 's Nest " -- two 1970

INTERVAL 1.097 - 2.381
CONTAINS 0.097%

an article published in N . Eng l . J .
League universities . Photo : Luis Sin co / Los Angeles
migrants 4 ways Hillary looms over the 2020 race Obama goes
handling ), Speed ( for Drag ster / Top Fuel levels
. Ser ious questions have been raised

INTERVAL -0.187 - 1.097
CONTAINS 78.942%

standard and is what investors will continue to watch , primarily
has commanded me to do . I am going
he pitched is a new ordinance that would prohibit sitting and
this idea that there s a love affair between
BIOS gives you an increased Power T une limit ( up

INTERVAL -1.472 - -0.187
CONTAINS 20.941%

of Peter and I having the conversation of " This guy
with his bl unders on the Hillary Clinton case reason enough
up in the A gap ( between the center and guard
our future vision to create stores which are carbon neutral ."
areas that don t necessarily have more people ,

INTERVAL -2.756 - -1.472
CONTAINS 0.019%

, which you might want to per use . Here is
30 . After I joined Pf izer Pharmaceutical s , and
position of EUR OP P European Politics and Policy or
seems the United States Conference of Catholic B ishops ( US
Lag oon , Dr J ek yll and Mr . Hyde
Token 2000
Token ID4751
Feature activation-2.87e-01

Pos logit contributions
ruff+0.107
erity+0.105
 jammed+0.103
 Tanz+0.102
itent+0.097
Neg logit contributions
xit-0.227
iac-0.197
cycles-0.197
cel-0.196
************-0.192
Token),
Token ID828
Feature activation-7.69e-01

Pos logit contributions
ruff+0.161
erity+0.158
 jammed+0.156
 Tanz+0.155
itent+0.148
Neg logit contributions
xit-0.225
iac-0.190
cycles-0.190
cel-0.189
************-0.184
Token my
Token ID616
Feature activation-1.00e+00

Pos logit contributions
ruff+0.465
erity+0.456
 jammed+0.453
 Tanz+0.448
itent+0.434
Neg logit contributions
xit-0.568
iac-0.477
cycles-0.476
cel-0.475
************-0.460
Token biography
Token ID26444
Feature activation+8.68e-01

Pos logit contributions
ruff+0.577
erity+0.569
 jammed+0.558
 Tanz+0.555
itent+0.536
Neg logit contributions
xit-0.768
iac-0.650
cel-0.648
cycles-0.646
************-0.626
Token of
Token ID286
Feature activation+1.38e+00

Pos logit contributions
xit+0.619
cycles+0.516
iac+0.516
cel+0.505
************+0.495
Neg logit contributions
ruff-0.546
erity-0.538
 jammed-0.531
 Tanz-0.528
 Danger-0.509
Token the
Token ID262
Feature activation+2.38e+00

Pos logit contributions
xit+1.008
iac+0.837
cycles+0.836
cel+0.818
************+0.806
Neg logit contributions
ruff-0.846
 jammed-0.823
erity-0.820
 Tanz-0.807
 Danger-0.787
Token great
Token ID1049
Feature activation+1.51e+00

Pos logit contributions
xit+1.208
cycles+0.947
iac+0.908
cel+0.894
soDeliveryDate+0.890
Neg logit contributions
ruff-1.977
 jammed-1.966
erity-1.949
 Tanz-1.944
 Danger-1.932
Token libertarian
Token ID19466
Feature activation+1.37e-02

Pos logit contributions
xit+0.792
cycles+0.614
iac+0.600
soDeliveryDate+0.580
cel+0.580
Neg logit contributions
ruff-1.247
 jammed-1.233
erity-1.220
 Tanz-1.219
 Danger-1.191
Token thinker
Token ID45206
Feature activation+1.83e-01

Pos logit contributions
xit+0.007
cycles+0.005
iac+0.005
cel+0.005
************+0.005
Neg logit contributions
ruff-0.012
erity-0.011
 jammed-0.011
 Tanz-0.011
itent-0.011
Token,
Token ID11
Feature activation+1.39e+00

Pos logit contributions
xit+0.131
cycles+0.108
iac+0.108
cel+0.107
************+0.105
Neg logit contributions
ruff-0.115
erity-0.113
 jammed-0.112
 Tanz-0.111
itent-0.107
Token here
Token ID994
Feature activation-4.18e-01

Pos logit contributions
xit+0.832
cycles+0.659
iac+0.656
cel+0.644
************+0.638
Neg logit contributions
ruff-1.034
 jammed-1.011
erity-1.006
 Tanz-1.002
 Danger-0.978
Token in
Token ID287
Feature activation+9.80e-02

Pos logit contributions
xit+0.593
cycles+0.494
iac+0.488
cel+0.484
************+0.473
Neg logit contributions
ruff-0.521
 jammed-0.507
erity-0.505
 Tanz-0.496
 Danger-0.486
Token our
Token ID674
Feature activation+1.23e+00

Pos logit contributions
xit+0.064
cycles+0.052
iac+0.052
cel+0.052
************+0.050
Neg logit contributions
ruff-0.068
erity-0.066
 jammed-0.066
 Tanz-0.065
itent-0.063
Token city
Token ID1748
Feature activation+4.20e-01

Pos logit contributions
xit+0.865
cycles+0.708
iac+0.700
cel+0.699
************+0.678
Neg logit contributions
ruff-0.800
 jammed-0.785
erity-0.783
 Tanz-0.766
itent-0.749
Token and
Token ID290
Feature activation+7.32e-01

Pos logit contributions
xit+0.308
cycles+0.255
iac+0.254
cel+0.252
************+0.247
Neg logit contributions
ruff-0.260
erity-0.253
 jammed-0.252
 Tanz-0.249
itent-0.241
Token state
Token ID1181
Feature activation-5.19e-01

Pos logit contributions
xit+0.507
cycles+0.415
iac+0.413
cel+0.411
************+0.402
Neg logit contributions
ruff-0.480
erity-0.470
 jammed-0.469
 Tanz-0.461
 Danger-0.447
Token for
Token ID329
Feature activation+2.27e+00

Pos logit contributions
ruff+0.342
erity+0.337
 jammed+0.334
 Tanz+0.332
itent+0.320
Neg logit contributions
xit-0.355
cycles-0.292
iac-0.292
cel-0.289
************-0.281
Token free
Token ID1479
Feature activation+1.47e+00

Pos logit contributions
xit+1.730
cycles+1.503
iac+1.453
cel+1.436
soDeliveryDate+1.427
Neg logit contributions
erity-1.300
 jammed-1.297
ruff-1.290
 Tanz-1.240
 Danger-1.233
Token.
Token ID13
Feature activation+6.59e-02

Pos logit contributions
xit+1.073
cycles+0.895
iac+0.883
cel+0.879
************+0.861
Neg logit contributions
ruff-0.899
erity-0.884
 jammed-0.884
 Tanz-0.857
itent-0.845
Token Any
Token ID4377
Feature activation+1.38e+00

Pos logit contributions
xit+0.041
cycles+0.033
iac+0.033
cel+0.033
************+0.032
Neg logit contributions
ruff-0.047
erity-0.047
 jammed-0.046
 Tanz-0.046
itent-0.044
Token contribution
Token ID10156
Feature activation+5.10e-01

Pos logit contributions
xit+0.743
cycles+0.580
iac+0.577
cel+0.557
soDeliveryDate+0.545
Neg logit contributions
ruff-1.113
erity-1.104
 jammed-1.085
 Tanz-1.070
 Danger-1.057
Token to
Token ID284
Feature activation+1.29e+00

Pos logit contributions
xit+0.356
cycles+0.293
iac+0.292
cel+0.290
************+0.282
Neg logit contributions
ruff-0.330
erity-0.324
 jammed-0.322
 Tanz-0.318
 Danger-0.308
Token this
Token ID428
Feature activation+8.85e-02

Pos logit contributions
xit+0.380
iac+0.311
cycles+0.311
cel+0.308
************+0.299
Neg logit contributions
ruff-0.373
 jammed-0.365
erity-0.365
 Tanz-0.359
itent-0.348
Token season
Token ID1622
Feature activation+8.50e-02

Pos logit contributions
xit+0.057
cycles+0.046
iac+0.046
cel+0.045
************+0.044
Neg logit contributions
ruff-0.062
erity-0.061
 jammed-0.061
 Tanz-0.060
itent-0.058
Token,
Token ID11
Feature activation+5.26e-02

Pos logit contributions
xit+0.060
cycles+0.049
iac+0.049
cel+0.049
************+0.048
Neg logit contributions
ruff-0.054
erity-0.053
 jammed-0.053
 Tanz-0.052
itent-0.051
Token with
Token ID351
Feature activation+2.20e-01

Pos logit contributions
xit+0.039
iac+0.032
cycles+0.032
cel+0.032
************+0.031
Neg logit contributions
ruff-0.032
erity-0.031
 jammed-0.031
 Tanz-0.031
itent-0.030
Token Brian
Token ID8403
Feature activation+1.63e-01

Pos logit contributions
xit+0.151
iac+0.123
cycles+0.123
cel+0.122
************+0.119
Neg logit contributions
ruff-0.146
erity-0.143
 jammed-0.142
 Tanz-0.141
 Danger-0.136
Token H
Token ID367
Feature activation+2.26e+00

Pos logit contributions
xit+0.104
cycles+0.083
iac+0.083
cel+0.082
************+0.080
Neg logit contributions
ruff-0.116
erity-0.114
 jammed-0.113
 Tanz-0.112
itent-0.109
Tokenoyer
Token ID35301
Feature activation+7.78e-02

Pos logit contributions
xit+1.800
cycles+1.521
soDeliveryDate+1.505
iac+1.489
cel+1.480
Neg logit contributions
ruff-1.271
erity-1.203
 jammed-1.179
 Tanz-1.166
ifle-1.159
Token and
Token ID290
Feature activation+4.66e-01

Pos logit contributions
xit+0.057
cycles+0.048
iac+0.048
cel+0.047
************+0.046
Neg logit contributions
ruff-0.048
erity-0.047
 jammed-0.046
 Tanz-0.046
itent-0.044
Token Winston
Token ID21400
Feature activation-3.80e-02

Pos logit contributions
xit+0.324
iac+0.266
cycles+0.266
cel+0.262
************+0.256
Neg logit contributions
ruff-0.305
erity-0.298
 jammed-0.297
 Tanz-0.294
 Danger-0.284
Token held
Token ID2714
Feature activation+5.03e-01

Pos logit contributions
ruff+0.023
erity+0.022
 jammed+0.022
 Tanz+0.022
itent+0.021
Neg logit contributions
xit-0.028
iac-0.024
cycles-0.024
cel-0.023
************-0.023
Token under
Token ID739
Feature activation+3.55e-01

Pos logit contributions
xit+0.353
cycles+0.290
iac+0.290
cel+0.287
************+0.280
Neg logit contributions
ruff-0.325
 jammed-0.318
erity-0.318
 Tanz-0.313
itent-0.303
Token Trump
Token ID1301
Feature activation-7.86e-02

Pos logit contributions
xit+0.209
cycles+0.157
iac+0.157
cel+0.155
************+0.148
Neg logit contributions
ruff-0.351
erity-0.345
 jammed-0.344
 Tanz-0.341
 Danger-0.333
TokenHouse
Token ID18102
Feature activation+2.12e+00

Pos logit contributions
ruff+0.055
erity+0.054
 jammed+0.053
 Tanz+0.053
itent+0.051
Neg logit contributions
xit-0.051
iac-0.041
cycles-0.041
cel-0.041
************-0.040
Token committee
Token ID5583
Feature activation+7.40e-01

Pos logit contributions
xit+1.550
iac+1.310
cycles+1.294
************+1.267
cel+1.259
Neg logit contributions
ruff-1.293
erity-1.293
 jammed-1.275
 Danger-1.246
 Tanz-1.240
Token believes
Token ID5804
Feature activation+6.13e-01

Pos logit contributions
xit+0.668
iac+0.580
cycles+0.577
cel+0.574
************+0.560
Neg logit contributions
ruff-0.327
erity-0.318
 jammed-0.316
 Tanz-0.308
 Danger-0.295
Token it
Token ID340
Feature activation-1.19e+00

Pos logit contributions
xit+0.399
cycles+0.324
iac+0.323
cel+0.320
************+0.312
Neg logit contributions
ruff-0.424
erity-0.418
 jammed-0.416
 Tanz-0.409
 Danger-0.400
Token has
Token ID468
Feature activation+2.14e+00

Pos logit contributions
ruff+0.761
erity+0.746
 Tanz+0.744
 jammed+0.730
itent+0.704
Neg logit contributions
xit-0.853
iac-0.700
cycles-0.699
cel-0.693
 anim-0.677
Token evidence
Token ID2370
Feature activation-2.52e-01

Pos logit contributions
xit+1.341
cycles+1.083
cel+1.074
iac+1.066
soDeliveryDate+1.049
Neg logit contributions
 jammed-1.556
ruff-1.514
erity-1.511
 Tanz-1.466
 Danger-1.463
Token Trump
Token ID1301
Feature activation-9.49e-02

Pos logit contributions
ruff+0.170
erity+0.167
 jammed+0.166
 Tanz+0.165
itent+0.159
Neg logit contributions
xit-0.169
iac-0.138
cycles-0.138
cel-0.137
************-0.133
Token requested
Token ID9167
Feature activation+1.06e+00

Pos logit contributions
ruff+0.060
erity+0.059
 jammed+0.058
 Tanz+0.058
itent+0.056
Neg logit contributions
xit-0.068
iac-0.056
cycles-0.056
cel-0.056
************-0.054
Token putting
Token ID5137
Feature activation+2.69e-01

Pos logit contributions
xit+0.795
cycles+0.667
iac+0.656
cel+0.648
soDeliveryDate+0.640
Neg logit contributions
ruff-0.641
 jammed-0.628
erity-0.626
 Tanz-0.616
 Danger-0.595
Token ally
Token ID12525
Feature activation-4.44e-02

Pos logit contributions
xit+0.194
cycles+0.161
iac+0.160
cel+0.159
************+0.155
Neg logit contributions
ruff-0.168
erity-0.164
 jammed-0.164
 Tanz-0.162
itent-0.156
Token.
Token ID13
Feature activation+1.77e-01

Pos logit contributions
ruff+0.233
erity+0.229
 jammed+0.227
 Tanz+0.225
itent+0.217
Neg logit contributions
xit-0.246
iac-0.202
cycles-0.202
cel-0.200
************-0.195
Token See
Token ID4091
Feature activation+6.22e-01

Pos logit contributions
xit+0.115
cycles+0.094
iac+0.093
cel+0.093
************+0.090
Neg logit contributions
ruff-0.122
erity-0.120
 jammed-0.119
 Tanz-0.118
itent-0.114
Token more
Token ID517
Feature activation+1.57e+00

Pos logit contributions
xit+0.454
iac+0.380
cycles+0.377
cel+0.374
soDeliveryDate+0.364
Neg logit contributions
ruff-0.384
 jammed-0.374
erity-0.374
 Tanz-0.369
 Danger-0.357
Token Virtual
Token ID15595
Feature activation-2.86e-01

Pos logit contributions
xit+1.090
iac+0.888
cycles+0.881
soDeliveryDate+0.863
cel+0.863
Neg logit contributions
ruff-1.036
 jammed-1.015
 Tanz-1.004
erity-1.004
 Danger-0.971
Token Console
Token ID24371
Feature activation-1.04e+00

Pos logit contributions
ruff+0.185
erity+0.182
 jammed+0.180
 Tanz+0.179
itent+0.173
Neg logit contributions
xit-0.200
iac-0.165
cycles-0.164
cel-0.163
************-0.159
Token games
Token ID1830
Feature activation+2.13e+00

Pos logit contributions
ruff+0.841
erity+0.828
 jammed+0.817
 Tanz+0.813
itent+0.793
Neg logit contributions
xit-0.560
iac-0.440
cycles-0.437
cel-0.432
************-0.418
Token for
Token ID329
Feature activation+1.15e+00

Pos logit contributions
xit+1.586
cycles+1.346
cel+1.314
iac+1.312
soDeliveryDate+1.306
Neg logit contributions
ruff-1.287
 jammed-1.276
erity-1.247
 Tanz-1.229
 Danger-1.194
Token Wii
Token ID16591
Feature activation-3.00e-01

Pos logit contributions
xit+0.619
cycles+0.472
iac+0.467
cel+0.466
soDeliveryDate+0.451
Neg logit contributions
ruff-0.932
 jammed-0.920
erity-0.907
 Tanz-0.906
itent-0.880
Token U
Token ID471
Feature activation+8.73e-01

Pos logit contributions
ruff+0.200
erity+0.196
 jammed+0.195
 Tanz+0.193
itent+0.187
Neg logit contributions
xit-0.203
cycles-0.167
iac-0.166
cel-0.165
************-0.160
Token.
Token ID13
Feature activation+2.45e-01

Pos logit contributions
xit+0.617
cycles+0.507
iac+0.506
cel+0.501
soDeliveryDate+0.489
Neg logit contributions
ruff-0.558
erity-0.547
 jammed-0.545
 Tanz-0.540
itent-0.521
Token<|endoftext|>
Token ID50256
Feature activation-2.20e-01

Pos logit contributions
xit+0.196
cycles+0.166
iac+0.165
cel+0.164
************+0.160
Neg logit contributions
ruff-0.134
erity-0.131
 jammed-0.130
 Tanz-0.129
 Danger-0.124
Token Donald
Token ID3759
Feature activation-1.22e-01

Pos logit contributions
xit+0.092
cycles+0.076
iac+0.076
cel+0.075
************+0.073
Neg logit contributions
ruff-0.087
erity-0.086
 jammed-0.085
 Tanz-0.084
itent-0.081
Token Trump
Token ID1301
Feature activation+1.75e-01

Pos logit contributions
ruff+0.104
erity+0.102
 jammed+0.102
 Tanz+0.101
itent+0.098
Neg logit contributions
xit-0.061
iac-0.046
cycles-0.046
cel-0.045
************-0.043
Token Donald
Token ID3759
Feature activation-4.14e-01

Pos logit contributions
xit+0.126
cycles+0.105
iac+0.104
cel+0.103
************+0.101
Neg logit contributions
ruff-0.110
erity-0.108
 jammed-0.107
 Tanz-0.106
itent-0.102
Token John
Token ID1757
Feature activation+4.15e-01

Pos logit contributions
ruff+0.294
erity+0.289
 jammed+0.286
 Tanz+0.284
itent+0.275
Neg logit contributions
xit-0.263
iac-0.213
cycles-0.213
cel-0.210
************-0.204
Token Trump
Token ID1301
Feature activation-7.86e-02

Pos logit contributions
xit+0.209
cycles+0.157
iac+0.157
cel+0.155
************+0.148
Neg logit contributions
ruff-0.351
erity-0.345
 jammed-0.344
 Tanz-0.341
 Danger-0.333
TokenHouse
Token ID18102
Feature activation+2.12e+00

Pos logit contributions
ruff+0.055
erity+0.054
 jammed+0.053
 Tanz+0.053
itent+0.051
Neg logit contributions
xit-0.051
iac-0.041
cycles-0.041
cel-0.041
************-0.040
Token committee
Token ID5583
Feature activation+7.40e-01

Pos logit contributions
xit+1.550
iac+1.310
cycles+1.294
************+1.267
cel+1.259
Neg logit contributions
ruff-1.293
erity-1.293
 jammed-1.275
 Danger-1.246
 Tanz-1.240
Token believes
Token ID5804
Feature activation+6.13e-01

Pos logit contributions
xit+0.668
iac+0.580
cycles+0.577
cel+0.574
************+0.560
Neg logit contributions
ruff-0.327
erity-0.318
 jammed-0.316
 Tanz-0.308
 Danger-0.295
Token it
Token ID340
Feature activation-1.19e+00

Pos logit contributions
xit+0.399
cycles+0.324
iac+0.323
cel+0.320
************+0.312
Neg logit contributions
ruff-0.424
erity-0.418
 jammed-0.416
 Tanz-0.409
 Danger-0.400
Token has
Token ID468
Feature activation+2.14e+00

Pos logit contributions
ruff+0.761
erity+0.746
 Tanz+0.744
 jammed+0.730
itent+0.704
Neg logit contributions
xit-0.853
iac-0.700
cycles-0.699
cel-0.693
 anim-0.677
Token evidence
Token ID2370
Feature activation-2.52e-01

Pos logit contributions
xit+1.341
cycles+1.083
cel+1.074
iac+1.066
soDeliveryDate+1.049
Neg logit contributions
 jammed-1.556
ruff-1.514
erity-1.511
 Tanz-1.466
 Danger-1.463
Token O
Token ID440
Feature activation+6.84e-01

Pos logit contributions
xit+0.562
cycles+0.461
iac+0.460
cel+0.455
************+0.442
Neg logit contributions
ruff-0.551
erity-0.540
 Tanz-0.535
 jammed-0.534
 Danger-0.515
Token.
Token ID13
Feature activation+9.00e-01

Pos logit contributions
xit+0.498
cycles+0.415
iac+0.414
cel+0.408
************+0.402
Neg logit contributions
ruff-0.422
erity-0.412
 jammed-0.409
 Tanz-0.404
itent-0.390
TokenJ
Token ID41
Feature activation+1.07e-01

Pos logit contributions
xit+0.745
cycles+0.638
iac+0.635
cel+0.626
************+0.618
Neg logit contributions
ruff-0.468
erity-0.454
 jammed-0.448
 Tanz-0.447
 Danger-0.427
Token.
Token ID13
Feature activation+6.47e-01

Pos logit contributions
xit+0.075
cycles+0.061
iac+0.061
cel+0.061
************+0.059
Neg logit contributions
ruff-0.069
erity-0.068
 jammed-0.067
 Tanz-0.067
itent-0.064
Token Simpson
Token ID20531
Feature activation+8.11e-01

Pos logit contributions
xit+0.396
cycles+0.317
iac+0.315
cel+0.311
************+0.302
Neg logit contributions
ruff-0.475
erity-0.468
 jammed-0.464
 Tanz-0.462
 Danger-0.447
Token:
Token ID25
Feature activation+2.11e+00

Pos logit contributions
xit+0.600
cycles+0.499
iac+0.495
cel+0.492
************+0.479
Neg logit contributions
ruff-0.494
erity-0.485
 jammed-0.482
 Tanz-0.477
 Danger-0.460
Token American
Token ID1605
Feature activation+1.01e+00

Pos logit contributions
xit+1.304
cycles+1.019
iac+1.018
cel+1.005
soDeliveryDate+0.970
Neg logit contributions
ruff-1.554
erity-1.547
 jammed-1.527
 Tanz-1.519
 Danger-1.490
Token Crime
Token ID10003
Feature activation-5.61e-01

Pos logit contributions
xit+0.797
cycles+0.672
iac+0.670
cel+0.666
************+0.649
Neg logit contributions
ruff-0.553
erity-0.545
 jammed-0.539
 Tanz-0.535
 Danger-0.517
Token Story
Token ID8362
Feature activation+3.69e-01

Pos logit contributions
ruff+0.329
erity+0.323
 jammed+0.319
 Tanz+0.316
itent+0.304
Neg logit contributions
xit-0.426
iac-0.358
cycles-0.357
cel-0.355
************-0.346
Token on
Token ID319
Feature activation+7.75e-02

Pos logit contributions
xit+0.266
cycles+0.220
iac+0.220
cel+0.218
************+0.212
Neg logit contributions
ruff-0.231
erity-0.226
 jammed-0.225
 Tanz-0.222
 Danger-0.214
Token Tuesday
Token ID3431
Feature activation-7.11e-02

Pos logit contributions
xit+0.057
cycles+0.047
iac+0.047
cel+0.047
************+0.046
Neg logit contributions
ruff-0.048
erity-0.047
 jammed-0.046
 Tanz-0.046
itent-0.044
Token 2010
Token ID3050
Feature activation+4.68e-01

Pos logit contributions
xit+0.056
cycles+0.048
iac+0.048
cel+0.047
************+0.046
Neg logit contributions
ruff-0.038
erity-0.037
 jammed-0.037
 Tanz-0.036
itent-0.035
Token The
Token ID383
Feature activation+2.46e-01

