TOP ACTIVATIONS
MAX = 5.260

in - C razy Air plane Pilot - 08 Election -
waters of Bangladesh 's Sund arb ans , the largest contiguous
Cuban - inspired coffee - gu ava stout . I think
It was an un gu arded moment ,
s writings . Ar gu ably though , the main
entrance to the Bangladesh Sund arb ans , southeast of the
forest official of the Sund arb ans in Bangladesh , told
aerial photograph of the Sund arb ans , made in 2010
's Orange - P ine apple - Ban ana works especially
haven t been lucky enough to get your hands
is unprecedented in the Sund arb ans , and we don
attempt to go get Ber gd ahl in the way that
ert of the University of Gu el ph in Ontario ,
horses . Acc omp an ied by their Bern
cl apped during high - profile Senate committee hearings .
W az ir istan air raids . K hy
to make employee protections more explicit . Does n
Wash , Steven La M ears , U . S .
from the beginning that Ber gd ahl had not been captured
Marine Division , participated in Operation Winter Storm . This was

MIN ACTIVATIONS
MIN = -6.139

immigrant argued that the tattoo sign ified his place of birth
- 11 season . He signed a five - year contract
she apparently ran a stop sign and slammed into the side
acious goal of cities who sign up to be part of
going back unless sign als are sent
three thousand IB EW members signed a new contract with Hydro
announced that the company has signed a deal with Japan financial
, 2004 joint venture agreement signed between his Muk ta Arts
playoff round or re - sign s Lang en br un
major tenants . Google has signed on to take over a
intersection while holding his stop sign al oft . While he
story <|endoftext|> Google has finally signed a deal to purchase live
Today , there is little sign of basketball s
[ 8 ] Chevron eventually signed the agreement in 2008 ,
developer Nerd Kingdom last week signed an agreement to become partners
advertisement " Interestingly enough , [ Tuesday ], Mor
al maps like sign ature food from each state
However , this is barely enough for any realistic optimism .
6 , O ka for signed a two - year contract
her bike through the stop sign and collided with a patrol

INTERVAL 2.411 - 5.260
CONTAINS 0.701%

you get from this sub wo ofer . I have this
machine can , despite software virtual ization . 4
use . Here is the link for buying the second edition
most damning of which was arguably an officer eating what appears
- we ird black - border cards : Block buster is

INTERVAL -0.439 - 2.411
CONTAINS 73.705%

At omic The heart of the library
by the fourth volume settles into a compl acent marriage with
as observed in our seismic analysis , note the
The shorts are modeled on the Body Paint line
projects , especially for Burning Man . [ Math

INTERVAL -3.289 - -0.439
CONTAINS 25.471%

x . x . x . 151 103 30 29 x
curb , g utter , and sidewalk are all raised by
Query and the public GitHub dataset to discover the most used
of the herd manifests a form of illness . Nonetheless ,
dirty trick he could think of to secure his re -

INTERVAL -6.139 - -3.289
CONTAINS 0.122%

playoff round or re - sign s Lang en br un
players were traded for and signed by the sophomore General Manager
had sex sex . I bought drugs and a massage from
activity elsewhere includes a new settlement ( with private foreign funding
Or at least , know enough about each culture so that
Tokenin
Token ID259
Feature activation+2.34e-01

Pos logit contributions
obar+0.869
 inadvert+0.834
20439+0.834
esty+0.799
 XY+0.784
Neg logit contributions
Msg-1.195
aida-1.161
 Belg-1.143
jac-1.104
hess-1.085
Token-
Token ID12
Feature activation-9.09e-01

Pos logit contributions
obar+0.155
 inadvert+0.150
20439+0.150
esty+0.144
 XY+0.144
Neg logit contributions
Msg-0.166
aida-0.162
 Belg-0.157
jac-0.152
hess-0.150
TokenC
Token ID34
Feature activation+9.70e-01

Pos logit contributions
Msg+0.620
aida+0.606
 Belg+0.589
jac+0.569
hess+0.562
Neg logit contributions
obar-0.628
20439-0.615
 inadvert-0.609
esty-0.584
 XY-0.578
Tokenrazy
Token ID5918
Feature activation+2.08e-01

Pos logit contributions
obar+0.619
20439+0.600
 inadvert+0.597
esty+0.575
 um+0.563
Neg logit contributions
Msg-0.716
aida-0.694
 Belg-0.681
jac-0.656
hess-0.648
Token Air
Token ID3701
Feature activation+8.91e-01

Pos logit contributions
obar+0.133
20439+0.130
 inadvert+0.129
esty+0.124
 XY+0.124
Neg logit contributions
Msg-0.152
aida-0.148
 Belg-0.144
jac-0.140
hess-0.138
Tokenplane
Token ID14382
Feature activation+5.26e+00

Pos logit contributions
obar+0.645
 inadvert+0.627
20439+0.625
esty+0.608
 XY+0.603
Neg logit contributions
Msg-0.574
aida-0.560
 Belg-0.541
jac-0.524
hess-0.