Pos logit contributions
xit+0.355
cycles+0.297
iac+0.296
cel+0.295
************+0.287
Neg logit contributions
ruff-0.274
erity-0.269
 jammed-0.266
 Tanz-0.264
 Danger-0.254
Token Associated
Token ID10575
Feature activation-1.97e-01

Pos logit contributions
xit+0.196
cycles+0.166
iac+0.165
cel+0.164
************+0.160
Neg logit contributions
ruff-0.135
erity-0.132
 jammed-0.131
 Tanz-0.130
itent-0.124
Token Press
Token ID4332
Feature activation-5.33e-01

Pos logit contributions
ruff+0.174
erity+0.171
 jammed+0.170
 Tanz+0.169
itent+0.165
Neg logit contributions
xit-0.092
iac-0.067
cycles-0.067
cel-0.066
************-0.063
Token.
Token ID13
Feature activation+8.75e-01

Pos logit contributions
ruff+0.349
erity+0.342
 jammed+0.340
 Tanz+0.338
itent+0.325
Neg logit contributions
xit-0.368
iac-0.304
cycles-0.303
cel-0.300
************-0.292
Token All
Token ID1439
Feature activation+2.11e+00

Pos logit contributions
xit+0.656
cycles+0.548
iac+0.545
cel+0.543
************+0.526
Neg logit contributions
ruff-0.523
erity-0.512
 Tanz-0.503
 jammed-0.503
 Danger-0.488
Token Rights
Token ID6923
Feature activation+2.71e-01

Pos logit contributions
xit+1.255
cel+0.966
cycles+0.965
iac+0.952
soDeliveryDate+0.939
Neg logit contributions
ruff-1.618
erity-1.582
 jammed-1.569
 Tanz-1.553
 Danger-1.534
Token Reserved
Token ID33876
Feature activation+3.60e-01

Pos logit contributions
xit+0.186
cycles+0.152
iac+0.152
cel+0.150
************+0.146
Neg logit contributions
ruff-0.180
erity-0.176
 jammed-0.174
 Tanz-0.173
 Danger-0.167
Token.
Token ID13
Feature activation+1.56e+00

Pos logit contributions
xit+0.255
cycles+0.210
iac+0.209
cel+0.208
************+0.202
Neg logit contributions
ruff-0.230
erity-0.225
 jammed-0.223
 Tanz-0.221
 Danger-0.214
Token This
Token ID770
Feature activation+9.64e-01

Pos logit contributions
xit+1.215
cycles+1.025
cel+1.016
iac+1.014
soDeliveryDate+0.989
Neg logit contributions
ruff-0.884
erity-0.867
 Tanz-0.851
 jammed-0.848
 Danger-0.832
Token material
Token ID2587
Feature activation+6.06e-01

Pos logit contributions
xit+0.648
cycles+0.529
iac+0.524
cel+0.522
************+0.506
Neg logit contributions
ruff-0.655
 jammed-0.638
erity-0.637
 Tanz-0.628
 Danger-0.611
Token best
Token ID1266
Feature activation-3.09e-01

Pos logit contributions
ruff+0.181
erity+0.177
 jammed+0.176
 Tanz+0.175
itent+0.168
Neg logit contributions
xit-0.213
iac-0.177
cycles-0.177
cel-0.175
************-0.171
Token record
Token ID1700
Feature activation+1.68e-01

Pos logit contributions
ruff+0.190
erity+0.186
 jammed+0.184
 Tanz+0.183
itent+0.176
Neg logit contributions
xit-0.227
iac-0.189
cycles-0.188
cel-0.187
************-0.182
Token,
Token ID11
Feature activation-4.23e-01

Pos logit contributions
xit+0.118
cycles+0.097
iac+0.097
cel+0.097
************+0.094
Neg logit contributions
ruff-0.107
erity-0.105
 jammed-0.105
 Tanz-0.103
itent-0.100
Token Caps
Token ID23534
Feature activation-1.15e-02

Pos logit contributions
ruff+0.271
erity+0.266
 jammed+0.264
 Tanz+0.262
itent+0.252
Neg logit contributions
xit-0.298
iac-0.246
cycles-0.245
cel-0.243
************-0.237
Token coach
Token ID3985
Feature activation+4.46e-01

Pos logit contributions
ruff+0.008
erity+0.007
 jammed+0.007
 Tanz+0.007
itent+0.007
Neg logit contributions
xit-0.008
cycles-0.007
iac-0.007
cel-0.007
************-0.006
Token Barry
Token ID14488
Feature activation+2.09e+00

Pos logit contributions
xit+0.288
iac+0.232
cycles+0.232
cel+0.229
************+0.223
Neg logit contributions
ruff-0.313
erity-0.307
 jammed-0.306
 Tanz-0.303
 Danger-0.293
Token Tro
Token ID8498
Feature activation-5.78e-01

Pos logit contributions
xit+1.887
iac+1.632
cycles+1.629
************+1.607
cel+1.604
Neg logit contributions
ruff-0.959
 jammed-0.904
erity-0.899
 Tanz-0.897
 Danger-0.870
Tokentz
Token ID22877
Feature activation-1.72e-01

Pos logit contributions
ruff+0.264
erity+0.257
 jammed+0.256
 Tanz+0.254
itent+0.240
Neg logit contributions
xit-0.514
iac-0.443
cycles-0.442
cel-0.439
************-0.429
Token reminded
Token ID14516
Feature activation+3.33e-02

Pos logit contributions
ruff+0.111
erity+0.109
 jammed+0.108
 Tanz+0.107
itent+0.104
Neg logit contributions
xit-0.121
iac-0.099
cycles-0.099
cel-0.098
************-0.096
Token DC
Token ID6257
Feature activation+1.09e-01

Pos logit contributions
xit+0.023
cycles+0.019
iac+0.019
cel+0.019
************+0.019
Neg logit contributions
ruff-0.022
erity-0.021
 jammed-0.021
 Tanz-0.021
itent-0.020
Token fans
Token ID3296
Feature activation+8.30e-02

Pos logit contributions
xit+0.076
cycles+0.062
iac+0.062
cel+0.062
************+0.060
Neg logit contributions
ruff-0.071
erity-0.070
 jammed-0.070
 Tanz-0.069
itent-0.067
Token Enemy
Token ID21785
Feature activation+2.38e-01

Pos logit contributions
xit+0.663
cycles+0.517
iac+0.508
cel+0.498
************+0.491
Neg logit contributions
ruff-0.910
erity-0.888
 jammed-0.886
 Tanz-0.882
 Danger-0.859
Token of
Token ID286
Feature activation+8.01e-01

Pos logit contributions
xit+0.167
cycles+0.137
iac+0.137
cel+0.136
************+0.133
Neg logit contributions
ruff-0.154
erity-0.150
 jammed-0.149
 Tanz-0.148
 Danger-0.143
Token the
Token ID262
Feature activation+8.17e-01

Pos logit contributions
xit+0.573
cycles+0.473
iac+0.471
cel+0.469
************+0.456
Neg logit contributions
ruff-0.506
erity-0.495
 jammed-0.492
 Tanz-0.486
 Danger-0.473
Token State
Token ID1812
Feature activation+1.66e-01

Pos logit contributions
xit+0.594
cycles+0.496
iac+0.491
cel+0.490
************+0.478
Neg logit contributions
ruff-0.503
erity-0.491
 jammed-0.488
 Tanz-0.487
 Danger-0.469
Token:
Token ID25
Feature activation+1.63e+00

Pos logit contributions
xit+0.122
cycles+0.101
iac+0.101
cel+0.100
************+0.097
Neg logit contributions
ruff-0.103
erity-0.101
 jammed-0.100
 Tanz-0.099
 Danger-0.095
Token The
Token ID383
Feature activation+2.09e+00

Pos logit contributions
xit+1.397
iac+1.209
cel+1.187
cycles+1.181
soDeliveryDate+1.170
Neg logit contributions
ruff-0.783
erity-0.781
 Tanz-0.763
 jammed-0.762
 Danger-0.739
Token Life
Token ID5155
Feature activation+4.64e-01

Pos logit contributions
xit+1.154
soDeliveryDate+0.885
iac+0.885
cycles+0.872
cel+0.861
Neg logit contributions
ruff-1.646
erity-1.646
 jammed-1.623
 Tanz-1.614
 Danger-1.612
Token of
Token ID286
Feature activation+8.99e-01

Pos logit contributions
xit+0.329
cycles+0.270
iac+0.269
cel+0.268
************+0.261
Neg logit contributions
ruff-0.296
erity-0.291
 jammed-0.288
 Tanz-0.285
 Danger-0.276
Token Murray
Token ID12164
Feature activation+1.23e+00

Pos logit contributions
xit+0.393
cycles+0.281
iac+0.276
cel+0.273
soDeliveryDate+0.261
Neg logit contributions
ruff-0.817
erity-0.808
 jammed-0.803
 Tanz-0.799
 Danger-0.782
Token N
Token ID399
Feature activation+1.60e+00

Pos logit contributions
xit+0.935
cycles+0.780
iac+0.776
cel+0.775
************+0.757
Neg logit contributions
ruff-0.728
 jammed-0.707
erity-0.702
 Tanz-0.699
 Danger-0.685
Token.
Token ID13
Feature activation+1.94e+00

Pos logit contributions
xit+1.193
cycles+0.989
cel+0.973
iac+0.972
soDeliveryDate+0.953
Neg logit contributions
ruff-0.986
 jammed-0.949
erity-0.936
 Tanz-0.929
itent-0.905
Token Donald
Token ID3759
Feature activation+9.87e-02

Pos logit contributions
xit+0.502
cycles+0.403
iac+0.403
cel+0.401
************+0.388
Neg logit contributions
ruff-0.564
 jammed-0.553
erity-0.552
 Tanz-0.546
 Danger-0.530
Token Trump
Token ID1301
Feature activation+3.93e-01

Pos logit contributions
xit+0.049
cycles+0.037
iac+0.037
cel+0.036
************+0.035
Neg logit contributions
ruff-0.084
erity-0.083
 jammed-0.082
 Tanz-0.082
 Danger-0.079
Token Donald
Token ID3759
Feature activation-5.64e-02

Pos logit contributions
xit+0.246
cycles+0.198
iac+0.197
cel+0.195
************+0.189
Neg logit contributions
ruff-0.283
erity-0.277
 jammed-0.277
 Tanz-0.274
itent-0.266
Token John
Token ID1757
Feature activation+2.77e-01

Pos logit contributions
ruff+0.040
erity+0.039
 jammed+0.039
 Tanz+0.038
itent+0.037
Neg logit contributions
xit-0.036
iac-0.029
cycles-0.029
cel-0.029
************-0.028
Token Trump
Token ID1301
Feature activation-5.00e-02

Pos logit contributions
xit+0.138
cycles+0.104
iac+0.104
cel+0.102
************+0.098
Neg logit contributions
ruff-0.235
erity-0.231
 jammed-0.230
 Tanz-0.228
itent-0.222
TokenHouse
Token ID18102
Feature activation+2.08e+00

Pos logit contributions
ruff+0.035
erity+0.034
 jammed+0.034
 Tanz+0.034
itent+0.033
Neg logit contributions
xit-0.032
iac-0.026
cycles-0.026
cel-0.026
************-0.025
Token committee
Token ID5583
Feature activation+4.64e-01

Pos logit contributions
xit+1.541
iac+1.302
cycles+1.282
************+1.257
cel+1.246
Neg logit contributions
ruff-1.260
erity-1.255
 jammed-1.240
 Danger-1.209
 Tanz-1.202
Token believes
Token ID5804
Feature activation+5.90e-01

Pos logit contributions
xit+0.417
iac+0.360
cycles+0.359
cel+0.357
************+0.349
Neg logit contributions
ruff-0.207
erity-0.202
 jammed-0.201
 Tanz-0.196
 Danger-0.187
Token it
Token ID340
Feature activation-9.50e-01

Pos logit contributions
xit+0.335
iac+0.261
cycles+0.261
cel+0.258
************+0.250
Neg logit contributions
ruff-0.458
erity-0.452
 jammed-0.451
 Tanz-0.444
 Danger-0.434
Token has
Token ID468
Feature activation+1.90e+00

Pos logit contributions
ruff+0.582
erity+0.570
 Tanz+0.568
 jammed+0.560
itent+0.539
Neg logit contributions
xit-0.698
iac-0.578
cycles-0.578
cel-0.573
************-0.558
Token evidence
Token ID2370
Feature activation-2.37e-01

Pos logit contributions
xit+1.182
cycles+0.945
cel+0.943
iac+0.940
soDeliveryDate+0.905
Neg logit contributions
 jammed-1.380
ruff-1.356
erity-1.346
 Tanz-1.307
 Danger-1.302
Token Nation
Token ID8741
Feature activation+9.14e-01

Pos logit contributions
xit+0.291
cycles+0.236
iac+0.236
cel+0.234
************+0.227
Neg logit contributions
ruff-0.307
erity-0.300
 jammed-0.299
 Tanz-0.297
 Danger-0.287
Token,
Token ID11
Feature activation+6.35e-01

Pos logit contributions
xit+0.669
cycles+0.558
iac+0.554
cel+0.549
************+0.535
Neg logit contributions
ruff-0.564
erity-0.550
 jammed-0.545
 Tanz-0.538
itent-0.525
Token check
Token ID2198
Feature activation+6.85e-01

Pos logit contributions
xit+0.477
cycles+0.400
iac+0.393
cel+0.393
************+0.384
Neg logit contributions
ruff-0.381
erity-0.373
 jammed-0.369
 Tanz-0.363
itent-0.351
Token out
Token ID503
Feature activation+1.46e+00

Pos logit contributions
xit+0.521
cycles+0.437
iac+0.436
cel+0.431
************+0.422
Neg logit contributions
ruff-0.402
erity-0.393
 jammed-0.390
 Tanz-0.382
itent-0.370
Token our
Token ID674
Feature activation+1.37e+00

Pos logit contributions
xit+0.997
cycles+0.822
iac+0.817
cel+0.807
************+0.793
Neg logit contributions
ruff-0.964
 jammed-0.944
erity-0.940
 Tanz-0.925
 Danger-0.904
Token latest
Token ID3452
Feature activation+2.08e+00

Pos logit contributions
xit+0.853
cycles+0.692
iac+0.678
cel+0.671
************+0.654
Neg logit contributions
ruff-1.010
 jammed-0.985
erity-0.978
 Tanz-0.969
 Danger-0.942
Token issue
Token ID2071
Feature activation-6.42e-01

Pos logit contributions
xit+1.306
cycles+1.051
iac+1.045
cel+1.033
************+1.011
Neg logit contributions
ruff-1.501
erity-1.484
 jammed-1.480
 Tanz-1.452
 Danger-1.420
Token
Token ID198
Feature activation-1.36e-01

Pos logit contributions
ruff+0.402
erity+0.394
 jammed+0.392
 Tanz+0.389
itent+0.375
Neg logit contributions
xit-0.461
iac-0.383
cycles-0.381
cel-0.379
************-0.369
Token
Token ID198
Feature activation-2.75e-02

Pos logit contributions
ruff+0.084
erity+0.082
 jammed+0.082
 Tanz+0.081
itent+0.078
Neg logit contributions
xit-0.099
iac-0.082
cycles-0.082
cel-0.082
************-0.080
TokenSubscribe
Token ID27125
Feature activation+1.38e-01

Pos logit contributions
ruff+0.018
erity+0.018
 jammed+0.018
 Tanz+0.018
itent+0.017
Neg logit contributions
xit-0.019
iac-0.015
cycles-0.015
cel-0.015
************-0.015
Token now
Token ID783
Feature activation+2.33e-01

Pos logit contributions
xit+0.107
cycles+0.090
iac+0.090
cel+0.089
************+0.087
Neg logit contributions
ruff-0.079
erity-0.077
 jammed-0.076
 Tanz-0.075
itent-0.072
Token by
Token ID416
Feature activation+7.38e-01

Pos logit contributions
ruff+0.056
erity+0.055
 jammed+0.055
 Tanz+0.054
itent+0.053
Neg logit contributions
xit-0.062
iac-0.051
cycles-0.051
cel-0.050
************-0.049
Token its
Token ID663
Feature activation+6.19e-01

Pos logit contributions
xit+0.547
iac+0.453
cycles+0.450
cel+0.448
************+0.437
Neg logit contributions
ruff-0.450
 jammed-0.439
erity-0.439
 Tanz-0.432
itent-0.418
Token Editorial
Token ID39525
Feature activation-5.50e-01

Pos logit contributions
xit+0.523
cycles+0.446
iac+0.443
cel+0.441
************+0.432
Neg logit contributions
ruff-0.313
erity-0.306
 jammed-0.303
 Tanz-0.299
 Danger-0.286
Token Board
Token ID5926
Feature activation-1.48e+00

Pos logit contributions
ruff+0.355
erity+0.348
 jammed+0.344
 Tanz+0.342
itent+0.332
Neg logit contributions
xit-0.384
cycles-0.318
iac-0.318
cel-0.315
************-0.305
Token,
Token ID11
Feature activation+3.52e-01

Pos logit contributions
ruff+0.984
 jammed+0.966
erity+0.966
 Tanz+0.962
itent+0.924
Neg logit contributions
xit-0.996
iac-0.822
cycles-0.819
cel-0.813
 anim-0.792
Token a
Token ID257
Feature activation+2.05e+00

Pos logit contributions
xit+0.307
iac+0.264
cycles+0.264
cel+0.262
************+0.256
Neg logit contributions
ruff-0.167
erity-0.161
 jammed-0.161
 Tanz-0.159
itent-0.151
Token dem
Token ID1357
Feature activation-7.77e-01

Pos logit contributions
xit+1.480
cycles+1.217
iac+1.213
cel+1.199
************+1.162
Neg logit contributions
ruff-1.305
 jammed-1.276
erity-1.276
 Tanz-1.266
 Danger-1.237
Tokenographically
Token ID33145
Feature activation+5.30e-01

Pos logit contributions
ruff+0.481
 jammed+0.472
erity+0.471
 Tanz+0.465
 Danger+0.449
Neg logit contributions
xit-0.559
iac-0.470
cycles-0.465
cel-0.464
************-0.451
Token and
Token ID290
Feature activation-1.74e-02

Pos logit contributions
xit+0.348
cycles+0.282
iac+0.281
cel+0.279
************+0.270
Neg logit contributions
ruff-0.368
erity-0.360
 jammed-0.359
 Tanz-0.355
itent-0.343
Token ideologically
Token ID49764
Feature activation+8.15e-01

Pos logit contributions
ruff+0.010
erity+0.010
 jammed+0.010
 Tanz+0.009
itent+0.009
Neg logit contributions
xit-0.014
iac-0.011
cycles-0.011
cel-0.011
************-0.011
Token diverse
Token ID10084
Feature activation+9.17e-01

Pos logit contributions
xit+0.549
cycles+0.448
iac+0.447
cel+0.442
************+0.430
Neg logit contributions
ruff-0.552
 jammed-0.537
erity-0.536
 Tanz-0.532
itent-0.512
Token Nations
Token ID7973
Feature activation+5.74e-01

Pos logit contributions
xit+0.104
cycles+0.085
iac+0.085
cel+0.084
************+0.082
Neg logit contributions
ruff-0.107
erity-0.105
 jammed-0.104
 Tanz-0.104
itent-0.100
Token Educational
Token ID30038
Feature activation+9.09e-02

Pos logit contributions
xit+0.381
cycles+0.309
iac+0.308
cel+0.305
************+0.296
Neg logit contributions
ruff-0.393
erity-0.386
 jammed-0.385
 Tanz-0.381
 Danger-0.368
Token,
Token ID11
Feature activation+1.27e+00

Pos logit contributions
xit+0.065
iac+0.054
cycles+0.054
cel+0.053
************+0.052
Neg logit contributions
ruff-0.058
erity-0.056
 jammed-0.056
 Tanz-0.055
itent-0.053
Token Scientific
Token ID22060
Feature activation+5.64e-01

Pos logit contributions
xit+0.578
cycles+0.413
iac+0.410
cel+0.402
soDeliveryDate+0.395
Neg logit contributions
ruff-1.142
erity-1.132
 jammed-1.128
 Tanz-1.124
 Danger-1.093
Token and
Token ID290
Feature activation+4.07e-01

Pos logit contributions
xit+0.413
iac+0.342
cycles+0.342
cel+0.338
************+0.330
Neg logit contributions
ruff-0.349
erity-0.342
 jammed-0.338
 Tanz-0.336
itent-0.323
Token Cultural
Token ID23897
Feature activation+2.02e+00

Pos logit contributions
xit+0.286
cycles+0.235
iac+0.235
cel+0.232
************+0.226
Neg logit contributions
ruff-0.263
erity-0.258
 jammed-0.257
 Tanz-0.255
itent-0.246
Token Organisation
Token ID30801
Feature activation+1.21e-01

Pos logit contributions
xit+1.627
iac+1.396
cycles+1.371
soDeliveryDate+1.356
cel+1.353
Neg logit contributions
ruff-1.105
 Tanz-1.063
erity-1.062
 jammed-1.057
 Danger-1.028
Token)
Token ID8
Feature activation+1.65e-01

Pos logit contributions
xit+0.087
cycles+0.072
iac+0.072
cel+0.071
************+0.069
Neg logit contributions
ruff-0.077
erity-0.075
 jammed-0.074
 Tanz-0.074
itent-0.071
Token designated
Token ID11032
Feature activation+9.31e-02

Pos logit contributions
xit+0.117
cycles+0.097
iac+0.097
cel+0.096
************+0.093
Neg logit contributions
ruff-0.106
erity-0.103
 jammed-0.103
 Tanz-0.102
itent-0.098
Token Lake
Token ID6233
Feature activation+2.06e-01

Pos logit contributions
xit+0.063
iac+0.051
cycles+0.051
cel+0.051
************+0.049
Neg logit contributions
ruff-0.063
erity-0.061
 jammed-0.061
 Tanz-0.060
itent-0.058
Token Ur
Token ID8799
Feature activation+2.04e-01

Pos logit contributions
xit+0.139
cycles+0.114
iac+0.114
cel+0.113
************+0.109
Neg logit contributions
ruff-0.138
erity-0.135
 jammed-0.134
 Tanz-0.133
 Danger-0.128
Token-
Token ID12
Feature activation-3.28e-01

Pos logit contributions
ruff+0.241
erity+0.237
 jammed+0.234
 Tanz+0.233
itent+0.225
Neg logit contributions
xit-0.256
iac-0.210
cycles-0.210
cel-0.208
************-0.202
Tokenoff
Token ID2364
Feature activation+3.56e-01

Pos logit contributions
ruff+0.223
erity+0.219
 jammed+0.218
 Tanz+0.216
itent+0.209
Neg logit contributions
xit-0.219
iac-0.178
cycles-0.178
cel-0.176
************-0.171
Token between
Token ID1022
Feature activation+1.75e-01

Pos logit contributions
xit+0.252
cycles+0.208
iac+0.208
cel+0.206
************+0.200
Neg logit contributions
ruff-0.227
erity-0.222
 jammed-0.222
 Tanz-0.219
itent-0.211
Token Gu
Token ID1962
Feature activation+3.63e-01

Pos logit contributions
xit+0.121
cycles+0.099
iac+0.099
cel+0.098
************+0.096
Neg logit contributions
ruff-0.115
erity-0.113
 jammed-0.112
 Tanz-0.111
itent-0.107
Tokeniller
Token ID4665
Feature activation-3.94e-01

Pos logit contributions
xit+0.321
cycles+0.277
iac+0.276
cel+0.273
************+0.269
Neg logit contributions
ruff-0.168
erity-0.163
 jammed-0.161
 Tanz-0.160
itent-0.152
Tokenmo
Token ID5908
Feature activation+1.98e+00

Pos logit contributions
ruff+0.247
erity+0.243
 jammed+0.240
 Tanz+0.238
itent+0.229
Neg logit contributions
xit-0.284
iac-0.236
cycles-0.235
cel-0.234
************-0.227
Token L
Token ID406
Feature activation+5.23e-01

Pos logit contributions
xit+1.372
cycles+1.139
iac+1.131
cel+1.127
soDeliveryDate+1.109
Neg logit contributions
ruff-1.276
 Tanz-1.254
 jammed-1.253
erity-1.234
 Danger-1.212
Tokenasso
Token ID28372
Feature activation+2.05e-01

Pos logit contributions
xit+0.338
cycles+0.274
iac+0.273
cel+0.270
************+0.264
Neg logit contributions
ruff-0.367
erity-0.359
 jammed-0.356
 Tanz-0.353
itent-0.342
Token and
Token ID290
Feature activation+3.73e-01

Pos logit contributions
xit+0.147
cycles+0.122
iac+0.121
cel+0.120
************+0.117
Neg logit contributions
ruff-0.129
erity-0.126
 jammed-0.125
 Tanz-0.124
itent-0.119
Token Lenin
Token ID22899
Feature activation+1.38e-01

Pos logit contributions
xit+0.244
cycles+0.198
iac+0.198
cel+0.195
************+0.190
Neg logit contributions
ruff-0.258
erity-0.253
 jammed-0.252
 Tanz-0.250
itent-0.241
Token Moreno
Token ID43269
Feature activation+1.36e-01

Pos logit contributions
xit+0.108
cycles+0.091
iac+0.091
cel+0.090
************+0.088
Neg logit contributions
ruff-0.077
erity-0.076
 jammed-0.075
 Tanz-0.074
itent-0.071
Token MORE
Token ID12011
Feature activation+9.88e-02

Pos logit contributions
xit+0.934
cycles+0.783
iac+0.770
cel+0.767
************+0.749
Neg logit contributions
ruff-0.757
 jammed-0.741
erity-0.737
 Tanz-0.733
 Danger-0.709
Token and
Token ID290
Feature activation-1.04e-01

Pos logit contributions
xit+0.071
cycles+0.059
iac+0.059
cel+0.058
************+0.057
Neg logit contributions
ruff-0.062
erity-0.061
 jammed-0.060
 Tanz-0.060
itent-0.058
Token Hillary
Token ID5073
Feature activation-2.00e-01

Pos logit contributions
ruff+0.067
erity+0.065
 jammed+0.065
 Tanz+0.064
itent+0.062
Neg logit contributions
xit-0.073
iac-0.060
cycles-0.060
cel-0.060
************-0.058
Token Clinton
Token ID2605
Feature activation+2.87e-02

Pos logit contributions
ruff+0.150
erity+0.147
 jammed+0.146
 Tanz+0.145
itent+0.141
Neg logit contributions
xit-0.119
iac-0.094
cycles-0.094
cel-0.093
************-0.090
Token Hillary
Token ID5073
Feature activation+5.42e-01

Pos logit contributions
xit+0.017
iac+0.014
cycles+0.014
cel+0.013
************+0.013
Neg logit contributions
ruff-0.021
erity-0.021
 jammed-0.021
 Tanz-0.021
itent-0.020
Token Diane
Token ID26542
Feature activation+1.97e+00

Pos logit contributions
xit+0.464
cycles+0.395
iac+0.394
cel+0.392
************+0.385
Neg logit contributions
ruff-0.267
erity-0.260
 jammed-0.258
 Tanz-0.254
itent-0.243
Token Rodham
Token ID41848
Feature activation-3.67e-01

Pos logit contributions
xit+1.063
cycles+0.823
iac+0.805
cel+0.800
************+0.784
Neg logit contributions
ruff-1.623
erity-1.571
 jammed-1.555
 Tanz-1.546
 Danger-1.525
Token Clinton
Token ID2605
Feature activation+8.10e-02

Pos logit contributions
ruff+0.277
erity+0.274
 jammed+0.272
 Tanz+0.270
itent+0.261
Neg logit contributions
xit-0.216
iac-0.171
cycles-0.171
cel-0.169
************-0.163
TokenSanders
Token ID26747
Feature activation+6.40e-01

Pos logit contributions
xit+0.058
iac+0.048
cycles+0.048
cel+0.047
************+0.046
Neg logit contributions
ruff-0.051
erity-0.050
 jammed-0.050
 Tanz-0.050
itent-0.048
Token:
Token ID25
Feature activation+1.00e+00

Pos logit contributions
xit+0.459
cycles+0.381
iac+0.380
cel+0.376
************+0.368
Neg logit contributions
ruff-0.403
erity-0.396
 jammed-0.392
 Tanz-0.387
 Danger-0.376
Token '
Token ID705
Feature activation+3.11e-01

Pos logit contributions
xit+0.764
cycles+0.639
iac+0.631
cel+0.630
************+0.616
Neg logit contributions
ruff-0.592
erity-0.586
 jammed-0.576
 Tanz-0.568
 Danger-0.553
Token Please
Token ID4222
Feature activation-1.97e-01

Pos logit contributions
xit+0.017
cycles+0.015
iac+0.015
cel+0.014
************+0.014
Neg logit contributions
ruff-0.014
erity-0.014
 jammed-0.014
 Tanz-0.013
itent-0.013
Token turn
Token ID1210
Feature activation+2.07e-01

Pos logit contributions
ruff+0.128
erity+0.126
 jammed+0.125
 Tanz+0.124
itent+0.120
Neg logit contributions
xit-0.137
iac-0.113
cycles-0.113
cel-0.112
************-0.109
Token on
Token ID319
Feature activation+1.19e+00

Pos logit contributions
xit+0.151
cycles+0.126
iac+0.126
cel+0.124
************+0.121
Neg logit contributions
ruff-0.127
erity-0.124
 jammed-0.123
 Tanz-0.122
itent-0.118
Token JavaScript
Token ID11933
Feature activation-2.26e-01

Pos logit contributions
xit+0.862
cycles+0.715
iac+0.706
cel+0.700
************+0.687
Neg logit contributions
ruff-0.743
erity-0.731
 jammed-0.727
 Tanz-0.712
 Danger-0.695
Token.
Token ID13
Feature activation+8.21e-01

Pos logit contributions
ruff+0.147
erity+0.144
 jammed+0.143
 Tanz+0.142
itent+0.137
Neg logit contributions
xit-0.157
iac-0.130
cycles-0.129
cel-0.128
************-0.125
Token Media
Token ID6343
Feature activation+1.96e+00

Pos logit contributions
xit+0.591
cycles+0.490
iac+0.483
cel+0.482
************+0.469
Neg logit contributions
ruff-0.516
erity-0.507
 jammed-0.500
 Tanz-0.497
 Danger-0.481
Token requires
Token ID4433
Feature activation+8.36e-01

Pos logit contributions
xit+1.726
cycles+1.488
cel+1.461
iac+1.458
soDeliveryDate+1.429
Neg logit contributions
ruff-0.917
erity-0.909
 jammed-0.901
 Tanz-0.854
 Danger-0.843
Token JavaScript
Token ID11933
Feature activation-1.91e-02

Pos logit contributions
xit+0.596
cycles+0.496
iac+0.487
cel+0.485
************+0.476
Neg logit contributions
ruff-0.528
erity-0.522
 jammed-0.516
 Tanz-0.508
 Danger-0.496
Token to
Token ID284
Feature activation+1.90e-01

Pos logit contributions
ruff+0.013
erity+0.012
 jammed+0.012
 Tanz+0.012
itent+0.012
Neg logit contributions
xit-0.013
cycles-0.011
iac-0.011
cel-0.011
************-0.010
Token play
Token ID711
Feature activation+3.64e-01

Pos logit contributions
xit+0.168
cycles+0.144
iac+0.144
cel+0.143
************+0.140
Neg logit contributions
ruff-0.088
erity-0.085
 jammed-0.085
 Tanz-0.083
itent-0.079
Token.
Token ID13
Feature activation+3.97e-01

Pos logit contributions
xit+0.258
cycles+0.213
iac+0.212
cel+0.211
************+0.205
Neg logit contributions
ruff-0.232
erity-0.227
 jammed-0.226
 Tanz-0.224
 Danger-0.216
Token President
Token ID1992
Feature activation+4.16e-01

Pos logit contributions
xit+0.089
cycles+0.073
iac+0.073
cel+0.072
************+0.070
Neg logit contributions
ruff-0.090
erity-0.088
 jammed-0.088
 Tanz-0.087
itent-0.084
Token Trump
Token ID1301
Feature activation+2.88e-02

Pos logit contributions
xit+0.241
iac+0.190
cycles+0.189
cel+0.188
************+0.182
Neg logit contributions
ruff-0.320
erity-0.314
 jammed-0.312
 Tanz-0.310
itent-0.300
Token Donald
Token ID3759
Feature activation-3.28e-01

Pos logit contributions
xit+0.021
cycles+0.017
iac+0.017
cel+0.017
************+0.016
Neg logit contributions
ruff-0.018
erity-0.018
 jammed-0.018
 Tanz-0.017
itent-0.017
Token John
Token ID1757
Feature activation+1.97e-01

Pos logit contributions
ruff+0.232
erity+0.228
 jammed+0.227
 Tanz+0.225
itent+0.217
Neg logit contributions
xit-0.210
iac-0.169
cycles-0.169
cel-0.167
************-0.162
Token Trump
Token ID1301
Feature activation+6.79e-03

Pos logit contributions
xit+0.098
iac+0.074
cycles+0.074
cel+0.073
************+0.069
Neg logit contributions
ruff-0.168
erity-0.165
 jammed-0.164
 Tanz-0.163
 Danger-0.159
TokenHouse
Token ID18102
Feature activation+1.95e+00

Pos logit contributions
xit+0.005
iac+0.004
cycles+0.004
cel+0.004
************+0.004
Neg logit contributions
ruff-0.005
erity-0.005
 jammed-0.004
 Tanz-0.004
itent-0.004
Token committee
Token ID5583
Feature activation+5.20e-01

Pos logit contributions
xit+1.414
iac+1.190
cycles+1.169
************+1.148
cel+1.144
Neg logit contributions
ruff-1.212
erity-1.207
 jammed-1.190
 Danger-1.160
 Tanz-1.157
Token believes
Token ID5804
Feature activation+3.42e-01

Pos logit contributions
xit+0.466
iac+0.405
cycles+0.403
cel+0.401
************+0.392
Neg logit contributions
ruff-0.232
erity-0.226
 jammed-0.224
 Tanz-0.219
 Danger-0.209
Token it
Token ID340
Feature activation-1.05e+00

Pos logit contributions
xit+0.222
cycles+0.179
iac+0.179
cel+0.178
************+0.173
Neg logit contributions
ruff-0.238
erity-0.235
 jammed-0.234
 Tanz-0.231
itent-0.224
Token has
Token ID468
Feature activation+1.86e+00

Pos logit contributions
ruff+0.642
erity+0.627
 Tanz+0.627
 jammed+0.615
itent+0.593
Neg logit contributions
xit-0.769
iac-0.640
cycles-0.637
cel-0.633
 anim-0.617
Token evidence
Token ID2370
Feature activation-6.74e-01

Pos logit contributions
xit+1.146
cycles+0.920
cel+0.912
iac+0.912
soDeliveryDate+0.885
Neg logit contributions
 jammed-1.360
ruff-1.334
erity-1.331
 Tanz-1.289
 Danger-1.286
Token The
Token ID383
Feature activation+2.09e+00

Pos logit contributions
xit+1.397
iac+1.209
cel+1.187
cycles+1.181
soDeliveryDate+1.170
Neg logit contributions
ruff-0.783
erity-0.781
 Tanz-0.763
 jammed-0.762
 Danger-0.739
Token Life
Token ID5155
Feature activation+4.64e-01

Pos logit contributions
xit+1.154
soDeliveryDate+0.885
iac+0.885
cycles+0.872
cel+0.861
Neg logit contributions
ruff-1.646
erity-1.646
 jammed-1.623
 Tanz-1.614
 Danger-1.612
Token of
Token ID286
Feature activation+8.99e-01

Pos logit contributions
xit+0.329
cycles+0.270
iac+0.269
cel+0.268
************+0.261
Neg logit contributions
ruff-0.296
erity-0.291
 jammed-0.288
 Tanz-0.285
 Danger-0.276
Token Murray
Token ID12164
Feature activation+1.23e+00

Pos logit contributions
xit+0.393
cycles+0.281
iac+0.276
cel+0.273
soDeliveryDate+0.261
Neg logit contributions
ruff-0.817
erity-0.808
 jammed-0.803
 Tanz-0.799
 Danger-0.782
Token N
Token ID399
Feature activation+1.60e+00

Pos logit contributions
xit+0.935
cycles+0.780
iac+0.776
cel+0.775
************+0.757
Neg logit contributions
ruff-0.728
 jammed-0.707
erity-0.702
 Tanz-0.699
 Danger-0.685
Token.
Token ID13
Feature activation+1.94e+00

Pos logit contributions
xit+1.193
cycles+0.989
cel+0.973
iac+0.972
soDeliveryDate+0.953
Neg logit contributions
ruff-0.986
 jammed-0.949
erity-0.936
 Tanz-0.929
itent-0.905
Token Roth
Token ID16131
Feature activation-1.72e-01

Pos logit contributions
xit+0.603
cycles+0.371
cel+0.343
iac+0.337
nan+0.310
Neg logit contributions
ruff-2.021
 Tanz-1.985
 jammed-1.979
erity-1.965
itent-1.942
Tokenbard
Token ID23024
Feature activation+7.44e-01

Pos logit contributions
ruff+0.090
erity+0.088
 jammed+0.088
 Tanz+0.087
itent+0.083
Neg logit contributions
xit-0.141
iac-0.120
cycles-0.120
cel-0.119
************-0.116
Token (
Token ID357
Feature activation+6.31e-02

Pos logit contributions
xit+0.534
cycles+0.440
iac+0.434
cel+0.432
************+0.423
Neg logit contributions
ruff-0.472
erity-0.464
 jammed-0.456
 Tanz-0.451
itent-0.438
TokenProm
Token ID24129
Feature activation-1.70e+00

Pos logit contributions
xit+0.057
cycles+0.050
iac+0.050
cel+0.049
************+0.048
Neg logit contributions
ruff-0.028
erity-0.027
 jammed-0.026
 Tanz-0.026
itent-0.025
Tokenetheus
Token ID36916
Feature activation-7.83e-01

Pos logit contributions
ruff+0.656
erity+0.631
 jammed+0.622
 Tanz+0.611
 Danger+0.576
Neg logit contributions
xit-1.640
cel-1.438
cycles-1.436
iac-1.435
iste-1.399
Token'
Token ID6
Feature activation+1.05e+00

Pos logit contributions
xit+1.021
cycles+0.846
iac+0.840
cel+0.836
************+0.813
Neg logit contributions
ruff-0.791
 jammed-0.774
erity-0.769
 Tanz-0.758
 Danger-0.734
Token I
Token ID314
Feature activation+1.53e+00

Pos logit contributions
xit+0.767
cel+0.638
cycles+0.637
iac+0.630
************+0.613
Neg logit contributions
ruff-0.645
 jammed-0.634
erity-0.627
 Tanz-0.623
itent-0.606
Token'll
Token ID1183
Feature activation+1.06e-01

Pos logit contributions
xit+1.065
cycles+0.877
cel+0.860
iac+0.855
************+0.846
Neg logit contributions
ruff-0.995
 jammed-0.990
erity-0.975
 Tanz-0.960
itent-0.942
Token make
Token ID787
Feature activation+7.04e-01

Pos logit contributions
xit+0.080
cycles+0.067
iac+0.067
cel+0.066
************+0.064
Neg logit contributions
ruff-0.062
erity-0.061
 jammed-0.060
 Tanz-0.060
itent-0.058
Token the
Token ID262
Feature activation+2.03e-01

Pos logit contributions
xit+0.502
cycles+0.413
iac+0.411
cel+0.408
************+0.400
Neg logit contributions
ruff-0.449
erity-0.438
 jammed-0.435
 Tanz-0.431
 Danger-0.420
Token large
Token ID1588
Feature activation+1.94e+00

Pos logit contributions
xit+0.135
cycles+0.110
iac+0.110
cel+0.109
************+0.106
Neg logit contributions
ruff-0.138
erity-0.135
 jammed-0.135
 Tanz-0.133
itent-0.129
Token corporations
Token ID10225
Feature activation-2.29e-01

Pos logit contributions
xit+1.171
iac+0.928
cycles+0.926
cel+0.915
nan+0.879
Neg logit contributions
ruff-1.441
erity-1.427
 jammed-1.417
 Tanz-1.379
 Danger-1.363
Token pay
Token ID1414
Feature activation+1.24e+00

Pos logit contributions
ruff+0.114
erity+0.111
 jammed+0.110
 Tanz+0.109
itent+0.103
Neg logit contributions
xit-0.195
iac-0.166
cycles-0.166
cel-0.165
************-0.161
Token '
Token ID705
Feature activation-1.10e-01

Pos logit contributions
xit+0.895
cycles+0.752
iac+0.745
cel+0.738
************+0.726
Neg logit contributions
ruff-0.760
erity-0.755
 jammed-0.747
 Tanz-0.730
 Danger-0.712
Tokenfair
Token ID22043
Feature activation+8.06e-01

Pos logit contributions
ruff+0.068
erity+0.066
 jammed+0.066
 Tanz+0.065
itent+0.063
Neg logit contributions
xit-0.080
iac-0.066
cycles-0.066
cel-0.066
************-0.064
Token share
Token ID2648
Feature activation-1.80e-01

Pos logit contributions
xit+0.643
iac+0.545
cycles+0.543
cel+0.542
************+0.527
Neg logit contributions
ruff-0.442
erity-0.437
 jammed-0.429
 Tanz-0.417
 Danger-0.408
Token and
Token ID290
Feature activation+4.77e-01

Pos logit contributions
xit+0.290
cycles+0.240
iac+0.239
cel+0.237
************+0.231
Neg logit contributions
ruff-0.258
erity-0.253
 jammed-0.253
 Tanz-0.249
 Danger-0.240
Token deep
Token ID2769
Feature activation+1.08e+00

Pos logit contributions
xit+0.345
iac+0.286
cycles+0.286
cel+0.283
************+0.276
Neg logit contributions
ruff-0.297
erity-0.291
 jammed-0.291
 Tanz-0.287
 Danger-0.276
Token balls
Token ID11333
Feature activation+5.48e-01

Pos logit contributions
xit+0.690
iac+0.555
cycles+0.554
cel+0.548
************+0.534
Neg logit contributions
ruff-0.766
 jammed-0.752
erity-0.749
 Tanz-0.742
 Danger-0.722
Token to
Token ID284
Feature activation+8.59e-02

Pos logit contributions
xit+0.390
cycles+0.323
iac+0.322
cel+0.319
************+0.311
Neg logit contributions
ruff-0.348
 jammed-0.341
erity-0.341
 Tanz-0.336
 Danger-0.324
Token Stef
Token ID22350
Feature activation-3.09e-01

Pos logit contributions
xit+0.063
cycles+0.053
iac+0.053
cel+0.052
************+0.051
Neg logit contributions
ruff-0.052
erity-0.051
 jammed-0.051
 Tanz-0.050
itent-0.048
Tokenon
Token ID261
Feature activation-2.76e+00

Pos logit contributions
ruff+0.202
erity+0.198
 jammed+0.196
 Tanz+0.195
itent+0.188
Neg logit contributions
xit-0.214
iac-0.176
cycles-0.175
cel-0.174
************-0.169
Token D
Token ID360
Feature activation-1.58e+00

Pos logit contributions
ruff+1.593
erity+1.589
 jammed+1.555
 Tanz+1.549
ifle+1.524
Neg logit contributions
xit-2.077
cel-1.753
iac-1.734
cycles-1.721
 Domain-1.688
Tokeniggs
Token ID20340
Feature activation+1.24e-01

Pos logit contributions
ruff+1.183
erity+1.170
 Tanz+1.162
 jammed+1.160
 Danger+1.123
Neg logit contributions
xit-0.928
iac-0.758
cel-0.740
cycles-0.737
nan-0.712
Token.
Token ID13
Feature activation-2.11e-02

Pos logit contributions
xit+0.089
cycles+0.073
iac+0.073
cel+0.073
************+0.071
Neg logit contributions
ruff-0.079
erity-0.077
 jammed-0.077
 Tanz-0.076
itent-0.073
Token
Token ID198
Feature activation+6.68e-02

Pos logit contributions
ruff+0.013
erity+0.012
 jammed+0.012
 Tanz+0.012
itent+0.012
Neg logit contributions
xit-0.016
iac-0.013
cycles-0.013
cel-0.013
************-0.013
Token
Token ID198
Feature activation-2.11e-01

Pos logit contributions
xit+0.049
cycles+0.041
iac+0.041
cel+0.040
************+0.039
Neg logit contributions
ruff-0.041
erity-0.040
 jammed-0.040
 Tanz-0.039
itent-0.038
Token their
Token ID511
Feature activation+1.03e-01

Pos logit contributions
xit+0.196
cycles+0.163
iac+0.163
cel+0.161
************+0.157
Neg logit contributions
ruff-0.164
erity-0.160
 jammed-0.159
 Tanz-0.158
 Danger-0.152
Token play
Token ID711
Feature activation+5.39e-01

Pos logit contributions
xit+0.074
cycles+0.061
iac+0.061
cel+0.060
************+0.059
Neg logit contributions
ruff-0.065
erity-0.063
 jammed-0.063
 Tanz-0.062
itent-0.060
Token enough
Token ID1576
Feature activation+2.91e-01

Pos logit contributions
xit+0.381
iac+0.313
cycles+0.312
cel+0.310
************+0.302
Neg logit contributions
ruff-0.345
erity-0.339
 jammed-0.336
 Tanz-0.333
itent-0.322
Token.
Token ID13
Feature activation-1.06e-01

Pos logit contributions
xit+0.202
cycles+0.166
iac+0.166
cel+0.164
************+0.160
Neg logit contributions
ruff-0.190
erity-0.186
 jammed-0.185
 Tanz-0.183
itent-0.177
Token Brad
Token ID8114
Feature activation-8.55e-01

Pos logit contributions
ruff+0.066
erity+0.065
 jammed+0.064
 Tanz+0.064
itent+0.062
Neg logit contributions
xit-0.076
iac-0.063
cycles-0.063
cel-0.062
************-0.061
Tokenen
Token ID268
Feature activation-2.38e+00

Pos logit contributions
ruff+0.517
erity+0.506
 jammed+0.501
 Tanz+0.496
itent+0.481
Neg logit contributions
xit-0.635
iac-0.532
cycles-0.527
cel-0.524
************-0.508
Token Holt
Token ID28330
Feature activation-7.13e-01

Pos logit contributions
ruff+1.183
erity+1.175
 Tanz+1.147
 jammed+1.138
ifle+1.118
Neg logit contributions
xit-1.994
cel-1.737
iac-1.731
cycles-1.712
nan-1.684
Tokenby
Token ID1525
Feature activation+1.52e-01

Pos logit contributions
ruff+0.477
erity+0.469
 jammed+0.465
 Tanz+0.463
 Danger+0.446
Neg logit contributions
xit-0.480
cycles-0.394
iac-0.393
cel-0.390
************-0.379
Token lacks
Token ID16523
Feature activation+1.22e-01

Pos logit contributions
xit+0.107
cycles+0.089
iac+0.088
cel+0.088
************+0.085
Neg logit contributions
ruff-0.098
erity-0.096
 jammed-0.095
 Tanz-0.094
itent-0.091
Token the
Token ID262
Feature activation+9.01e-02

Pos logit contributions
xit+0.099
cycles+0.084
iac+0.084
cel+0.083
************+0.081
Neg logit contributions
ruff-0.066
erity-0.064
 jammed-0.064
 Tanz-0.063
itent-0.060
Token stamina
Token ID32312
Feature activation+3.23e-01

Pos logit contributions
xit+0.066
cycles+0.055
iac+0.055
cel+0.055
************+0.053
Neg logit contributions
ruff-0.055
erity-0.054
 jammed-0.053
 Tanz-0.053
itent-0.051
Token newspaper
Token ID7533
Feature activation+6.71e-01

Pos logit contributions
xit+0.280
cycles+0.228
iac+0.227
cel+0.225
************+0.219
Neg logit contributions
ruff-0.286
erity-0.280
 jammed-0.279
 Tanz-0.277
 Danger-0.267
Token J
Token ID449
Feature activation+1.17e-01

Pos logit contributions
xit+0.475
cycles+0.391
iac+0.391
cel+0.387
************+0.377
Neg logit contributions
ruff-0.429
erity-0.421
 jammed-0.419
 Tanz-0.418
 Danger-0.402
Tokenyll
Token ID25727
Feature activation+2.75e-01

Pos logit contributions
xit+0.123
cycles+0.108
iac+0.108
cel+0.108
************+0.106
Neg logit contributions
ruff-0.035
erity-0.033
 jammed-0.033
 Tanz-0.032
itent-0.030
Tokenands
Token ID1746
Feature activation+1.70e-01

Pos logit contributions
xit+0.148
cycles+0.115
iac+0.114
cel+0.112
************+0.109
Neg logit contributions
ruff-0.222
erity-0.218
 jammed-0.217
 Tanz-0.215
itent-0.210
Token-
Token ID12
Feature activation-1.17e+00

Pos logit contributions
xit+0.117
cycles+0.096
iac+0.096
cel+0.095
************+0.093
Neg logit contributions
ruff-0.111
erity-0.109
 jammed-0.108
 Tanz-0.107
itent-0.103
TokenPost
Token ID6307
Feature activation-2.34e+00

Pos logit contributions
ruff+0.913
erity+0.910
 jammed+0.893
 Tanz+0.892
ifle+0.865
Neg logit contributions
xit-0.647
cel-0.513
iac-0.504
cycles-0.502
************-0.486
Tokenen
Token ID268
Feature activation+4.08e-01

Pos logit contributions
 jammed+1.715
 Tanz+1.709
ruff+1.708
erity+1.685
 prin+1.627
Neg logit contributions
xit-1.388
cel-1.149
iac-1.149
cycles-1.094
nan-1.092
Tokenin
Token ID259
Feature activation+2.70e-01

Pos logit contributions
xit+0.291
cycles+0.240
iac+0.240
cel+0.238
************+0.232
Neg logit contributions
ruff-0.259
erity-0.254
 jammed-0.253
 Tanz-0.250
itent-0.241
Token 2005
Token ID5075
Feature activation+2.60e-01

Pos logit contributions
xit+0.191
cycles+0.158
iac+0.158
cel+0.156
************+0.152
Neg logit contributions
ruff-0.172
erity-0.169
 jammed-0.168
 Tanz-0.166
itent-0.160
Token.
Token ID13
Feature activation+1.23e-01

Pos logit contributions
xit+0.185
cycles+0.153
iac+0.153
cel+0.152
************+0.148
Neg logit contributions
ruff-0.165
erity-0.162
 jammed-0.161
 Tanz-0.159
itent-0.153
Token It
Token ID632
Feature activation+2.71e-01

Pos logit contributions
xit+0.091
cycles+0.076
iac+0.076
cel+0.075
************+0.073
Neg logit contributions
ruff-0.074
erity-0.072
 jammed-0.072
 Tanz-0.071
 Danger-0.068
Token 30
Token ID1542
Feature activation+1.58e-01

Pos logit contributions
xit+0.164
cycles+0.135
iac+0.135
cel+0.134
************+0.131
Neg logit contributions
ruff-0.149
erity-0.146
 jammed-0.145
 Tanz-0.144
itent-0.139
Token.
Token ID13
Feature activation+2.35e-01

Pos logit contributions
xit+0.112
iac+0.092
cycles+0.092
cel+0.091
************+0.089
Neg logit contributions
ruff-0.101
erity-0.099
 jammed-0.098
 Tanz-0.097
itent-0.094
Token After
Token ID2293
Feature activation+4.02e-01

Pos logit contributions
xit+0.174
cycles+0.145
iac+0.145
cel+0.143
************+0.140
Neg logit contributions
ruff-0.143
erity-0.140
 jammed-0.139
 Tanz-0.138
 Danger-0.132
Token I
Token ID314
Feature activation+1.85e-01

Pos logit contributions
xit+0.287
cycles+0.237
iac+0.237
cel+0.235
************+0.229
Neg logit contributions
ruff-0.254
erity-0.249
 jammed-0.248
 Tanz-0.245
 Danger-0.236
Token joined
Token ID5399
Feature activation+2.41e-01

Pos logit contributions
xit+0.128
cycles+0.106
iac+0.106
cel+0.104
************+0.102
Neg logit contributions
ruff-0.121
erity-0.118
 jammed-0.118
 Tanz-0.116
itent-0.112
Token Pf
Token ID38477
Feature activation-2.26e+00

Pos logit contributions
xit+0.168
cycles+0.138
iac+0.138
cel+0.136
************+0.133
Neg logit contributions
ruff-0.157
erity-0.154
 jammed-0.153
 Tanz-0.152
itent-0.146
Tokenizer
Token ID7509
Feature activation+2.71e-01

Pos logit contributions
ruff+0.516
erity+0.476
 jammed+0.476
 Tanz+0.457
 Danger+0.416
Neg logit contributions
xit-2.515
iac-2.267
cel-2.250
cycles-2.247
nan-2.212
Token Pharmaceutical
Token ID37175
Feature activation+9.33e-03

Pos logit contributions
xit+0.193
cycles+0.159
iac+0.159
cel+0.158
************+0.154
Neg logit contributions
ruff-0.171
erity-0.168
 jammed-0.167
 Tanz-0.165
itent-0.159
Tokens
Token ID82
Feature activation+1.91e-01

Pos logit contributions
xit+0.007
iac+0.005
cycles+0.005
cel+0.005
************+0.005
Neg logit contributions
ruff-0.006
erity-0.006
 jammed-0.006
 Tanz-0.006
itent-0.006
Token,
Token ID11
Feature activation+2.32e-02

Pos logit contributions
xit+0.136
cycles+0.112
iac+0.112
cel+0.111
************+0.108
Neg logit contributions
ruff-0.121
erity-0.119
 jammed-0.118
 Tanz-0.117
itent-0.113
Token and
Token ID290
Feature activation-1.67e-02

Pos logit contributions
xit+0.017
iac+0.014
cycles+0.014
cel+0.014
************+0.014
Neg logit contributions
ruff-0.014
erity-0.014
 jammed-0.014
 Tanz-0.014
itent-0.013
Token.
Token ID13
Feature activation-4.46e-01

Pos logit contributions
ruff+0.045
erity+0.044
 jammed+0.044
 Tanz+0.044
itent+0.042
Neg logit contributions
xit-0.051
iac-0.042
cycles-0.042
cel-0.041
************-0.040
Token
Token ID198
Feature activation+8.35e-02

Pos logit contributions
ruff+0.268
erity+0.263
 jammed+0.261
 Tanz+0.258
itent+0.249
Neg logit contributions
xit-0.332
iac-0.277
cycles-0.277
cel-0.275
************-0.268
Token
Token ID198
Feature activation-4.18e-01

Pos logit contributions
xit+0.061
cycles+0.051
iac+0.051
cel+0.050
************+0.049
Neg logit contributions
ruff-0.051
erity-0.050
 jammed-0.050
 Tanz-0.049
itent-0.047
TokenAt
Token ID2953
Feature activation+4.17e-03

Pos logit contributions
ruff+0.255
erity+0.250
 jammed+0.248
 Tanz+0.246
itent+0.237
Neg logit contributions
xit-0.308
iac-0.257
cycles-0.257
cel-0.255
************-0.248
Token G
Token ID402
Feature activation-2.21e-01

Pos logit contributions
xit+0.003
cycles+0.003
iac+0.003
cel+0.003
************+0.002
Neg logit contributions
ruff-0.003
erity-0.003
 jammed-0.002
 Tanz-0.002
itent-0.002
Tokenf
Token ID69
Feature activation-2.26e+00

Pos logit contributions
ruff+0.112
erity+0.109
 jammed+0.108
 Tanz+0.107
itent+0.102
Neg logit contributions
xit-0.185
iac-0.158
cycles-0.158
cel-0.156
************-0.153
Tokeninity
Token ID6269
Feature activation-3.35e-01

Pos logit contributions
ruff+1.232
erity+1.222
 Tanz+1.199
 jammed+1.193
itent+1.140
Neg logit contributions
xit-1.793
iac-1.545
cycles-1.532
cel-1.527
 anim-1.475
Token 3
Token ID513
Feature activation-3.57e-01

Pos logit contributions
ruff+0.214
erity+0.210
 jammed+0.208
 Tanz+0.206
itent+0.199
Neg logit contributions
xit-0.238
iac-0.196
cycles-0.196
cel-0.195
************-0.189
Token r
Token ID374
Feature activation-8.43e-01

Pos logit contributions
ruff+0.228
erity+0.224
 jammed+0.222
 Tanz+0.220
itent+0.212
Neg logit contributions
xit-0.253
iac-0.209
cycles-0.209
cel-0.207
************-0.202
Tokenai
Token ID1872
Feature activation-5.57e-01

Pos logit contributions
ruff+0.502
erity+0.493
 jammed+0.489
 Tanz+0.484
itent+0.466
Neg logit contributions
xit-0.633
iac-0.529
cycles-0.527
cel-0.524
************-0.510
TokenN
Token ID45
Feature activation-6.59e-01

Pos logit contributions
ruff+0.322
erity+0.315
 jammed+0.312
 Tanz+0.310
itent+0.297
Neg logit contributions
xit-0.429
iac-0.360
cycles-0.359
cel-0.357
************-0.348
TokenYou
Token ID1639
Feature activation+4.75e-03

Pos logit contributions
xit+0.235
cycles+0.196
iac+0.196
cel+0.194
************+0.189
Neg logit contributions
ruff-0.182
erity-0.178
 jammed-0.176
 Tanz-0.174
itent-0.168
Token can
Token ID460
Feature activation+5.81e-01

Pos logit contributions
xit+0.003
cycles+0.002
iac+0.002
cel+0.002
************+0.002
Neg logit contributions
ruff-0.003
erity-0.003
 jammed-0.003
 Tanz-0.003
itent-0.003
Token check
Token ID2198
Feature activation-4.64e-01

Pos logit contributions
xit+0.434
cycles+0.361
iac+0.358
cel+0.357
************+0.349
Neg logit contributions
ruff-0.350
erity-0.341
 jammed-0.340
 Tanz-0.335
 Danger-0.325
Token out
Token ID503
Feature activation+6.58e-01

Pos logit contributions
ruff+0.282
erity+0.277
 jammed+0.274
 Tanz+0.272
itent+0.263
Neg logit contributions
xit-0.342
cycles-0.285
iac-0.284
cel-0.282
************-0.275
Token my
Token ID616
Feature activation-2.56e-01

Pos logit contributions
xit+0.512
iac+0.430
cycles+0.428
cel+0.424
************+0.417
Neg logit contributions
ruff-0.375
erity-0.367
 jammed-0.366
 Tanz-0.363
 Danger-0.348
Token Twitter
Token ID3009
Feature activation-2.25e+00

Pos logit contributions
ruff+0.163
erity+0.159
 jammed+0.158
 Tanz+0.157
itent+0.151
Neg logit contributions
xit-0.182
iac-0.151
cycles-0.150
cel-0.149
************-0.145
Token feed
Token ID3745
Feature activation+5.18e-02

Pos logit contributions
ruff+1.365
erity+1.350
 jammed+1.299
itent+1.281
ifle+1.278
Neg logit contributions
xit-1.636
cel-1.414
iac-1.398
cycles-1.396
 anim-1.389
Token by
Token ID416
Feature activation+1.13e+00

Pos logit contributions
xit+0.037
cycles+0.030
iac+0.030
cel+0.030
************+0.029
Neg logit contributions
ruff-0.033
erity-0.032
 jammed-0.032
 Tanz-0.032
itent-0.031
Token going
Token ID1016
Feature activation+4.63e-01

Pos logit contributions
xit+0.749
cycles+0.608
iac+0.602
cel+0.597
************+0.584
Neg logit contributions
ruff-0.781
 jammed-0.762
 Tanz-0.757
erity-0.752
itent-0.727
Token here
Token ID994
Feature activation-1.66e-01

Pos logit contributions
xit+0.270
iac+0.212
cycles+0.211
cel+0.209
************+0.203
Neg logit contributions
ruff-0.354
erity-0.348
 jammed-0.348
 Tanz-0.343
 Danger-0.333
Token.
Token ID13
Feature activation-5.30e-01

Pos logit contributions
ruff+0.108
erity+0.106
 jammed+0.105
 Tanz+0.104
itent+0.100
Neg logit contributions
xit-0.116
cycles-0.095
iac-0.095
cel-0.094
************-0.092
Token seems
Token ID2331
Feature activation+6.91e-02

Pos logit contributions
xit+0.045
cycles+0.038
iac+0.038
cel+0.037
************+0.036
Neg logit contributions
ruff-0.038
erity-0.037
 jammed-0.037
 Tanz-0.037
itent-0.035
Token the
Token ID262
Feature activation+6.78e-02

Pos logit contributions
xit+0.048
cycles+0.039
iac+0.039
cel+0.039
************+0.038
Neg logit contributions
ruff-0.045
erity-0.044
 jammed-0.044
 Tanz-0.043
itent-0.042
Token United
Token ID1578
Feature activation-3.40e-02

Pos logit contributions
xit+0.049
cycles+0.040
iac+0.040
cel+0.040
************+0.039
Neg logit contributions
ruff-0.043
erity-0.042
 jammed-0.041
 Tanz-0.041
itent-0.040
Token States
Token ID1829
Feature activation-4.43e-01

Pos logit contributions
ruff+0.022
erity+0.021
 jammed+0.021
 Tanz+0.021
itent+0.020
Neg logit contributions
xit-0.024
iac-0.020
cycles-0.020
cel-0.020
************-0.019
Token Conference
Token ID8785
Feature activation-9.16e-01

Pos logit contributions
ruff+0.258
erity+0.253
 jammed+0.250
 Tanz+0.248
itent+0.238
Neg logit contributions
xit-0.338
iac-0.284
cycles-0.283
cel-0.281
************-0.274
Token of
Token ID286
Feature activation-2.19e+00

Pos logit contributions
ruff+0.609
erity+0.596
 jammed+0.592
 Tanz+0.588
itent+0.567
Neg logit contributions
xit-0.625
iac-0.512
cycles-0.510
cel-0.507
************-0.492
Token Catholic
Token ID7835
Feature activation-4.64e-01

Pos logit contributions
ruff+1.619
erity+1.599
 jammed+1.557
 Tanz+1.551
ifle+1.517
Neg logit contributions
xit-1.331
iac-1.085
cycles-1.072
cel-1.066
 anim-1.017
Token B
Token ID347
Feature activation+7.18e-01

Pos logit contributions
ruff+0.394
erity+0.388
 jammed+0.386
 Tanz+0.384
ifle+0.373
Neg logit contributions
xit-0.231
iac-0.175
cycles-0.174
cel-0.172
************-0.164
Tokenishops
Token ID21863
Feature activation-2.33e-01

Pos logit contributions
xit+0.559
cycles+0.469
iac+0.467
cel+0.463
************+0.455
Neg logit contributions
ruff-0.410
erity-0.399
 jammed-0.396
 Tanz-0.390
itent-0.377
Token (
Token ID357
Feature activation+1.65e-01

Pos logit contributions
ruff+0.146
erity+0.143
 jammed+0.142
 Tanz+0.141
itent+0.136
Neg logit contributions
xit-0.168
iac-0.139
cycles-0.139
cel-0.138
************-0.134
TokenUS
Token ID2937
Feature activation-2.75e-01

Pos logit contributions
xit+0.097
cycles+0.077
iac+0.077
cel+0.076
************+0.073
Neg logit contributions
ruff-0.125
erity-0.123
 jammed-0.122
 Tanz-0.121
itent-0.117
Token-
Token ID12
Feature activation-5.58e-01

Pos logit contributions
ruff+0.087
erity+0.086
 jammed+0.085
 Tanz+0.084
itent+0.081
Neg logit contributions
xit-0.092
iac-0.076
cycles-0.076
cel-0.075
************-0.073
Tokeneconom
Token ID13926
Feature activation+5.77e-03

Pos logit contributions
ruff+0.161
erity+0.154
 jammed+0.153
 Tanz+0.151
 Danger+0.138
Neg logit contributions
xit-0.590
cycles-0.523
iac-0.523
cel-0.519
************-0.509
Tokenics
Token ID873
Feature activation-9.65e-02

Pos logit contributions
xit+0.003
cycles+0.002
iac+0.002
cel+0.002
************+0.002
Neg logit contributions
ruff-0.005
erity-0.005
 jammed-0.005
 Tanz-0.004
itent-0.004
Token-
Token ID12
Feature activation-3.52e-02

Pos logit contributions
ruff+0.064
erity+0.062
 jammed+0.062
 Tanz+0.061
itent+0.059
Neg logit contributions
xit-0.066
iac-0.054
cycles-0.054
cel-0.054
************-0.052
Tokenand
Token ID392
Feature activation-5.11e-01

Pos logit contributions
ruff+0.021
erity+0.020
 jammed+0.020
 Tanz+0.020
itent+0.019
Neg logit contributions
xit-0.027
iac-0.023
cycles-0.023
cel-0.022
************-0.022
Token-
Token ID12
Feature activation-2.10e+00

Pos logit contributions
ruff+0.340
erity+0.335
 jammed+0.332
 Tanz+0.330
itent+0.317
Neg logit contributions
xit-0.347
iac-0.285
cycles-0.284
cel-0.282
************-0.274
Tokenf
Token ID69
Feature activation-8.45e-01

Pos logit contributions
ruff+0.919
 Tanz+0.894
erity+0.886
 jammed+0.884
ifle+0.814
Neg logit contributions
xit-1.920
cycles-1.684
iac-1.681
cel-1.678
nan-1.620
Tokeninance
Token ID14149
Feature activation+2.26e-01

Pos logit contributions
ruff+0.636
 jammed+0.626
 Tanz+0.624
erity+0.623
 Danger+0.600
Neg logit contributions
xit-0.503
iac-0.404
cycles-0.398
cel-0.396
************-0.380
Token,
Token ID11
Feature activation+2.35e-01

Pos logit contributions
xit+0.162
cycles+0.134
iac+0.134
cel+0.132
************+0.129
Neg logit contributions
ruff-0.142
erity-0.139
 jammed-0.138
 Tanz-0.137
itent-0.132
Token aust
Token ID38132
Feature activation+2.73e-01

Pos logit contributions
xit+0.167
cycles+0.138
iac+0.138
cel+0.137
************+0.133
Neg logit contributions
ruff-0.150
erity-0.146
 jammed-0.146
 Tanz-0.144
itent-0.139
Tokenral
Token ID1373
Feature activation+5.90e-01

Pos logit contributions
xit+0.199
cycles+0.166
iac+0.165
cel+0.164
************+0.160
Neg logit contributions
ruff-0.169
erity-0.166
 jammed-0.164
 Tanz-0.162
itent-0.156
Token PA
Token ID8147
Feature activation-6.89e-01

Pos logit contributions
ruff+0.050
erity+0.049
 jammed+0.049
 Tanz+0.049
itent+0.047
Neg logit contributions
xit-0.054
iac-0.045
cycles-0.045
cel-0.044
************-0.043
TokenK
Token ID42
Feature activation-2.93e-01

Pos logit contributions
ruff+0.431
erity+0.422
 jammed+0.418
 Tanz+0.414
itent+0.399
Neg logit contributions
xit-0.498
iac-0.412
cycles-0.411
cel-0.409
************-0.399
Token files
Token ID3696
Feature activation+2.72e-01

Pos logit contributions
ruff+0.193
erity+0.190
 jammed+0.188
 Tanz+0.187
itent+0.180
Neg logit contributions
xit-0.200
iac-0.164
cycles-0.164
cel-0.163
************-0.158
Token in
Token ID287
Feature activation+1.74e-01

Pos logit contributions
xit+0.194
cycles+0.160
iac+0.160
cel+0.159
************+0.154
Neg logit contributions
ruff-0.173
erity-0.169
 jammed-0.168
 Tanz-0.166
itent-0.161
Token Win
Token ID7178
Feature activation-8.16e-01

Pos logit contributions
xit+0.123
cycles+0.101
iac+0.101
cel+0.100
************+0.097
Neg logit contributions
ruff-0.112
erity-0.110
 jammed-0.109
 Tanz-0.108
itent-0.104
TokenR
Token ID49
Feature activation-2.05e+00

Pos logit contributions
ruff+0.491
erity+0.483
 jammed+0.480
 Tanz+0.475
itent+0.454
Neg logit contributions
xit-0.607
iac-0.507
cycles-0.505
cel-0.502
************-0.489
TokenAR
Token ID1503
Feature activation-2.23e-01

Pos logit contributions
ruff+1.045
erity+1.036
 jammed+1.025
 Tanz+1.007
itent+0.962
Neg logit contributions
xit-1.725
iac-1.481
cel-1.460
cycles-1.453
************-1.418
Token,
Token ID11
Feature activation-3.29e-02

Pos logit contributions
ruff+0.141
erity+0.139
 jammed+0.138
 Tanz+0.136
itent+0.131
Neg logit contributions
xit-0.158
iac-0.131
cycles-0.131
cel-0.130
************-0.126
Token then
Token ID788
Feature activation-4.44e-02

Pos logit contributions
ruff+0.021
erity+0.020
 jammed+0.020
 Tanz+0.020
itent+0.019
Neg logit contributions
xit-0.024
iac-0.020
cycles-0.020
cel-0.019
************-0.019
Token tweak
Token ID25393
Feature activation-2.98e-01

Pos logit contributions
ruff+0.028
erity+0.028
 jammed+0.027
 Tanz+0.027
itent+0.026
Neg logit contributions
xit-0.032
iac-0.026
cycles-0.026
cel-0.026
************-0.025
Token certain
Token ID1728
Feature activation-2.62e-01

Pos logit contributions
ruff+0.190
erity+0.186
 jammed+0.185
 Tanz+0.183
itent+0.177
Neg logit contributions
xit-0.211
cycles-0.174
iac-0.174
cel-0.173
************-0.168
Token per
Token ID583
Feature activation+1.09e-01

Pos logit contributions
ruff+0.941
erity+0.925
 jammed+0.902
 Tanz+0.896
itent+0.863
Neg logit contributions
xit-1.081
cycles-0.909
iac-0.907
cel-0.891
 anim-0.873
Tokenuse
Token ID1904
Feature activation-5.03e-01

Pos logit contributions
xit+0.091
cycles+0.078
iac+0.078
cel+0.077
************+0.075
Neg logit contributions
ruff-0.056
erity-0.054
 jammed-0.054
 Tanz-0.053
itent-0.051
Token.
Token ID13
Feature activation-1.07e+00

Pos logit contributions
ruff+0.329
erity+0.324
 jammed+0.321
 Tanz+0.318
itent+0.308
Neg logit contributions
xit-0.347
iac-0.285
cycles-0.285
cel-0.282
************-0.274
Token Here
Token ID3423
Feature activation-3.22e-01

Pos logit contributions
ruff+0.815
erity+0.803
 jammed+0.798
 Tanz+0.789
itent+0.774
Neg logit contributions
xit-0.616
iac-0.496
cycles-0.490
cel-0.487
************-0.472
Token is
Token ID318
Feature activation+1.99e-02

Pos logit contributions
ruff+0.208
erity+0.204
 jammed+0.203
 Tanz+0.201
itent+0.194
Neg logit contributions
xit-0.225
iac-0.185
cycles-0.185
cel-0.184
************-0.179
Token the
Token ID262
Feature activation-2.05e+00

Pos logit contributions
xit+0.014
iac+0.011
cycles+0.011
cel+0.011
************+0.011
Neg logit contributions
ruff-0.013
erity-0.013
 jammed-0.013
 Tanz-0.012
itent-0.012
Token link
Token ID2792
Feature activation+4.86e-01

Pos logit contributions
ruff+1.334
erity+1.302
 Tanz+1.296
 jammed+1.288
itent+1.261
Neg logit contributions
xit-1.401
cel-1.175
iac-1.173
cycles-1.163
 anim-1.132
Token for
Token ID329
Feature activation-9.56e-01

Pos logit contributions
xit+0.347
cycles+0.286
iac+0.285
cel+0.282
************+0.274
Neg logit contributions
ruff-0.309
erity-0.303
 jammed-0.301
 Tanz-0.299
 Danger-0.288
Token buying
Token ID7067
Feature activation-9.33e-01

Pos logit contributions
ruff+0.474
erity+0.463
 jammed+0.457
 Tanz+0.452
itent+0.434
Neg logit contributions
xit-0.811
cycles-0.698
iac-0.696
cel-0.688
************-0.673
Token the
Token ID262
Feature activation-6.81e-01

Pos logit contributions
ruff+0.624
erity+0.611
 jammed+0.607
 Tanz+0.606
itent+0.587
Neg logit contributions
xit-0.632
cycles-0.519
iac-0.518
cel-0.510
************-0.495
Token second
Token ID1218
Feature activation+6.35e-01

Pos logit contributions
ruff+0.449
erity+0.440
 jammed+0.438
 Tanz+0.435
itent+0.421
Neg logit contributions
xit-0.466
iac-0.386
cycles-0.383
cel-0.380
************-0.367
Token3
Token ID18
Feature activation-1.64e-01

Pos logit contributions
ruff+0.409
erity+0.402
 jammed+0.397
 Tanz+0.395
itent+0.381
Neg logit contributions
xit-0.464
iac-0.387
cycles-0.387
cel-0.382
************-0.371
Token,
Token ID11
Feature activation-5.14e-01

Pos logit contributions
ruff+0.104
erity+0.101
 jammed+0.101
 Tanz+0.100
itent+0.096
Neg logit contributions
xit-0.117
iac-0.097
cycles-0.097
cel-0.096
************-0.094
Token and
Token ID290
Feature activation-3.23e-01

Pos logit contributions
ruff+0.316
erity+0.309
 jammed+0.306
 Tanz+0.303
itent+0.292
Neg logit contributions
xit-0.376
iac-0.313
cycles-0.313
cel-0.310
************-0.302
Token could
Token ID714
Feature activation+2.47e-01

Pos logit contributions
ruff+0.206
erity+0.202
 jammed+0.200
 Tanz+0.198
itent+0.191
Neg logit contributions
xit-0.229
iac-0.189
cycles-0.189
cel-0.187
************-0.182
Token upset
Token ID9247
Feature activation-3.11e-01

Pos logit contributions
xit+0.179
cycles+0.148
iac+0.148
cel+0.147
************+0.143
Neg logit contributions
ruff-0.154
erity-0.150
 jammed-0.150
 Tanz-0.148
itent-0.143
Token Na
Token ID11013
Feature activation-2.05e+00

Pos logit contributions
ruff+0.200
erity+0.196
 jammed+0.194
 Tanz+0.192
itent+0.185
Neg logit contributions
xit-0.220
iac-0.181
cycles-0.181
cel-0.180
************-0.175
Token`
Token ID63
Feature activation-1.32e+00

Pos logit contributions
ruff+1.534
erity+1.498
 jammed+1.494
 Tanz+1.476
itent+1.430
Neg logit contributions
xit-1.232
iac-0.990
cel-0.979
cycles-0.975
************-0.936
TokenVi
Token ID38432
Feature activation-1.29e-01

Pos logit contributions
ruff+0.901
erity+0.887
 jammed+0.877
 Tanz+0.876
itent+0.845
Neg logit contributions
xit-0.877
iac-0.714
cel-0.707
cycles-0.704
************-0.678
Token in
Token ID287
Feature activation+3.60e-02

Pos logit contributions
ruff+0.083
erity+0.081
 jammed+0.080
 Tanz+0.080
itent+0.077
Neg logit contributions
xit-0.091
iac-0.075
cycles-0.075
cel-0.075
************-0.073
Token some
Token ID617
Feature activation-2.20e-01

Pos logit contributions
xit+0.025
iac+0.021
cycles+0.021
cel+0.021
************+0.020
Neg logit contributions
ruff-0.023
erity-0.023
 jammed-0.023
 Tanz-0.022
itent-0.022
Token universe
Token ID6881
Feature activation-9.81e-02

Pos logit contributions
ruff+0.125
erity+0.122
 jammed+0.121
 Tanz+0.120
itent+0.115
Neg logit contributions
xit-0.172
cycles-0.144
iac-0.144
cel-0.143
************-0.140
Token Fox
Token ID5426
Feature activation-5.34e-01

Pos logit contributions
ruff+0.097
erity+0.095
 jammed+0.094
 Tanz+0.093
itent+0.090
Neg logit contributions
xit-0.117
iac-0.097
cycles-0.097
cel-0.096
************-0.094
Token Julia
Token ID22300
Feature activation-3.25e-01

Pos logit contributions
ruff+0.343
erity+0.337
 jammed+0.335
 Tanz+0.331
itent+0.320
Neg logit contributions
xit-0.374
iac-0.310
cycles-0.308
cel-0.307
************-0.298
Token Louis
Token ID5593
Feature activation-1.68e-01

Pos logit contributions
ruff+0.163
erity+0.159
 jammed+0.158
 Tanz+0.156
itent+0.149
Neg logit contributions
xit-0.274
iac-0.234
cycles-0.234
cel-0.232
************-0.227
Token-
Token ID12
Feature activation+2.08e-01

Pos logit contributions
ruff+0.111
erity+0.109
 jammed+0.108
 Tanz+0.107
itent+0.104
Neg logit contributions
xit-0.115
iac-0.094
cycles-0.094
cel-0.093
************-0.091
TokenD
Token ID35
Feature activation+1.76e-01

Pos logit contributions
xit+0.175
cycles+0.149
iac+0.149
cel+0.148
************+0.145
Neg logit contributions
ruff-0.106
erity-0.103
 jammed-0.102
 Tanz-0.101
itent-0.096
Tokenrey
Token ID4364
Feature activation-2.04e+00

Pos logit contributions
xit+0.127
cycles+0.105
iac+0.105
cel+0.104
************+0.102
Neg logit contributions
ruff-0.110
erity-0.107
 jammed-0.107
 Tanz-0.105
itent-0.102
Tokenf
Token ID69
Feature activation+9.00e-02

Pos logit contributions
ruff+0.878
erity+0.875
 jammed+0.870
 Tanz+0.864
itent+0.817
Neg logit contributions
xit-1.856
cel-1.629
iac-1.613
cycles-1.612
nan-1.569
Tokenus
Token ID385
Feature activation-3.05e-01

Pos logit contributions
xit+0.069
cycles+0.058
iac+0.058
cel+0.057
************+0.056
Neg logit contributions
ruff-0.052
erity-0.051
 jammed-0.051
 Tanz-0.050
itent-0.048
Token Ve
Token ID8016
Feature activation+2.88e-01

Pos logit contributions
ruff+0.188
erity+0.185
 jammed+0.183
 Tanz+0.181
itent+0.175
Neg logit contributions
xit-0.223
iac-0.185
cycles-0.185
cel-0.184
************-0.179
Tokenep
Token ID538
Feature activation-3.09e-01

Pos logit contributions
xit+0.121
cycles+0.086
iac+0.085
cel+0.084
************+0.080
Neg logit contributions
ruff-0.267
erity-0.263
 jammed-0.261
 Tanz-0.260
itent-0.254
Token HBO
Token ID18804
Feature activation-3.14e-01

Pos logit contributions
ruff+0.194
erity+0.191
 jammed+0.189
 Tanz+0.187
itent+0.181
Neg logit contributions
xit-0.221
iac-0.183
cycles-0.183
cel-0.181
************-0.176
Token by
Token ID416
Feature activation+9.60e-02

Pos logit contributions
ruff+0.007
erity+0.007
 jammed+0.007
 Tanz+0.007
itent+0.006
Neg logit contributions
xit-0.010
iac-0.008
cycles-0.008
cel-0.008
************-0.008
Token cutting
Token ID7720
Feature activation-3.45e-01

Pos logit contributions
xit+0.070
cycles+0.058
iac+0.058
cel+0.058
************+0.056
Neg logit contributions
ruff-0.059
erity-0.058
 jammed-0.058
 Tanz-0.057
itent-0.055
Token or
Token ID393
Feature activation+1.50e-01

Pos logit contributions
ruff+0.224
erity+0.219
 jammed+0.217
 Tanz+0.216
itent+0.208
Neg logit contributions
xit-0.241
iac-0.199
cycles-0.198
cel-0.197
************-0.192
Token restructuring
Token ID32324
Feature activation-1.34e-01

Pos logit contributions
xit+0.112
cycles+0.094
iac+0.094
cel+0.093
************+0.090
Neg logit contributions
ruff-0.090
erity-0.088
 jammed-0.087
 Tanz-0.086
itent-0.083
Token Brand
Token ID13512
Feature activation+1.07e+00

Pos logit contributions
ruff+0.089
erity+0.087
 jammed+0.086
 Tanz+0.085
itent+0.082
Neg logit contributions
xit-0.092
iac-0.075
cycles-0.075
cel-0.075
************-0.073
Tokenen
Token ID268
Feature activation-1.99e+00

Pos logit contributions
xit+0.728
cycles+0.599
iac+0.593
cel+0.588
************+0.575
Neg logit contributions
ruff-0.708
erity-0.694
 jammed-0.688
 Tanz-0.683
 Danger-0.660
Token Albert
Token ID9966
Feature activation+4.88e-01

Pos logit contributions
ruff+1.243
 jammed+1.221
erity+1.203
 Tanz+1.189
ifle+1.170
Neg logit contributions
xit-1.431
iac-1.206
cycles-1.185
cel-1.169
************-1.149
Token ($
Token ID7198
Feature activation-3.61e-02

Pos logit contributions
xit+0.349
cycles+0.289
iac+0.288
cel+0.285
************+0.278
Neg logit contributions
ruff-0.309
erity-0.303
 jammed-0.300
 Tanz-0.297
itent-0.287
Token10
Token ID940
Feature activation-2.96e-01

Pos logit contributions
ruff+0.023
erity+0.023
 jammed+0.023
 Tanz+0.022
itent+0.022
Neg logit contributions
xit-0.025
iac-0.021
cycles-0.021
cel-0.021
************-0.020
Token.
Token ID13
Feature activation+8.27e-02

Pos logit contributions
ruff+0.125
erity+0.121
 jammed+0.120
 Tanz+0.118
itent+0.112
Neg logit contributions
xit-0.273
iac-0.237
cycles-0.236
cel-0.235
************-0.230
Token6
Token ID21
Feature activation-1.59e-01

Pos logit contributions
xit+0.062
cycles+0.052
iac+0.052
cel+0.052
************+0.050
Neg logit contributions
ruff-0.049
erity-0.048
 jammed-0.047
 Tanz-0.047
itent-0.045
Token
Token ID447
Feature activation-2.47e-02

Pos logit contributions
xit+0.088
cycles+0.076
iac+0.076
cel+0.075
************+0.074
Neg logit contributions
ruff-0.044
erity-0.043
 jammed-0.042
 Tanz-0.042
itent-0.040
Token
Token ID247
Feature activation-3.59e-02

Pos logit contributions
ruff+0.017
erity+0.017
 jammed+0.017
 Tanz+0.017
itent+0.016
Neg logit contributions
xit-0.016
iac-0.013
cycles-0.013
cel-0.013
************-0.013
Tokent
Token ID83
Feature activation+2.67e-01

Pos logit contributions
ruff+0.023
erity+0.023
 jammed+0.022
 Tanz+0.022
itent+0.021
Neg logit contributions
xit-0.025
iac-0.021
cycles-0.021
cel-0.021
************-0.020
Token.
Token ID13
Feature activation-1.48e-01

Pos logit contributions
xit+0.181
iac+0.147
cycles+0.147
cel+0.146
************+0.142
Neg logit contributions
ruff-0.179
erity-0.176
 jammed-0.175
 Tanz-0.173
itent-0.167
Token Franklin
Token ID14021
Feature activation-5.15e-01

Pos logit contributions
ruff+0.090
erity+0.088
 jammed+0.087
 Tanz+0.086
itent+0.083
Neg logit contributions
xit-0.109
iac-0.091
cycles-0.091
cel-0.090
************-0.088
Token Del
Token ID4216
Feature activation-1.99e+00

Pos logit contributions
ruff+0.248
erity+0.242
 jammed+0.239
 Tanz+0.236
itent+0.225
Neg logit contributions
xit-0.446
iac-0.382
cycles-0.382
cel-0.380
************-0.371
Tokenano
Token ID5733
Feature activation-1.76e+00

Pos logit contributions
ruff+1.176
erity+1.145
 Tanz+1.144
 jammed+1.142
itent+1.088
Neg logit contributions
xit-1.487
iac-1.296
cycles-1.258
cel-1.252
************-1.218
Token Roosevelt
Token ID19297
Feature activation-1.76e-01

Pos logit contributions
ruff+0.563
erity+0.545
 Tanz+0.525
 jammed+0.523
itent+0.487
Neg logit contributions
xit-1.806
iac-1.629
cycles-1.590
cel-1.589
************-1.558
Token was
Token ID373
Feature activation-3.26e-01

Pos logit contributions
ruff+0.112
erity+0.110
 jammed+0.109
 Tanz+0.108
itent+0.104
Neg logit contributions
xit-0.124
iac-0.103
cycles-0.103
cel-0.102
************-0.099
Token credited
Token ID18141
Feature activation+8.67e-03

Pos logit contributions
ruff+0.209
erity+0.205
 jammed+0.203
 Tanz+0.201
itent+0.194
Neg logit contributions
xit-0.229
iac-0.189
cycles-0.189
cel-0.188
************-0.183
Token as
Token ID355
Feature activation+5.13e-02

Pos logit contributions
xit+0.006
iac+0.005
cycles+0.005
cel+0.005
************+0.005
Neg logit contributions
ruff-0.006
erity-0.006
 jammed-0.006
 Tanz-0.005
itent-0.005
Token go
Token ID467
Feature activation+1.19e-01

Pos logit contributions
ruff+0.111
erity+0.109
 jammed+0.108
 Tanz+0.107
itent+0.103
Neg logit contributions
xit-0.137
iac-0.114
cycles-0.114
cel-0.113
************-0.110
Token over
Token ID625
Feature activation+9.00e-02

Pos logit contributions
xit+0.082
cycles+0.068
iac+0.068
cel+0.067
************+0.065
Neg logit contributions
ruff-0.078
erity-0.077
 jammed-0.076
 Tanz-0.075
itent-0.073
Token some
Token ID617
Feature activation-1.37e-01

Pos logit contributions
xit+0.063
iac+0.052
cycles+0.052
cel+0.052
************+0.050
Neg logit contributions
ruff-0.058
erity-0.057
 jammed-0.056
 Tanz-0.056
itent-0.054
Token basic
Token ID4096
Feature activation-3.93e-01

Pos logit contributions
ruff+0.087
erity+0.085
 jammed+0.084
 Tanz+0.083
itent+0.080
Neg logit contributions
xit-0.098
iac-0.081
cycles-0.081
cel-0.081
************-0.078
Token dos
Token ID23430
Feature activation-5.54e-01

Pos logit contributions
ruff+0.230
erity+0.225
 jammed+0.223
 Tanz+0.221
itent+0.212
Neg logit contributions
xit-0.299
iac-0.250
cycles-0.250
cel-0.248
************-0.243
Token and
Token ID290
Feature activation-1.98e+00

Pos logit contributions
ruff+0.351
erity+0.344
 jammed+0.342
 Tanz+0.339
itent+0.326
Neg logit contributions
xit-0.395
iac-0.327
cycles-0.326
cel-0.324
************-0.315
Token don
Token ID836
Feature activation-9.59e-02

Pos logit contributions
erity+1.308
ruff+1.301
 Tanz+1.280
 jammed+1.261
ifle+1.241
Neg logit contributions
xit-1.350
cycles-1.117
iac-1.112
cel-1.111
************-1.076
Token't
Token ID470
Feature activation+3.68e-01

Pos logit contributions
ruff+0.043
erity+0.042
 jammed+0.042
 Tanz+0.041
itent+0.039
Neg logit contributions
xit-0.086
iac-0.074
cycles-0.074
cel-0.074
************-0.072
Tokens
Token ID82
Feature activation+1.98e-01

Pos logit contributions
xit+0.266
cycles+0.219
iac+0.219
cel+0.217
************+0.212
Neg logit contributions
ruff-0.230
erity-0.225
 jammed-0.224
 Tanz-0.222
itent-0.213
Token,
Token ID11
Feature activation-6.15e-02

Pos logit contributions
xit+0.139
cycles+0.115
iac+0.114
cel+0.113
************+0.110
Neg logit contributions
ruff-0.128
erity-0.125
 jammed-0.124
 Tanz-0.123
itent-0.119
Token using
Token ID1262
Feature activation-2.51e-01

Pos logit contributions
ruff+0.039
erity+0.038
 jammed+0.038
 Tanz+0.037
itent+0.036
Neg logit contributions
xit-0.044
iac-0.037
cycles-0.037
cel-0.036
************-0.035
TokenOP
Token ID3185
Feature activation+4.46e-01

Pos logit contributions
ruff+0.439
erity+0.428
 jammed+0.426
 Tanz+0.423
itent+0.409
Neg logit contributions
xit-0.410
iac-0.333
cycles-0.332
cel-0.329
************-0.320
TokenP
Token ID47
Feature activation-5.55e-01

Pos logit contributions
xit+0.329
cycles+0.274
iac+0.273
cel+0.270
************+0.264
Neg logit contributions
ruff-0.271
erity-0.267
 jammed-0.263
 Tanz-0.261
itent-0.251
Token
Token ID784
Feature activation-1.48e+00

Pos logit contributions
ruff+0.390
erity+0.380
 jammed+0.380
 Tanz+0.376
itent+0.365
Neg logit contributions
xit-0.356
iac-0.289
cycles-0.289
cel-0.287
************-0.278
Token European
Token ID3427
Feature activation+2.66e-01

Pos logit contributions
ruff+0.727
erity+0.689
 jammed+0.689
 Tanz+0.683
itent+0.654
Neg logit contributions
xit-1.294
cycles-1.101
cel-1.093
iac-1.092
 anim-1.076
Token Politics
Token ID17554
Feature activation-9.19e-01

Pos logit contributions
xit+0.206
cycles+0.173
iac+0.173
cel+0.172
************+0.167
Neg logit contributions
ruff-0.152
erity-0.150
 jammed-0.148
 Tanz-0.147
 Danger-0.141
Token and
Token ID290
Feature activation-1.97e+00

Pos logit contributions
ruff+0.594
 jammed+0.578
erity+0.578
 Tanz+0.573
itent+0.552
Neg logit contributions
xit-0.642
cycles-0.531
cel-0.527
iac-0.526
************-0.512
Token Policy
Token ID7820
Feature activation+4.19e-01

Pos logit contributions
ruff+1.553
erity+1.528
 jammed+1.515
 Tanz+1.506
itent+1.452
Neg logit contributions
xit-1.125
cycles-0.870
iac-0.864
cel-0.843
************-0.825
Token or
Token ID393
Feature activation-5.45e-01

Pos logit contributions
xit+0.302
iac+0.249
cycles+0.249
cel+0.247
************+0.240
Neg logit contributions
ruff-0.263
erity-0.258
 jammed-0.255
 Tanz-0.253
itent-0.244
Token the
Token ID262
Feature activation-6.34e-01

Pos logit contributions
ruff+0.359
erity+0.348
 jammed+0.348
 Tanz+0.344
itent+0.333
Neg logit contributions
xit-0.377
iac-0.309
cycles-0.309
cel-0.307
************-0.298
Token London
Token ID3576
Feature activation+3.54e-01

Pos logit contributions
ruff+0.395
erity+0.383
 jammed+0.383
 Tanz+0.377
itent+0.365
Neg logit contributions
xit-0.460
iac-0.382
cycles-0.381
cel-0.378
************-0.369
Token School
Token ID3961
Feature activation-6.44e-01

Pos logit contributions
xit+0.251
iac+0.208
cycles+0.207
cel+0.205
************+0.199
Neg logit contributions
ruff-0.224
erity-0.221
 jammed-0.219
 Tanz-0.217
 Danger-0.209
Token while
Token ID981
Feature activation+1.95e-01

Pos logit contributions
xit+0.296
cycles+0.245
iac+0.245
cel+0.243
************+0.236
Neg logit contributions
ruff-0.251
erity-0.246
 jammed-0.245
 Tanz-0.243
 Danger-0.234
Token CBS
Token ID11133
Feature activation-2.83e-01

Pos logit contributions
xit+0.137
cycles+0.113
iac+0.113
cel+0.112
************+0.109
Neg logit contributions
ruff-0.126
erity-0.123
 jammed-0.122
 Tanz-0.121
itent-0.117
Token'
Token ID6
Feature activation-1.39e-01

Pos logit contributions
ruff+0.165
erity+0.162
 jammed+0.160
 Tanz+0.159
itent+0.153
Neg logit contributions
xit-0.215
iac-0.180
cycles-0.180
cel-0.179
************-0.174
Token anchor
Token ID18021
Feature activation-8.56e-01

Pos logit contributions
ruff+0.090
erity+0.088
 jammed+0.088
 Tanz+0.087
itent+0.084
Neg logit contributions
xit-0.096
iac-0.079
cycles-0.079
cel-0.079
************-0.076
Token Scott
Token ID4746
Feature activation-7.66e-01

Pos logit contributions
ruff+0.559
erity+0.551
 jammed+0.542
 Tanz+0.536
itent+0.521
Neg logit contributions
xit-0.592
iac-0.489
cycles-0.485
cel-0.483
************-0.469
Token Pel
Token ID12903
Feature activation-1.97e+00

Pos logit contributions
ruff+0.497
erity+0.491
 jammed+0.485
 Tanz+0.479
itent+0.466
Neg logit contributions
xit-0.532
iac-0.440
cycles-0.436
cel-0.435
************-0.422
Tokenley
Token ID1636
Feature activation+2.63e-01

Pos logit contributions
 jammed+1.592
ruff+1.585
 Tanz+1.565
erity+1.559
 Danger+1.519
Neg logit contributions
xit-1.043
iac-0.828
cel-0.815
cycles-0.801
nan-0.776
Token is
Token ID318
Feature activation+2.34e-01

Pos logit contributions
xit+0.186
cycles+0.154
iac+0.153
cel+0.152
************+0.148
Neg logit contributions
ruff-0.168
erity-0.165
 jammed-0.164
 Tanz-0.162
itent-0.156
Token leading
Token ID3756
Feature activation-4.05e-01

Pos logit contributions
xit+0.158
cycles+0.129
iac+0.129
cel+0.127
************+0.124
Neg logit contributions
ruff-0.157
erity-0.154
 jammed-0.153
 Tanz-0.152
itent-0.147
Token his
Token ID465
Feature activation-3.78e-01

Pos logit contributions
ruff+0.259
erity+0.254
 jammed+0.252
 Tanz+0.250
itent+0.241
Neg logit contributions
xit-0.285
iac-0.235
cycles-0.235
cel-0.233
************-0.227
Token network
Token ID3127
Feature activation-2.40e-01

Pos logit contributions
ruff+0.245
erity+0.241
 jammed+0.238
 Tanz+0.237
itent+0.228
Neg logit contributions
xit-0.263
iac-0.216
cycles-0.216
cel-0.214
************-0.208
Token E
Token ID412
Feature activation+3.62e-01

Pos logit contributions
ruff+0.799
erity+0.784
 jammed+0.776
 Tanz+0.770
ifle+0.748
Neg logit contributions
xit-0.716
cycles-0.583
iac-0.575
cel-0.571
 anim-0.554
Token-
Token ID12
Feature activation-9.26e-01

Pos logit contributions
xit+0.253
cycles+0.208
iac+0.207
cel+0.205
************+0.200
Neg logit contributions
ruff-0.236
erity-0.231
 jammed-0.229
 Tanz-0.227
itent-0.219
Tokenmail
Token ID4529
Feature activation-5.37e-01

Pos logit contributions
ruff+0.610
erity+0.608
 jammed+0.602
 Tanz+0.596
itent+0.574
Neg logit contributions
xit-0.633
cycles-0.520
cel-0.520
iac-0.518
************-0.498
Token this
Token ID428
Feature activation+1.30e-01

Pos logit contributions
ruff+0.378
erity+0.373
 jammed+0.368
 Tanz+0.366
itent+0.355
Neg logit contributions
xit-0.343
cycles-0.278
iac-0.277
cel-0.275
************-0.266
Token to
Token ID284
Feature activation-2.49e-01

Pos logit contributions
xit+0.090
cycles+0.074
iac+0.074
cel+0.073
************+0.071
Neg logit contributions
ruff-0.085
erity-0.084
 jammed-0.083
 Tanz-0.082
itent-0.080
Token a
Token ID257
Feature activation-1.96e+00

Pos logit contributions
ruff+0.157
erity+0.153
 jammed+0.152
 Tanz+0.151
itent+0.145
Neg logit contributions
xit-0.178
iac-0.148
cycles-0.148
cel-0.147
************-0.143
Token friend
Token ID1545
Feature activation+1.02e-01

Pos logit contributions
ruff+1.210
erity+1.206
 Tanz+1.189
 jammed+1.169
ifle+1.135
Neg logit contributions
xit-1.398
cel-1.186
iac-1.166
cycles-1.156
************-1.136
Token Print
Token ID12578
Feature activation-5.21e-01

Pos logit contributions
xit+0.078
iac+0.066
cycles+0.066
cel+0.065
************+0.064
Neg logit contributions
ruff-0.059
erity-0.058
 jammed-0.057
 Tanz-0.057
itent-0.054
Tokenable
Token ID540
Feature activation+2.24e-01

Pos logit contributions
ruff+0.414
erity+0.411
 jammed+0.407
 Tanz+0.405
itent+0.393
Neg logit contributions
xit-0.285
cycles-0.221
iac-0.220
cel-0.218
************-0.210
Token version
Token ID2196
Feature activation-5.41e-01

Pos logit contributions
xit+0.157
cycles+0.130
iac+0.129
cel+0.128
************+0.125
Neg logit contributions
ruff-0.145
erity-0.141
 jammed-0.140
 Tanz-0.139
 Danger-0.134
Token<|endoftext|>
Token ID50256
Feature activation-2.41e-01

Pos logit contributions
ruff+0.288
erity+0.282
 jammed+0.279
 Tanz+0.275
itent+0.264
Neg logit contributions
xit-0.442
iac-0.374
cycles-0.373
cel-0.371
************-0.364
Token
Token ID198
Feature activation+3.05e-01

Pos logit contributions
xit+0.008
cycles+0.007
iac+0.007
cel+0.007
************+0.007
Neg logit contributions
ruff-0.007
erity-0.007
 jammed-0.007
 Tanz-0.007
itent-0.007
TokenFacebook
Token ID12025
Feature activation-2.45e-01

Pos logit contributions
xit+0.204
cycles+0.167
iac+0.167
cel+0.165
************+0.160
Neg logit contributions
ruff-0.207
erity-0.203
 jammed-0.202
 Tanz-0.199
 Danger-0.193
Token
Token ID198
Feature activation-2.21e-01

Pos logit contributions
ruff+0.152
erity+0.149
 jammed+0.148
 Tanz+0.146
itent+0.141
Neg logit contributions
xit-0.178
iac-0.148
cycles-0.148
cel-0.147
************-0.143
Token
Token ID198
Feature activation-9.34e-01

Pos logit contributions
ruff+0.137
erity+0.134
 jammed+0.133
 Tanz+0.132
itent+0.127
Neg logit contributions
xit-0.161
iac-0.133
cycles-0.133
cel-0.132
************-0.129
TokenSt
Token ID1273
Feature activation-1.60e+00

Pos logit contributions
ruff+0.693
erity+0.687
 Tanz+0.681
 jammed+0.678
itent+0.655
Neg logit contributions
xit-0.558
cycles-0.446
iac-0.446
cel-0.444
************-0.427
Tokenumble
Token ID10344
Feature activation-1.96e+00

Pos logit contributions
erity+0.899
ruff+0.895
 jammed+0.886
 Tanz+0.874
itent+0.849
Neg logit contributions
xit-1.235
iac-1.053
cel-1.043
cycles-1.035
************-1.020
TokenUpon
Token ID23792
Feature activation-8.31e-01

Pos logit contributions
erity+1.557
ruff+1.557
 Tanz+1.525
 jammed+1.525
itent+1.486
Neg logit contributions
xit-1.058
iac-0.849
cycles-0.837
cel-0.828
 anim-0.785
Token What
Token ID1867
Feature activation-9.79e-01

Pos logit contributions
ruff+0.507
erity+0.499
 jammed+0.490
 Tanz+0.486
itent+0.471
Neg logit contributions
xit-0.609
iac-0.510
cycles-0.507
cel-0.504
************-0.492
Token are
Token ID389
Feature activation+6.69e-01

Pos logit contributions
ruff+0.676
erity+0.669
 jammed+0.662
 Tanz+0.659
itent+0.636
Neg logit contributions
xit-0.636
cel-0.514
cycles-0.513
iac-0.513
************-0.501
Token these
Token ID777
Feature activation+5.75e-01

Pos logit contributions
xit+0.549
cycles+0.468
iac+0.464
cel+0.461
************+0.451
Neg logit contributions
ruff-0.355
 jammed-0.343
erity-0.343
 Tanz-0.338
 Danger-0.324
Token?
Token ID30
Feature activation-1.22e+00

Pos logit contributions
xit+0.373
cycles+0.302
iac+0.300
cel+0.298
************+0.289
Neg logit contributions
ruff-0.403
erity-0.395
 jammed-0.394
 Tanz-0.390
itent-0.377
Token Over
Token ID3827
Feature activation-5.54e-01

Pos logit contributions
ruff+0.383
erity+0.377
 jammed+0.373
 Tanz+0.369
itent+0.354
Neg logit contributions
xit-0.544
iac-0.461
cycles-0.457
cel-0.455
************-0.443
Token the
Token ID262
Feature activation-1.32e+00

Pos logit contributions
ruff+0.365
erity+0.361
 jammed+0.357
 Tanz+0.352
itent+0.342
Neg logit contributions
xit-0.379
iac-0.311
cycles-0.310
cel-0.308
************-0.299
Token C
Token ID327
Feature activation+1.61e-01

Pos logit contributions
ruff+1.011
erity+1.006
 jammed+0.995
 Tanz+0.986
itent+0.959
Neg logit contributions
xit-0.760
cel-0.598
iac-0.595
cycles-0.586
nan-0.564
Tokenuck
Token ID1347
Feature activation+3.96e-01

Pos logit contributions
xit+0.108
cycles+0.088
iac+0.088
cel+0.087
************+0.084
Neg logit contributions
ruff-0.110
erity-0.107
 jammed-0.107
 Tanz-0.106
itent-0.102
Tokenoo
Token ID2238
Feature activation-1.13e+00

Pos logit contributions
xit+0.249
cycles+0.200
iac+0.198
cel+0.197
************+0.192
Neg logit contributions
ruff-0.286
erity-0.279
 jammed-0.278
 Tanz-0.276
 Danger-0.267
Token's
Token ID338
Feature activation-1.95e+00

Pos logit contributions
ruff+0.711
erity+0.702
 jammed+0.698
 Tanz+0.685
itent+0.670
Neg logit contributions
xit-0.800
iac-0.661
cel-0.660
cycles-0.657
************-0.636
Token Nest
Token ID21420
Feature activation-7.46e-02

Pos logit contributions
ruff+1.219
erity+1.217
 jammed+1.203
 Tanz+1.175
itent+1.172
Neg logit contributions
xit-1.373
cel-1.149
iac-1.148
cycles-1.121
************-1.101
Token"
Token ID1
Feature activation+2.03e-01

Pos logit contributions
ruff+0.051
erity+0.050
 jammed+0.050
 Tanz+0.050
itent+0.048
Neg logit contributions
xit-0.049
iac-0.040
cycles-0.040
cel-0.039
************-0.038
Token --
Token ID1377
Feature activation-2.14e-01

Pos logit contributions
xit+0.146
cycles+0.121
iac+0.121
cel+0.120
************+0.117
Neg logit contributions
ruff-0.128
erity-0.125
 jammed-0.124
 Tanz-0.123
itent-0.119
Token two
Token ID734
Feature activation+2.47e-02

Pos logit contributions
ruff+0.134
erity+0.132
 jammed+0.131
 Tanz+0.130
itent+0.125
Neg logit contributions
xit-0.154
iac-0.127
cycles-0.127
cel-0.126
************-0.123
Token 1970
Token ID8069
Feature activation+2.30e-01

Pos logit contributions
xit+0.017
cycles+0.014
iac+0.014
cel+0.014
************+0.013
Neg logit contributions
ruff-0.016
erity-0.016
 jammed-0.016
 Tanz-0.016
itent-0.015
Token an
Token ID281
Feature activation-1.19e-01

Pos logit contributions
xit+0.018
cycles+0.015
iac+0.015
cel+0.015
************+0.015
Neg logit contributions
ruff-0.015
erity-0.015
 jammed-0.015
 Tanz-0.015
itent-0.014
Token article
Token ID2708
Feature activation+2.42e-02

Pos logit contributions
ruff+0.078
erity+0.076
 jammed+0.076
 Tanz+0.075
itent+0.072
Neg logit contributions
xit-0.083
iac-0.068
cycles-0.068
cel-0.068
************-0.066
Token published
Token ID3199
Feature activation+1.54e-01

Pos logit contributions
xit+0.017
cycles+0.014
iac+0.014
cel+0.013
************+0.013
Neg logit contributions
ruff-0.016
erity-0.016
 jammed-0.016
 Tanz-0.015
itent-0.015
Token in
Token ID287
Feature activation+6.16e-02

Pos logit contributions
xit+0.108
cycles+0.089
iac+0.089
cel+0.088
************+0.086
Neg logit contributions
ruff-0.099
erity-0.097
 jammed-0.097
 Tanz-0.096
itent-0.093
Token N
Token ID399
Feature activation+1.66e-01

Pos logit contributions
xit+0.043
cycles+0.035
iac+0.035
cel+0.035
************+0.034
Neg logit contributions
ruff-0.040
erity-0.039
 jammed-0.039
 Tanz-0.038
itent-0.037
Token.
Token ID13
Feature activation+1.18e+00

Pos logit contributions
xit+0.116
cycles+0.096
iac+0.095
cel+0.095
************+0.092
Neg logit contributions
ruff-0.108
erity-0.106
 jammed-0.105
 Tanz-0.104
itent-0.100
Token Eng
Token ID1985
Feature activation-3.41e-01

Pos logit contributions
xit+0.786
cycles+0.638
iac+0.632
cel+0.625
************+0.609
Neg logit contributions
ruff-0.805
 jammed-0.789
erity-0.787
 Tanz-0.782
 Danger-0.758
Tokenl
Token ID75
Feature activation-2.61e-01

Pos logit contributions
ruff+0.240
erity+0.237
 jammed+0.235
 Tanz+0.233
itent+0.226
Neg logit contributions
xit-0.217
iac-0.176
cycles-0.176
cel-0.174
************-0.168
Token.
Token ID13
Feature activation+3.35e-01

Pos logit contributions
ruff+0.169
erity+0.166
 jammed+0.165
 Tanz+0.163
itent+0.157
Neg logit contributions
xit-0.182
iac-0.150
cycles-0.149
cel-0.148
************-0.144
Token J
Token ID449
Feature activation+4.86e-01

Pos logit contributions
xit+0.236
cycles+0.194
iac+0.193
cel+0.192
************+0.187
Neg logit contributions
ruff-0.216
erity-0.211
 jammed-0.210
 Tanz-0.208
 Danger-0.201
Token.
Token ID13
Feature activation+8.34e-01

Pos logit contributions
xit+0.345
cycles+0.284
iac+0.282
cel+0.280
************+0.275
Neg logit contributions
ruff-0.310
erity-0.304
 jammed-0.303
 Tanz-0.298
 Danger-0.289
Token League
Token ID4041
Feature activation+4.53e-01

Pos logit contributions
xit+0.025
iac+0.018
cycles+0.018
cel+0.018
************+0.017
Neg logit contributions
ruff-0.046
erity-0.045
 jammed-0.045
 Tanz-0.045
itent-0.043
Token universities
Token ID11155
Feature activation-3.50e-01

Pos logit contributions
xit+0.307
iac+0.251
cycles+0.250
cel+0.247
************+0.241
Neg logit contributions
ruff-0.303
erity-0.297
 jammed-0.296
 Tanz-0.293
itent-0.283
Token.
Token ID13
Feature activation-1.08e-01

Pos logit contributions
ruff+0.226
erity+0.222
 jammed+0.220
 Tanz+0.218
itent+0.211
Neg logit contributions
xit-0.245
iac-0.202
cycles-0.202
cel-0.200
************-0.195
Token Photo
Token ID5555
Feature activation+4.85e-01

Pos logit contributions
ruff+0.067
erity+0.066
 jammed+0.065
 Tanz+0.065
itent+0.062
Neg logit contributions
xit-0.078
iac-0.065
cycles-0.065
cel-0.064
************-0.062
Token:
Token ID25
Feature activation+3.81e-01

Pos logit contributions
xit+0.351
cycles+0.290
iac+0.290
cel+0.287
************+0.280
Neg logit contributions
ruff-0.302
erity-0.296
 jammed-0.294
 Tanz-0.292
 Danger-0.280
Token Luis
Token ID20894
Feature activation+1.57e+00

Pos logit contributions
xit+0.271
cycles+0.224
iac+0.224
cel+0.222
************+0.216
Neg logit contributions
ruff-0.242
erity-0.237
 jammed-0.236
 Tanz-0.234
 Danger-0.225
Token Sin
Token ID10884
Feature activation+7.04e-01

Pos logit contributions
xit+1.113
cycles+0.928
iac+0.904
cel+0.894
************+0.887
Neg logit contributions
ruff-1.004
 Tanz-0.977
 jammed-0.973
erity-0.971
 Danger-0.951
Tokenco
Token ID1073
Feature activation-2.00e-02

Pos logit contributions
xit+0.500
cycles+0.411
iac+0.410
cel+0.406
************+0.400
Neg logit contributions
ruff-0.448
erity-0.439
 jammed-0.436
 Tanz-0.431
itent-0.418
Token/
Token ID14
Feature activation-5.01e-01

Pos logit contributions
ruff+0.012
erity+0.012
 jammed+0.011
 Tanz+0.011
itent+0.011
Neg logit contributions
xit-0.015
iac-0.013
cycles-0.013
cel-0.013
************-0.012
TokenLos
Token ID28903
Feature activation+3.43e-01

Pos logit contributions
ruff+0.297
erity+0.291
 jammed+0.289
 Tanz+0.285
itent+0.275
Neg logit contributions
xit-0.378
iac-0.317
cycles-0.316
cel-0.314
************-0.306
Token Angeles
Token ID5652
Feature activation+3.27e-01

Pos logit contributions
xit+0.254
cycles+0.211
iac+0.211
cel+0.209
************+0.204
Neg logit contributions
ruff-0.209
erity-0.204
 jammed-0.202
 Tanz-0.201
 Danger-0.193
Token migrants
Token ID12783
Feature activation+5.11e-01

Pos logit contributions
xit+0.834
cycles+0.696
iac+0.691
cel+0.688
************+0.678
Neg logit contributions
ruff-0.698
 jammed-0.682
 Tanz-0.680
erity-0.676
 Danger-0.654
Token 4
Token ID604
Feature activation+1.10e+00

Pos logit contributions
xit+0.361
cycles+0.299
iac+0.298
cel+0.295
************+0.288
Neg logit contributions
ruff-0.325
erity-0.319
 jammed-0.318
 Tanz-0.315
 Danger-0.305
Token ways
Token ID2842
Feature activation+3.91e-01

Pos logit contributions
xit+0.810
cycles+0.675
iac+0.673
cel+0.668
************+0.656
Neg logit contributions
ruff-0.662
erity-0.652
 jammed-0.645
 Tanz-0.641
 Danger-0.624
Token Hillary
Token ID5073
Feature activation+1.23e+00

Pos logit contributions
xit+0.271
cycles+0.224
iac+0.223
cel+0.221
************+0.216
Neg logit contributions
ruff-0.255
erity-0.249
 jammed-0.248
 Tanz-0.245
itent-0.237
Token looms
Token ID46234
Feature activation-5.50e-01

Pos logit contributions
xit+0.761
cycles+0.617
cel+0.610
iac+0.610
************+0.596
Neg logit contributions
ruff-0.884
erity-0.868
 jammed-0.866
 Tanz-0.844
 Danger-0.831
Token over
Token ID625
Feature activation+1.54e+00

Pos logit contributions
ruff+0.336
erity+0.330
 jammed+0.326
 Tanz+0.324
ifle+0.311
Neg logit contributions
xit-0.405
iac-0.338
cycles-0.338
cel-0.333
************-0.326
Token the
Token ID262
Feature activation+1.32e+00

Pos logit contributions
xit+1.153
cycles+0.983
iac+0.966
cel+0.958
nan+0.949
Neg logit contributions
ruff-0.905
 jammed-0.893
 Tanz-0.876
erity-0.873
itent-0.851
Token 2020
Token ID12131
Feature activation-1.59e-01

Pos logit contributions
xit+0.822
cycles+0.674
iac+0.673
cel+0.659
nan+0.644
Neg logit contributions
ruff-0.943
 jammed-0.929
erity-0.917
 Tanz-0.908
 Danger-0.895
Token race
Token ID3234
Feature activation+1.20e+00

Pos logit contributions
ruff+0.102
erity+0.101
 jammed+0.100
 Tanz+0.099
itent+0.095
Neg logit contributions
xit-0.112
iac-0.092
cycles-0.092
cel-0.091
************-0.089
Token Obama
Token ID2486
Feature activation+1.65e+00

Pos logit contributions
xit+0.918
cycles+0.773
iac+0.769
cel+0.768
************+0.745
Neg logit contributions
ruff-0.699
erity-0.685
 jammed-0.681
 Tanz-0.670
 Danger-0.652
Token goes
Token ID2925
Feature activation-7.91e-01

Pos logit contributions
xit+1.359
cycles+1.167
cel+1.156
iac+1.154
************+1.144
Neg logit contributions
ruff-0.857
 jammed-0.850
erity-0.842
 Tanz-0.828
 Danger-0.794
Token handling
Token ID9041
Feature activation-1.81e-01

Pos logit contributions
xit+0.188
iac+0.154
cycles+0.154
cel+0.152
************+0.148
Neg logit contributions
ruff-0.176
erity-0.173
 jammed-0.172
 Tanz-0.170
itent-0.164
Token),
Token ID828
Feature activation+7.54e-02

Pos logit contributions
ruff+0.111
erity+0.108
 jammed+0.108
 Tanz+0.107
itent+0.103
Neg logit contributions
xit-0.133
cycles-0.110
iac-0.110
cel-0.109
************-0.107
Token Speed
Token ID8729
Feature activation+6.29e-01

Pos logit contributions
xit+0.051
iac+0.042
cycles+0.042
cel+0.041
************+0.040
Neg logit contributions
ruff-0.050
erity-0.049
 jammed-0.049
 Tanz-0.049
itent-0.047
Token (
Token ID357
Feature activation-9.70e-02

Pos logit contributions
xit+0.441
iac+0.363
cycles+0.362
cel+0.360
************+0.350
Neg logit contributions
ruff-0.406
erity-0.397
 jammed-0.394
 Tanz-0.390
 Danger-0.378
Tokenfor
Token ID1640
Feature activation+1.35e-01

Pos logit contributions
ruff+0.059
erity+0.058
 jammed+0.057
 Tanz+0.057
itent+0.055
Neg logit contributions
xit-0.072
cycles-0.060
iac-0.060
cel-0.059
************-0.058
Token Drag
Token ID12697
Feature activation+1.15e+00

Pos logit contributions
xit+0.101
iac+0.084
cycles+0.084
cel+0.084
************+0.082
Neg logit contributions
ruff-0.080
erity-0.078
 jammed-0.078
 Tanz-0.077
itent-0.074
Tokenster
Token ID1706
Feature activation+5.51e-01

Pos logit contributions
xit+0.702
iac+0.554
cycles+0.549
cel+0.548
************+0.532
Neg logit contributions
ruff-0.852
 jammed-0.833
erity-0.831
 Tanz-0.821
 Danger-0.803
Token/
Token ID14
Feature activation+7.16e-02

Pos logit contributions
xit+0.385
iac+0.316
cycles+0.315
cel+0.313
************+0.306
Neg logit contributions
ruff-0.358
erity-0.350
 jammed-0.349
 Tanz-0.344
 Danger-0.333
TokenTop
Token ID9126
Feature activation+1.02e+00

Pos logit contributions
xit+0.050
iac+0.041
cycles+0.041
cel+0.041
************+0.040
Neg logit contributions
ruff-0.046
erity-0.045
 jammed-0.045
 Tanz-0.045
itent-0.043
Token Fuel
Token ID25483
Feature activation+5.23e-01

Pos logit contributions
xit+0.689
iac+0.559
cycles+0.559
cel+0.553
************+0.543
Neg logit contributions
ruff-0.693
erity-0.677
 jammed-0.674
 Tanz-0.667
 Danger-0.646
Token levels
Token ID2974
Feature activation-6.43e-03

Pos logit contributions
xit+0.380
iac+0.314
cycles+0.313
cel+0.312
************+0.304
Neg logit contributions
ruff-0.324
erity-0.317
 jammed-0.316
 Tanz-0.311
itent-0.301
Token.
Token ID13
Feature activation-1.76e-01

Pos logit contributions
ruff+0.028
erity+0.028
 jammed+0.028
 Tanz+0.027
itent+0.026
Neg logit contributions
xit-0.031
iac-0.026
cycles-0.026
cel-0.025
************-0.025
Token
Token ID198
Feature activation-2.86e-04

Pos logit contributions
ruff+0.108
erity+0.106
 jammed+0.105
 Tanz+0.104
itent+0.100
Neg logit contributions
xit-0.129
iac-0.107
cycles-0.107
cel-0.106
************-0.103
Token
Token ID198
Feature activation+1.37e-01

Pos logit contributions
ruff+0.000
erity+0.000
 jammed+0.000
 Tanz+0.000
itent+0.000
Neg logit contributions
xit-0.000
cycles-0.000
iac-0.000
cel-0.000
************-0.000
Token
Token ID447
Feature activation+2.81e-01

Pos logit contributions
xit+0.098
cycles+0.081
iac+0.081
cel+0.080
************+0.078
Neg logit contributions
ruff-0.087
erity-0.085
 jammed-0.084
 Tanz-0.084
itent-0.081
Token
Token ID250
Feature activation+1.87e-01

Pos logit contributions
xit+0.181
iac+0.146
cycles+0.146
cel+0.145
************+0.140
Neg logit contributions
ruff-0.198
erity-0.194
 jammed-0.193
 Tanz-0.191
itent-0.185
TokenSer
Token ID7089
Feature activation+1.33e+00

Pos logit contributions
xit+0.137
cycles+0.114
iac+0.114
cel+0.112
************+0.110
Neg logit contributions
ruff-0.115
erity-0.112
 jammed-0.111
 Tanz-0.110
itent-0.106
Tokenious
Token ID699
Feature activation+2.12e-01

Pos logit contributions
xit+0.840
cycles+0.673
iac+0.667
cel+0.663
************+0.648
Neg logit contributions
ruff-0.952
erity-0.937
 jammed-0.927
 Tanz-0.919
itent-0.894
Token questions
Token ID2683
Feature activation-1.36e-01

Pos logit contributions
xit+0.155
iac+0.129
cycles+0.129
cel+0.128
************+0.124
Neg logit contributions
ruff-0.130
erity-0.128
 jammed-0.127
 Tanz-0.125
itent-0.121
Token have
Token ID423
Feature activation+6.40e-02

Pos logit contributions
ruff+0.082
erity+0.080
 jammed+0.080
 Tanz+0.079
itent+0.076
Neg logit contributions
xit-0.102
iac-0.085
cycles-0.085
cel-0.084
************-0.082
Token been
Token ID587
Feature activation-3.24e-01

Pos logit contributions
xit+0.046
cycles+0.038
iac+0.038
cel+0.038
************+0.037
Neg logit contributions
ruff-0.040
erity-0.039
 jammed-0.039
 Tanz-0.039
itent-0.037
Token raised
Token ID4376
Feature activation-2.18e-01

Pos logit contributions
ruff+0.185
erity+0.181
 jammed+0.179
 Tanz+0.178
itent+0.171
Neg logit contributions
xit-0.251
iac-0.211
cycles-0.210
cel-0.209
************-0.204
Token standard
Token ID3210
Feature activation-3.15e-01

Pos logit contributions
ruff+0.021
erity+0.020
 jammed+0.020
 Tanz+0.020
itent+0.019
Neg logit contributions
xit-0.023
iac-0.019
cycles-0.019
cel-0.019
************-0.018
Token and
Token ID290
Feature activation-3.98e-02

Pos logit contributions
ruff+0.198
erity+0.194
 jammed+0.192
 Tanz+0.191
itent+0.184
Neg logit contributions
xit-0.226
iac-0.187
cycles-0.187
cel-0.185
************-0.180
Token is
Token ID318
Feature activation+9.33e-02

Pos logit contributions
ruff+0.025
erity+0.025
 jammed+0.025
 Tanz+0.024
itent+0.024
Neg logit contributions
xit-0.028
iac-0.023
cycles-0.023
cel-0.023
************-0.022
Token what
Token ID644
Feature activation+2.50e-02

Pos logit contributions
xit+0.066
cycles+0.054
iac+0.054
cel+0.054
************+0.052
Neg logit contributions
ruff-0.060
erity-0.059
 jammed-0.058
 Tanz-0.058
itent-0.056
Token investors
Token ID7713
Feature activation-8.34e-02

Pos logit contributions
xit+0.018
iac+0.015
cycles+0.015
cel+0.015
************+0.014
Neg logit contributions
ruff-0.016
erity-0.015
 jammed-0.015
 Tanz-0.015
itent-0.014
Token will
Token ID481
Feature activation-2.32e-02

Pos logit contributions
ruff+0.051
erity+0.050
 jammed+0.050
 Tanz+0.049
itent+0.047
Neg logit contributions
xit-0.061
iac-0.051
cycles-0.051
cel-0.051
************-0.049
Token continue
Token ID2555
Feature activation+4.49e-02

Pos logit contributions
ruff+0.014
erity+0.014
 jammed+0.014
 Tanz+0.014
itent+0.013
Neg logit contributions
xit-0.017
iac-0.014
cycles-0.014
cel-0.014
************-0.014
Token to
Token ID284
Feature activation+1.29e-01

Pos logit contributions
xit+0.031
iac+0.025
cycles+0.025
cel+0.025
************+0.024
Neg logit contributions
ruff-0.029
erity-0.029
 jammed-0.029
 Tanz-0.028
itent-0.027
Token watch
Token ID2342
Feature activation+2.24e-01

Pos logit contributions
xit+0.097
cycles+0.081
iac+0.081
cel+0.080
************+0.078
Neg logit contributions
ruff-0.077
erity-0.075
 jammed-0.075
 Tanz-0.074
itent-0.071
Token,
Token ID11
Feature activation+4.24e-01

Pos logit contributions
xit+0.156
cycles+0.129
iac+0.129
cel+0.127
************+0.124
Neg logit contributions
ruff-0.145
erity-0.142
 jammed-0.141
 Tanz-0.140
itent-0.135
Token primarily
Token ID7525
Feature activation+1.44e-01

Pos logit contributions
xit+0.288
cycles+0.236
iac+0.236
cel+0.233
************+0.227
Neg logit contributions
ruff-0.283
erity-0.278
 jammed-0.276
 Tanz-0.274
itent-0.264
Token has
Token ID468
Feature activation+2.84e-01

Pos logit contributions
xit+0.088
iac+0.073
cycles+0.073
cel+0.072
************+0.070
Neg logit contributions
ruff-0.074
erity-0.072
 jammed-0.072
 Tanz-0.071
itent-0.068
Token commanded
Token ID22419
Feature activation+2.37e-01

Pos logit contributions
xit+0.207
cycles+0.172
iac+0.171
cel+0.170
************+0.165
Neg logit contributions
ruff-0.176
erity-0.172
 jammed-0.171
 Tanz-0.169
itent-0.163
Token me
Token ID502
Feature activation+2.73e-01

Pos logit contributions
xit+0.184
cycles+0.155
iac+0.155
cel+0.153
************+0.150
Neg logit contributions
ruff-0.135
erity-0.132
 jammed-0.130
 Tanz-0.129
itent-0.124
Token to
Token ID284
Feature activation-1.04e-02

Pos logit contributions
xit+0.189
cycles+0.155
iac+0.155
cel+0.153
************+0.149
Neg logit contributions
ruff-0.178
erity-0.175
 jammed-0.174
 Tanz-0.172
itent-0.166
Token do
Token ID466
Feature activation+1.91e-01

Pos logit contributions
ruff+0.007
erity+0.007
 jammed+0.007
 Tanz+0.007
itent+0.007
Neg logit contributions
xit-0.007
iac-0.006
cycles-0.006
cel-0.005
************-0.005
Token.
Token ID13
Feature activation-1.32e-01

Pos logit contributions
xit+0.135
cycles+0.111
iac+0.111
cel+0.110
************+0.107
Neg logit contributions
ruff-0.123
erity-0.120
 jammed-0.119
 Tanz-0.118
itent-0.114
Token
Token ID198
Feature activation+1.84e-01

Pos logit contributions
ruff+0.080
erity+0.078
 jammed+0.078
 Tanz+0.077
itent+0.074
Neg logit contributions
xit-0.097
iac-0.081
cycles-0.081
cel-0.080
************-0.078
Token
Token ID198
Feature activation-3.36e-02

Pos logit contributions
xit+0.135
cycles+0.113
iac+0.112
cel+0.111
************+0.108
Neg logit contributions
ruff-0.112
erity-0.110
 jammed-0.109
 Tanz-0.108
itent-0.104
TokenI
Token ID40
Feature activation+9.02e-02

Pos logit contributions
ruff+0.021
erity+0.021
 jammed+0.021
 Tanz+0.021
itent+0.020
Neg logit contributions
xit-0.024
iac-0.020
cycles-0.020
cel-0.019
************-0.019
Token am
Token ID716
Feature activation+2.08e-01

Pos logit contributions
xit+0.062
cycles+0.051
iac+0.051
cel+0.050
************+0.049
Neg logit contributions
ruff-0.059
erity-0.058
 jammed-0.058
 Tanz-0.057
itent-0.055
Token going
Token ID1016
Feature activation-6.35e-02

Pos logit contributions
xit+0.144
cycles+0.118
iac+0.118
cel+0.117
************+0.114
Neg logit contributions
ruff-0.136
erity-0.134
 jammed-0.133
 Tanz-0.132
itent-0.127
Token he
Token ID339
Feature activation-1.90e-01

Pos logit contributions
xit+0.071
cycles+0.058
iac+0.058
cel+0.058
************+0.056
Neg logit contributions
ruff-0.063
erity-0.062
 jammed-0.061
 Tanz-0.061
itent-0.058
Token pitched
Token ID21730
Feature activation-1.27e-01

Pos logit contributions
ruff+0.122
erity+0.120
 jammed+0.119
 Tanz+0.118
itent+0.113
Neg logit contributions
xit-0.134
iac-0.110
cycles-0.110
cel-0.109
************-0.107
Token is
Token ID318
Feature activation-2.26e-01

Pos logit contributions
ruff+0.082
erity+0.080
 jammed+0.079
 Tanz+0.079
itent+0.076
Neg logit contributions
xit-0.090
iac-0.074
cycles-0.074
cel-0.073
************-0.071
Token a
Token ID257
Feature activation-2.02e-01

Pos logit contributions
ruff+0.146
erity+0.143
 jammed+0.142
 Tanz+0.140
itent+0.135
Neg logit contributions
xit-0.159
iac-0.131
cycles-0.131
cel-0.130
************-0.126
Token new
Token ID649
Feature activation+1.89e-01

Pos logit contributions
ruff+0.121
erity+0.118
 jammed+0.117
 Tanz+0.116
itent+0.112
Neg logit contributions
xit-0.151
iac-0.126
cycles-0.126
cel-0.125
************-0.122
Token ordinance
Token ID19784
Feature activation-4.64e-02

Pos logit contributions
xit+0.142
cycles+0.118
iac+0.118
cel+0.117
************+0.114
Neg logit contributions
ruff-0.113
erity-0.111
 jammed-0.110
 Tanz-0.109
itent-0.105
Token that
Token ID326
Feature activation+1.05e-01

Pos logit contributions
ruff+0.030
erity+0.029
 jammed+0.029
 Tanz+0.029
itent+0.027
Neg logit contributions
xit-0.033
iac-0.027
cycles-0.027
cel-0.027
************-0.026
Token would
Token ID561
Feature activation-5.35e-02

Pos logit contributions
xit+0.076
cycles+0.063
iac+0.063
cel+0.063
************+0.061
Neg logit contributions
ruff-0.065
erity-0.064
 jammed-0.063
 Tanz-0.063
itent-0.060
Token prohibit
Token ID20767
Feature activation+2.37e-01

Pos logit contributions
ruff+0.033
erity+0.032
 jammed+0.032
 Tanz+0.032
itent+0.030
Neg logit contributions
xit-0.039
iac-0.033
cycles-0.033
cel-0.032
************-0.031
Token sitting
Token ID5586
Feature activation-2.43e-01

Pos logit contributions
xit+0.166
cycles+0.136
iac+0.136
cel+0.135
************+0.131
Neg logit contributions
ruff-0.153
erity-0.150
 jammed-0.149
 Tanz-0.148
itent-0.142
Token and
Token ID290
Feature activation+2.36e-01

Pos logit contributions
ruff+0.156
erity+0.153
 jammed+0.152
 Tanz+0.151
itent+0.145
Neg logit contributions
xit-0.171
iac-0.141
cycles-0.141
cel-0.140
************-0.136
Token this
Token ID428
Feature activation+1.63e-01

Pos logit contributions
ruff+0.078
erity+0.076
 jammed+0.076
 Tanz+0.075
itent+0.072
Neg logit contributions
xit-0.084
iac-0.069
cycles-0.069
cel-0.068
************-0.067
Token idea
Token ID2126
Feature activation-2.70e-01

Pos logit contributions
xit+0.122
cycles+0.102
iac+0.102
cel+0.101
************+0.099
Neg logit contributions
ruff-0.097
erity-0.095
 jammed-0.095
 Tanz-0.094
itent-0.090
Token that
Token ID326
Feature activation+6.16e-02

Pos logit contributions
ruff+0.176
erity+0.173
 jammed+0.171
 Tanz+0.170
itent+0.164
Neg logit contributions
xit-0.187
iac-0.154
cycles-0.154
cel-0.153
************-0.148
Token there
Token ID612
Feature activation-8.77e-02

Pos logit contributions
xit+0.043
cycles+0.035
iac+0.035
cel+0.035
************+0.034
Neg logit contributions
ruff-0.040
erity-0.040
 jammed-0.039
 Tanz-0.039
itent-0.038
Token
Token ID447
Feature activation+3.90e-02

Pos logit contributions
ruff+0.058
erity+0.057
 jammed+0.056
 Tanz+0.056
itent+0.054
Neg logit contributions
xit-0.060
iac-0.049
cycles-0.049
cel-0.049
************-0.048
Token
Token ID247
Feature activation-8.77e-02

Pos logit contributions
xit+0.027
iac+0.022
cycles+0.022
cel+0.022
************+0.022
Neg logit contributions
ruff-0.025
erity-0.025
 jammed-0.025
 Tanz-0.024
itent-0.023
Tokens
Token ID82
Feature activation+2.65e-01

Pos logit contributions
ruff+0.055
erity+0.054
 jammed+0.054
 Tanz+0.053
itent+0.051
Neg logit contributions
xit-0.063
iac-0.052
cycles-0.052
cel-0.052
************-0.050
Token a
Token ID257
Feature activation+1.77e-01

Pos logit contributions
xit+0.187
cycles+0.154
iac+0.154
cel+0.152
************+0.148
Neg logit contributions
ruff-0.171
erity-0.167
 jammed-0.166
 Tanz-0.165
itent-0.159
Token love
Token ID1842
Feature activation+3.74e-01

Pos logit contributions
xit+0.119
cycles+0.097
iac+0.097
cel+0.096
************+0.093
Neg logit contributions
ruff-0.119
erity-0.117
 jammed-0.116
 Tanz-0.115
itent-0.111
Token affair
Token ID14669
Feature activation+5.02e-02

Pos logit contributions
xit+0.260
cycles+0.214
iac+0.214
cel+0.211
************+0.206
Neg logit contributions
ruff-0.243
erity-0.238
 jammed-0.237
 Tanz-0.235
itent-0.226
Token between
Token ID1022
Feature activation-6.42e-02

Pos logit contributions
xit+0.035
cycles+0.028
iac+0.028
cel+0.028
************+0.027
Neg logit contributions
ruff-0.033
erity-0.032
 jammed-0.032
 Tanz-0.032
itent-0.031
Token BIOS
Token ID27553
Feature activation+1.86e-01

Pos logit contributions
xit+0.237
iac+0.194
cycles+0.194
cel+0.192
************+0.187
Neg logit contributions
ruff-0.224
erity-0.220
 jammed-0.218
 Tanz-0.216
itent-0.209
Token gives
Token ID3607
Feature activation+4.30e-01

Pos logit contributions
xit+0.133
iac+0.110
cycles+0.110
cel+0.109
************+0.107
Neg logit contributions
ruff-0.117
erity-0.115
 jammed-0.114
 Tanz-0.113
itent-0.109
Token you
Token ID345
Feature activation+4.13e-02

Pos logit contributions
xit+0.298
cycles+0.245
iac+0.245
cel+0.243
************+0.236
Neg logit contributions
ruff-0.280
erity-0.275
 jammed-0.273
 Tanz-0.270
itent-0.261
Token an
Token ID281
Feature activation+1.14e-01

Pos logit contributions
xit+0.029
iac+0.024
cycles+0.024
cel+0.024
************+0.023
Neg logit contributions
ruff-0.026
erity-0.026
 jammed-0.026
 Tanz-0.025
itent-0.025
Token increased
Token ID3220
Feature activation+2.78e-01

Pos logit contributions
xit+0.084
cycles+0.070
iac+0.070
cel+0.069
************+0.067
Neg logit contributions
ruff-0.070
erity-0.068
 jammed-0.068
 Tanz-0.067
itent-0.065
Token Power
Token ID4333
Feature activation-1.80e-01

Pos logit contributions
xit+0.189
iac+0.155
cycles+0.154
cel+0.153
************+0.149
Neg logit contributions
ruff-0.185
erity-0.182
 jammed-0.181
 Tanz-0.179
itent-0.173
TokenT
Token ID51
Feature activation-3.27e-01

Pos logit contributions
ruff+0.113
erity+0.111
 jammed+0.110
 Tanz+0.109
itent+0.105
Neg logit contributions
xit-0.129
cycles-0.107
iac-0.107
cel-0.106
************-0.103
Tokenune
Token ID1726
Feature activation+6.33e-02

Pos logit contributions
ruff+0.204
erity+0.200
 jammed+0.199
 Tanz+0.197
itent+0.190
Neg logit contributions
xit-0.235
iac-0.195
cycles-0.194
cel-0.193
************-0.188
Token limit
Token ID4179
Feature activation+5.02e-02

Pos logit contributions
xit+0.045
iac+0.037
cycles+0.037
cel+0.037
************+0.036
Neg logit contributions
ruff-0.040
erity-0.040
 jammed-0.039
 Tanz-0.039
itent-0.037
Token (
Token ID357
Feature activation-4.36e-02

Pos logit contributions
xit+0.035
iac+0.029
cycles+0.029
cel+0.029
************+0.028
Neg logit contributions
ruff-0.032
erity-0.032
 jammed-0.031
 Tanz-0.031
itent-0.030
Tokenup
Token ID929
Feature activation+2.03e-01

Pos logit contributions
ruff+0.027
erity+0.027
 jammed+0.027
 Tanz+0.026
itent+0.025
Neg logit contributions
xit-0.031
iac-0.026
cycles-0.026
cel-0.026
************-0.025
Token of
Token ID286
Feature activation-1.74e-01

Pos logit contributions
xit+0.150
iac+0.123
cycles+0.123
cel+0.122
************+0.119
Neg logit contributions
ruff-0.136
erity-0.133
 jammed-0.133
 Tanz-0.131
itent-0.127
Token Peter
Token ID5613
Feature activation-1.92e-01

Pos logit contributions
ruff+0.110
erity+0.108
 jammed+0.107
 Tanz+0.106
itent+0.102
Neg logit contributions
xit-0.125
iac-0.103
cycles-0.103
cel-0.102
************-0.100
Token and
Token ID290
Feature activation+2.25e-01

Pos logit contributions
ruff+0.120
erity+0.118
 jammed+0.117
 Tanz+0.116
itent+0.112
Neg logit contributions
xit-0.138
iac-0.114
cycles-0.114
cel-0.113
************-0.110
Token I
Token ID314
Feature activation-5.88e-02

Pos logit contributions
xit+0.158
cycles+0.130
iac+0.130
cel+0.129
************+0.125
Neg logit contributions
ruff-0.145
erity-0.142
 jammed-0.141
 Tanz-0.140
 Danger-0.135
Token having
Token ID1719
Feature activation-1.37e-01

Pos logit contributions
ruff+0.036
erity+0.036
 jammed+0.035
 Tanz+0.035
itent+0.034
Neg logit contributions
xit-0.043
iac-0.036
cycles-0.036
cel-0.035
************-0.034
Token the
Token ID262
Feature activation-2.36e-01

Pos logit contributions
ruff+0.085
erity+0.083
 jammed+0.082
 Tanz+0.082
itent+0.079
Neg logit contributions
xit-0.100
iac-0.083
cycles-0.083
cel-0.082
************-0.080
Token conversation
Token ID5273
Feature activation-9.81e-02

Pos logit contributions
ruff+0.148
erity+0.146
 jammed+0.144
 Tanz+0.143
itent+0.138
Neg logit contributions
xit-0.169
iac-0.140
cycles-0.140
cel-0.139
************-0.135
Token of
Token ID286
Feature activation-5.02e-02

Pos logit contributions
ruff+0.062
erity+0.061
 jammed+0.061
 Tanz+0.060
itent+0.058
Neg logit contributions
xit-0.070
iac-0.058
cycles-0.058
cel-0.057
************-0.056
Token "
Token ID366
Feature activation-2.89e-01

Pos logit contributions
ruff+0.033
erity+0.032
 jammed+0.032
 Tanz+0.031
itent+0.030
Neg logit contributions
xit-0.035
iac-0.029
cycles-0.029
cel-0.028
************-0.028
TokenThis
Token ID1212
Feature activation+3.15e-01

Pos logit contributions
ruff+0.183
erity+0.180
 jammed+0.178
 Tanz+0.177
itent+0.170
Neg logit contributions
xit-0.206
cycles-0.170
iac-0.170
cel-0.169
************-0.164
Token guy
Token ID3516
Feature activation+2.96e-01

Pos logit contributions
xit+0.224
cycles+0.186
iac+0.185
cel+0.183
************+0.179
Neg logit contributions
ruff-0.200
erity-0.196
 jammed-0.195
 Tanz-0.193
itent-0.186
Token with
Token ID351
Feature activation-1.51e-01

Pos logit contributions
xit+0.013
iac+0.010
cycles+0.010
cel+0.010
************+0.010
Neg logit contributions
ruff-0.011
erity-0.010
 jammed-0.010
 Tanz-0.010
itent-0.010
Token his
Token ID465
Feature activation+9.14e-02

Pos logit contributions
ruff+0.097
erity+0.095
 jammed+0.095
 Tanz+0.094
itent+0.090
Neg logit contributions
xit-0.107
iac-0.088
cycles-0.088
cel-0.087
************-0.085
Token bl
Token ID698
Feature activation+5.22e-01

Pos logit contributions
xit+0.066
cycles+0.055
iac+0.055
cel+0.054
************+0.053
Neg logit contributions
ruff-0.057
erity-0.056
 jammed-0.055
 Tanz-0.055
itent-0.053
Tokenunders
Token ID41116
Feature activation-1.04e-02

Pos logit contributions
xit+0.345
cycles+0.282
iac+0.280
cel+0.277
************+0.269
Neg logit contributions
ruff-0.358
erity-0.351
 jammed-0.347
 Tanz-0.345
itent-0.335
Token on
Token ID319
Feature activation-3.00e-02

Pos logit contributions
ruff+0.006
erity+0.006
 jammed+0.006
 Tanz+0.006
itent+0.006
Neg logit contributions
xit-0.008
cycles-0.006
iac-0.006
cel-0.006
************-0.006
Token the
Token ID262
Feature activation-7.23e-01

Pos logit contributions
ruff+0.019
erity+0.019
 jammed+0.019
 Tanz+0.018
itent+0.018
Neg logit contributions
xit-0.021
iac-0.018
cycles-0.018
cel-0.017
************-0.017
Token Hillary
Token ID5073
Feature activation+7.92e-02

Pos logit contributions
ruff+0.444
erity+0.436
 jammed+0.428
 Tanz+0.426
itent+0.410
Neg logit contributions
xit-0.530
iac-0.440
cycles-0.439
cel-0.438
************-0.426
Token Clinton
Token ID2605
Feature activation-1.47e-01

Pos logit contributions
xit+0.049
cycles+0.039
iac+0.039
cel+0.039
************+0.038
Neg logit contributions
ruff-0.057
erity-0.056
 jammed-0.056
 Tanz-0.056
itent-0.054
Token case
Token ID1339
Feature activation+6.94e-02

Pos logit contributions
ruff+0.106
erity+0.105
 jammed+0.104
 Tanz+0.103
itent+0.100
Neg logit contributions
xit-0.092
iac-0.074
cycles-0.074
cel-0.073
************-0.071
Token reason
Token ID1738
Feature activation-4.00e-01

Pos logit contributions
xit+0.050
cycles+0.041
iac+0.041
cel+0.041
************+0.040
Neg logit contributions
ruff-0.043
erity-0.043
 jammed-0.042
 Tanz-0.042
itent-0.040
Token enough
Token ID1576
Feature activation-5.43e-01

Pos logit contributions
ruff+0.258
erity+0.253
 jammed+0.251
 Tanz+0.249
itent+0.240
Neg logit contributions
xit-0.280
iac-0.231
cycles-0.230
cel-0.229
************-0.222
Token up
Token ID510
Feature activation+9.16e-02

Pos logit contributions
xit+0.006
cycles+0.005
iac+0.005
cel+0.005
************+0.005
Neg logit contributions
ruff-0.005
erity-0.005
 jammed-0.005
 Tanz-0.005
itent-0.005
Token in
Token ID287
Feature activation+3.64e-01

Pos logit contributions
xit+0.065
cycles+0.053
iac+0.053
cel+0.053
************+0.051
Neg logit contributions
ruff-0.059
erity-0.058
 jammed-0.057
 Tanz-0.057
itent-0.055
Token the
Token ID262
Feature activation+4.17e-01

Pos logit contributions
xit+0.253
iac+0.207
cycles+0.207
cel+0.205
************+0.200
Neg logit contributions
ruff-0.237
erity-0.232
 jammed-0.231
 Tanz-0.229
 Danger-0.221
Token A
Token ID317
Feature activation+7.76e-01

Pos logit contributions
xit+0.265
cycles+0.213
iac+0.213
cel+0.210
************+0.203
Neg logit contributions
ruff-0.298
erity-0.292
 jammed-0.291
 Tanz-0.289
 Danger-0.279
Token gap
Token ID7625
Feature activation-1.61e-01

Pos logit contributions
xit+0.535
cycles+0.440
iac+0.438
cel+0.433
************+0.422
Neg logit contributions
ruff-0.512
erity-0.500
 jammed-0.499
 Tanz-0.492
itent-0.477
Token (
Token ID357
Feature activation-2.81e-01

Pos logit contributions
ruff+0.104
erity+0.102
 jammed+0.101
 Tanz+0.100
itent+0.097
Neg logit contributions
xit-0.113
iac-0.093
cycles-0.093
cel-0.092
************-0.090
Tokenbetween
Token ID23395
Feature activation-8.28e-02

Pos logit contributions
ruff+0.180
erity+0.177
 jammed+0.175
 Tanz+0.174
itent+0.168
Neg logit contributions
xit-0.197
cycles-0.163
iac-0.163
cel-0.161
************-0.157
Token the
Token ID262
Feature activation+9.73e-02

Pos logit contributions
ruff+0.055
erity+0.054
 jammed+0.053
 Tanz+0.053
itent+0.051
Neg logit contributions
xit-0.057
iac-0.047
cycles-0.047
cel-0.046
************-0.045
Token center
Token ID3641
Feature activation-2.01e-01

Pos logit contributions
xit+0.064
iac+0.052
cycles+0.052
cel+0.051
************+0.050
Neg logit contributions
ruff-0.067
erity-0.066
 jammed-0.066
 Tanz-0.065
itent-0.063
Token and
Token ID290
Feature activation+4.04e-01

Pos logit contributions
ruff+0.127
erity+0.124
 jammed+0.123
 Tanz+0.122
itent+0.118
Neg logit contributions
xit-0.143
iac-0.119
cycles-0.118
cel-0.117
************-0.114
Token guard
Token ID4860
Feature activation-3.01e-01

Pos logit contributions
xit+0.269
iac+0.219
cycles+0.219
cel+0.217
************+0.210
Neg logit contributions
ruff-0.275
erity-0.270
 jammed-0.269
 Tanz-0.266
 Danger-0.257
Token our
Token ID674
Feature activation-2.87e-01

Pos logit contributions
ruff+0.141
erity+0.138
 jammed+0.137
 Tanz+0.136
itent+0.131
Neg logit contributions
xit-0.168
iac-0.139
cycles-0.139
cel-0.138
************-0.135
Token future
Token ID2003
Feature activation-1.07e-01

Pos logit contributions
ruff+0.166
erity+0.163
 jammed+0.161
 Tanz+0.160
itent+0.153
Neg logit contributions
xit-0.220
iac-0.184
cycles-0.184
cel-0.183
************-0.178
Token vision
Token ID5761
Feature activation+1.30e-01

Pos logit contributions
ruff+0.068
erity+0.067
 jammed+0.066
 Tanz+0.066
itent+0.063
Neg logit contributions
xit-0.076
iac-0.063
cycles-0.063
cel-0.063
************-0.061
Token to
Token ID284
Feature activation-1.98e-02

Pos logit contributions
xit+0.091
cycles+0.075
iac+0.075
cel+0.074
************+0.073
Neg logit contributions
ruff-0.083
erity-0.082
 jammed-0.081
 Tanz-0.080
itent-0.077
Token create
Token ID2251
Feature activation-3.09e-01

Pos logit contributions
ruff+0.012
erity+0.012
 jammed+0.012
 Tanz+0.012
itent+0.011
Neg logit contributions
xit-0.015
iac-0.012
cycles-0.012
cel-0.012
************-0.012
Token stores
Token ID7000
Feature activation-3.48e-01

Pos logit contributions
ruff+0.194
erity+0.190
 jammed+0.188
 Tanz+0.187
itent+0.180
Neg logit contributions
xit-0.222
iac-0.184
cycles-0.184
cel-0.182
************-0.177
Token which
Token ID543
Feature activation+1.30e-01

Pos logit contributions
ruff+0.225
erity+0.221
 jammed+0.219
 Tanz+0.217
itent+0.209
Neg logit contributions
xit-0.243
iac-0.200
cycles-0.200
cel-0.198
************-0.193
Token are
Token ID389
Feature activation-1.74e-01

Pos logit contributions
xit+0.093
cycles+0.077
iac+0.077
cel+0.076
************+0.074
Neg logit contributions
ruff-0.082
erity-0.081
 jammed-0.080
 Tanz-0.079
itent-0.077
Token carbon
Token ID6588
Feature activation-3.90e-01

Pos logit contributions
ruff+0.110
erity+0.108
 jammed+0.107
 Tanz+0.106
itent+0.102
Neg logit contributions
xit-0.125
iac-0.103
cycles-0.103
cel-0.102
************-0.099
Token neutral
Token ID8500
Feature activation-1.24e-02

Pos logit contributions
ruff+0.304
erity+0.300
 jammed+0.297
 Tanz+0.296
itent+0.287
Neg logit contributions
xit-0.221
iac-0.173
cycles-0.172
cel-0.171
************-0.164
Token."
Token ID526
Feature activation-1.62e-01

Pos logit contributions
ruff+0.008
erity+0.008
 jammed+0.008
 Tanz+0.008
itent+0.007
Neg logit contributions
xit-0.009
iac-0.007
cycles-0.007
cel-0.007
************-0.007
Token areas
Token ID3006
Feature activation+3.15e-02

Pos logit contributions
xit+0.000
cycles+0.000
iac+0.000
cel+0.000
************+0.000
Neg logit contributions
ruff-0.000
erity-0.000
 jammed-0.000
 Tanz-0.000
itent-0.000
Token that
Token ID326
Feature activation-5.55e-02

Pos logit contributions
xit+0.022
cycles+0.018
iac+0.018
cel+0.018
************+0.018
Neg logit contributions
ruff-0.020
erity-0.020
 jammed-0.020
 Tanz-0.019
itent-0.019
Token don
Token ID836
Feature activation-4.74e-02

Pos logit contributions
ruff+0.036
erity+0.036
 jammed+0.035
 Tanz+0.035
itent+0.034
Neg logit contributions
xit-0.038
iac-0.032
cycles-0.032
cel-0.031
************-0.030
Token
Token ID447
Feature activation-5.41e-02

Pos logit contributions
ruff+0.024
erity+0.024
 jammed+0.023
 Tanz+0.023
itent+0.022
Neg logit contributions
xit-0.040
iac-0.034
cycles-0.034
cel-0.033
************-0.033
Token
Token ID247
Feature activation-5.77e-02

Pos logit contributions
ruff+0.035
erity+0.035
 jammed+0.034
 Tanz+0.034
itent+0.033
Neg logit contributions
xit-0.038
iac-0.031
cycles-0.031
cel-0.031
************-0.030
Tokent
Token ID83
Feature activation-2.10e-01

Pos logit contributions
ruff+0.029
erity+0.029
 jammed+0.028
 Tanz+0.028
itent+0.027
Neg logit contributions
xit-0.048
iac-0.041
cycles-0.041
cel-0.041
************-0.040
Token necessarily
Token ID6646
Feature activation-2.73e-01

Pos logit contributions
ruff+0.135
erity+0.133
 jammed+0.132
 Tanz+0.131
itent+0.126
Neg logit contributions
xit-0.147
iac-0.121
cycles-0.121
cel-0.120
************-0.117
Token have
Token ID423
Feature activation+2.47e-01

Pos logit contributions
ruff+0.168
erity+0.165
 jammed+0.163
 Tanz+0.162
itent+0.156
Neg logit contributions
xit-0.199
iac-0.165
cycles-0.165
cel-0.164
************-0.160
Token more
Token ID517
Feature activation+2.26e-01

Pos logit contributions
xit+0.176
cycles+0.146
iac+0.145
cel+0.144
************+0.140
Neg logit contributions
ruff-0.156
erity-0.153
 jammed-0.152
 Tanz-0.151
itent-0.145
Token people
Token ID661
Feature activation+8.08e-02

Pos logit contributions
xit+0.163
cycles+0.135
iac+0.135
cel+0.134
************+0.130
Neg logit contributions
ruff-0.142
erity-0.139
 jammed-0.138
 Tanz-0.137
itent-0.131
Token,
Token ID11
Feature activation+8.52e-02

Pos logit contributions
xit+0.058
cycles+0.047
iac+0.047
cel+0.047
************+0.046
Neg logit contributions
ruff-0.051
erity-0.050
 jammed-0.050
 Tanz-0.049
itent-0.048
Token,
Token ID11
Feature activation-2.68e-01

Pos logit contributions
ruff+0.143
erity+0.140
 jammed+0.139
 Tanz+0.138
itent+0.133
Neg logit contributions
xit-0.158
iac-0.131
cycles-0.130
cel-0.130
************-0.126
Token which
Token ID543
Feature activation+8.61e-02

Pos logit contributions
ruff+0.167
erity+0.164
 jammed+0.162
 Tanz+0.161
itent+0.156
Neg logit contributions
xit-0.193
iac-0.160
cycles-0.159
cel-0.158
************-0.154
Token you
Token ID345
Feature activation-5.68e-01

Pos logit contributions
xit+0.062
cycles+0.052
iac+0.052
cel+0.051
************+0.050
Neg logit contributions
ruff-0.054
erity-0.052
 jammed-0.052
 Tanz-0.052
itent-0.050
Token might
Token ID1244
Feature activation-1.07e+00

Pos logit contributions
ruff+0.352
erity+0.347
 jammed+0.344
 Tanz+0.342
itent+0.331
Neg logit contributions
xit-0.410
iac-0.340
cycles-0.339
cel-0.338
************-0.329
Token want
Token ID765
Feature activation-8.13e-01

Pos logit contributions
ruff+0.729
erity+0.715
 jammed+0.710
 Tanz+0.706
itent+0.684
Neg logit contributions
xit-0.701
iac-0.577
cycles-0.573
cel-0.568
************-0.556
Token to
Token ID284
Feature activation-1.50e+00

Pos logit contributions
ruff+0.554
erity+0.540
 Tanz+0.538
 jammed+0.537
ifle+0.516
Neg logit contributions
xit-0.542
iac-0.444
cycles-0.442
cel-0.441
************-0.427
Token per
Token ID583
Feature activation+1.09e-01

Pos logit contributions
ruff+0.941
erity+0.925
 jammed+0.902
 Tanz+0.896
itent+0.863
Neg logit contributions
xit-1.081
cycles-0.909
iac-0.907
cel-0.891
 anim-0.873
Tokenuse
Token ID1904
Feature activation-5.03e-01

Pos logit contributions
xit+0.091
cycles+0.078
iac+0.078
cel+0.077
************+0.075
Neg logit contributions
ruff-0.056
erity-0.054
 jammed-0.054
 Tanz-0.053
itent-0.051
Token.
Token ID13
Feature activation-1.07e+00

Pos logit contributions
ruff+0.329
erity+0.324
 jammed+0.321
 Tanz+0.318
itent+0.308
Neg logit contributions
xit-0.347
iac-0.285
cycles-0.285
cel-0.282
************-0.274
Token Here
Token ID3423
Feature activation-3.22e-01

Pos logit contributions
ruff+0.815
erity+0.803
 jammed+0.798
 Tanz+0.789
itent+0.774
Neg logit contributions
xit-0.616
iac-0.496
cycles-0.490
cel-0.487
************-0.472
Token is
Token ID318
Feature activation+1.99e-02

Pos logit contributions
ruff+0.208
erity+0.204
 jammed+0.203
 Tanz+0.201
itent+0.194
Neg logit contributions
xit-0.225
iac-0.185
cycles-0.185
cel-0.184
************-0.179
Token 30
Token ID1542
Feature activation+1.58e-01

Pos logit contributions
xit+0.164
cycles+0.135
iac+0.135
cel+0.134
************+0.131
Neg logit contributions
ruff-0.149
erity-0.146
 jammed-0.145
 Tanz-0.144
itent-0.139
Token.
Token ID13
Feature activation+2.35e-01

Pos logit contributions
xit+0.112
iac+0.092
cycles+0.092
cel+0.091
************+0.089
Neg logit contributions
ruff-0.101
erity-0.099
 jammed-0.098
 Tanz-0.097
itent-0.094
Token After
Token ID2293
Feature activation+4.02e-01

Pos logit contributions
xit+0.174
cycles+0.145
iac+0.145
cel+0.143
************+0.140
Neg logit contributions
ruff-0.143
erity-0.140
 jammed-0.139
 Tanz-0.138
 Danger-0.132
Token I
Token ID314
Feature activation+1.85e-01

Pos logit contributions
xit+0.287
cycles+0.237
iac+0.237
cel+0.235
************+0.229
Neg logit contributions
ruff-0.254
erity-0.249
 jammed-0.248
 Tanz-0.245
 Danger-0.236
Token joined
Token ID5399
Feature activation+2.41e-01

Pos logit contributions
xit+0.128
cycles+0.106
iac+0.106
cel+0.104
************+0.102
Neg logit contributions
ruff-0.121
erity-0.118
 jammed-0.118
 Tanz-0.116
itent-0.112
Token Pf
Token ID38477
Feature activation-2.26e+00

Pos logit contributions
xit+0.168
cycles+0.138
iac+0.138
cel+0.136
************+0.133
Neg logit contributions
ruff-0.157
erity-0.154
 jammed-0.153
 Tanz-0.152
itent-0.146
Tokenizer
Token ID7509
Feature activation+2.71e-01

Pos logit contributions
ruff+0.516
erity+0.476
 jammed+0.476
 Tanz+0.457
 Danger+0.416
Neg logit contributions
xit-2.515
iac-2.267
cel-2.250
cycles-2.247
nan-2.212
Token Pharmaceutical
Token ID37175
Feature activation+9.33e-03

Pos logit contributions
xit+0.193
cycles+0.159
iac+0.159
cel+0.158
************+0.154
Neg logit contributions
ruff-0.171
erity-0.168
 jammed-0.167
 Tanz-0.165
itent-0.159
Tokens
Token ID82
Feature activation+1.91e-01

Pos logit contributions
xit+0.007
iac+0.005
cycles+0.005
cel+0.005
************+0.005
Neg logit contributions
ruff-0.006
erity-0.006
 jammed-0.006
 Tanz-0.006
itent-0.006
Token,
Token ID11
Feature activation+2.32e-02

Pos logit contributions
xit+0.136
cycles+0.112
iac+0.112
cel+0.111
************+0.108
Neg logit contributions
ruff-0.121
erity-0.119
 jammed-0.118
 Tanz-0.117
itent-0.113
Token and
Token ID290
Feature activation-1.67e-02

Pos logit contributions
xit+0.017
iac+0.014
cycles+0.014
cel+0.014
************+0.014
Neg logit contributions
ruff-0.014
erity-0.014
 jammed-0.014
 Tanz-0.014
itent-0.013
Token position
Token ID2292
Feature activation-4.62e-01

Pos logit contributions
ruff+0.137
erity+0.134
 jammed+0.134
 Tanz+0.132
itent+0.128
Neg logit contributions
xit-0.125
iac-0.101
cycles-0.101
cel-0.100
************-0.097
Token of
Token ID286
Feature activation-3.90e-02

Pos logit contributions
ruff+0.304
erity+0.297
 jammed+0.296
 Tanz+0.295
itent+0.284
Neg logit contributions
xit-0.317
iac-0.260
cycles-0.259
cel-0.258
************-0.251
Token EUR
Token ID27526
Feature activation-6.29e-01

Pos logit contributions
ruff+0.031
erity+0.030
 jammed+0.030
 Tanz+0.030
itent+0.029
Neg logit contributions
xit-0.021
iac-0.017
cycles-0.017
cel-0.016
************-0.016
TokenOP
Token ID3185
Feature activation+4.46e-01

Pos logit contributions
ruff+0.439
erity+0.428
 jammed+0.426
 Tanz+0.423
itent+0.409
Neg logit contributions
xit-0.410
iac-0.333
cycles-0.332
cel-0.329
************-0.320
TokenP
Token ID47
Feature activation-5.55e-01

Pos logit contributions
xit+0.329
cycles+0.274
iac+0.273
cel+0.270
************+0.264
Neg logit contributions
ruff-0.271
erity-0.267
 jammed-0.263
 Tanz-0.261
itent-0.251
Token
Token ID784
Feature activation-1.48e+00

Pos logit contributions
ruff+0.390
erity+0.380
 jammed+0.380
 Tanz+0.376
itent+0.365
Neg logit contributions
xit-0.356
iac-0.289
cycles-0.289
cel-0.287
************-0.278
Token European
Token ID3427
Feature activation+2.66e-01

Pos logit contributions
ruff+0.727
erity+0.689
 jammed+0.689
 Tanz+0.683
itent+0.654
Neg logit contributions
xit-1.294
cycles-1.101
cel-1.093
iac-1.092
 anim-1.076
Token Politics
Token ID17554
Feature activation-9.19e-01

Pos logit contributions
xit+0.206
cycles+0.173
iac+0.173
cel+0.172
************+0.167
Neg logit contributions
ruff-0.152
erity-0.150
 jammed-0.148
 Tanz-0.147
 Danger-0.141
Token and
Token ID290
Feature activation-1.97e+00

Pos logit contributions
ruff+0.594
 jammed+0.578
erity+0.578
 Tanz+0.573
itent+0.552
Neg logit contributions
xit-0.642
cycles-0.531
cel-0.527
iac-0.526
************-0.512
Token Policy
Token ID7820
Feature activation+4.19e-01

Pos logit contributions
ruff+1.553
erity+1.528
 jammed+1.515
 Tanz+1.506
itent+1.452
Neg logit contributions
xit-1.125
cycles-0.870
iac-0.864
cel-0.843
************-0.825
Token or
Token ID393
Feature activation-5.45e-01

Pos logit contributions
xit+0.302
iac+0.249
cycles+0.249
cel+0.247
************+0.240
Neg logit contributions
ruff-0.263
erity-0.258
 jammed-0.255
 Tanz-0.253
itent-0.244
Token seems
Token ID2331
Feature activation+6.91e-02

Pos logit contributions
xit+0.045
cycles+0.038
iac+0.038
cel+0.037
************+0.036
Neg logit contributions
ruff-0.038
erity-0.037
 jammed-0.037
 Tanz-0.037
itent-0.035
Token the
Token ID262
Feature activation+6.78e-02

Pos logit contributions
xit+0.048
cycles+0.039
iac+0.039
cel+0.039
************+0.038
Neg logit contributions
ruff-0.045
erity-0.044
 jammed-0.044
 Tanz-0.043
itent-0.042
Token United
Token ID1578
Feature activation-3.40e-02

Pos logit contributions
xit+0.049
cycles+0.040
iac+0.040
cel+0.040
************+0.039
Neg logit contributions
ruff-0.043
erity-0.042
 jammed-0.041
 Tanz-0.041
itent-0.040
Token States
Token ID1829
Feature activation-4.43e-01

Pos logit contributions
ruff+0.022
erity+0.021
 jammed+0.021
 Tanz+0.021
itent+0.020
Neg logit contributions
xit-0.024
iac-0.020
cycles-0.020
cel-0.020
************-0.019
Token Conference
Token ID8785
Feature activation-9.16e-01

Pos logit contributions
ruff+0.258
erity+0.253
 jammed+0.250
 Tanz+0.248
itent+0.238
Neg logit contributions
xit-0.338
iac-0.284
cycles-0.283
cel-0.281
************-0.274
Token of
Token ID286
Feature activation-2.19e+00

Pos logit contributions
ruff+0.609
erity+0.596
 jammed+0.592
 Tanz+0.588
itent+0.567
Neg logit contributions
xit-0.625
iac-0.512
cycles-0.510
cel-0.507
************-0.492
Token Catholic
Token ID7835
Feature activation-4.64e-01

Pos logit contributions
ruff+1.619
erity+1.599
 jammed+1.557
 Tanz+1.551
ifle+1.517
Neg logit contributions
xit-1.331
iac-1.085
cycles-1.072
cel-1.066
 anim-1.017
Token B
Token ID347
Feature activation+7.18e-01

Pos logit contributions
ruff+0.394
erity+0.388
 jammed+0.386
 Tanz+0.384
ifle+0.373
Neg logit contributions
xit-0.231
iac-0.175
cycles-0.174
cel-0.172
************-0.164
Tokenishops
Token ID21863
Feature activation-2.33e-01

Pos logit contributions
xit+0.559
cycles+0.469
iac+0.467
cel+0.463
************+0.455
Neg logit contributions
ruff-0.410
erity-0.399
 jammed-0.396
 Tanz-0.390
itent-0.377
Token (
Token ID357
Feature activation+1.65e-01

Pos logit contributions
ruff+0.146
erity+0.143
 jammed+0.142
 Tanz+0.141
itent+0.136
Neg logit contributions
xit-0.168
iac-0.139
cycles-0.139
cel-0.138
************-0.134
TokenUS
Token ID2937
Feature activation-2.75e-01

Pos logit contributions
xit+0.097
cycles+0.077
iac+0.077
cel+0.076
************+0.073
Neg logit contributions
ruff-0.125
erity-0.123
 jammed-0.122
 Tanz-0.121
itent-0.117
Token Lag
Token ID21003
Feature activation+3.02e-01

Pos logit contributions
xit+0.211
iac+0.135
cycles+0.134
cel+0.131
************+0.123
Neg logit contributions
ruff-0.623
erity-0.612
 jammed-0.611
 Tanz-0.607
 Danger-0.594
Tokenoon
Token ID2049
Feature activation+2.83e-01

Pos logit contributions
xit+0.151
cycles+0.113
iac+0.113
cel+0.112
************+0.107
Neg logit contributions
ruff-0.255
erity-0.251
 jammed-0.250
 Tanz-0.248
itent-0.242
Token,
Token ID11
Feature activation+4.91e-02

Pos logit contributions
xit+0.203
cycles+0.168
iac+0.168
cel+0.166
************+0.162
Neg logit contributions
ruff-0.178
erity-0.174
 jammed-0.173
 Tanz-0.172
itent-0.165
Token Dr
Token ID1583
Feature activation-2.71e-02

Pos logit contributions
xit+0.035
cycles+0.029
iac+0.029
cel+0.029
************+0.028
Neg logit contributions
ruff-0.031
erity-0.030
 jammed-0.030
 Tanz-0.030
itent-0.029
Token J
Token ID449
Feature activation-2.67e-01

Pos logit contributions
ruff+0.018
erity+0.017
 jammed+0.017
 Tanz+0.017
itent+0.016
Neg logit contributions
xit-0.019
iac-0.016
cycles-0.016
cel-0.015
************-0.015
Tokenek
Token ID988
Feature activation-1.61e+00

Pos logit contributions
ruff+0.169
erity+0.167
 jammed+0.165
 Tanz+0.164
itent+0.157
Neg logit contributions
xit-0.189
iac-0.157
cycles-0.156
cel-0.155
************-0.151
Tokenyll
Token ID25727
Feature activation-4.19e-01

Pos logit contributions
ruff+0.520
erity+0.498
 jammed+0.493
 Tanz+0.485
itent+0.452
Neg logit contributions
xit-1.632
iac-1.445
cycles-1.445
cel-1.442
nan-1.414
Token and
Token ID290
Feature activation-1.70e-01

Pos logit contributions
ruff+0.268
erity+0.263
 jammed+0.261
 Tanz+0.258
itent+0.250
Neg logit contributions
xit-0.296
iac-0.244
cycles-0.244
cel-0.242
************-0.235
Token Mr
Token ID1770
Feature activation+2.80e-01

Pos logit contributions
ruff+0.083
erity+0.081
 jammed+0.080
 Tanz+0.080
itent+0.076
Neg logit contributions
xit-0.145
iac-0.125
cycles-0.124
cel-0.124
************-0.121
Token.
Token ID13
Feature activation+7.45e-01

Pos logit contributions
xit+0.193
iac+0.158
cycles+0.158
cel+0.156
************+0.153
Neg logit contributions
ruff-0.184
erity-0.180
 jammed-0.179
 Tanz-0.178
 Danger-0.172
Token Hyde
Token ID30785
Feature activation+2.51e-01

Pos logit contributions
xit+0.523
iac+0.428
cycles+0.428
cel+0.422
************+0.414
Neg logit contributions
ruff-0.482
 jammed-0.470
erity-0.469
 Tanz-0.467
 Danger-0.454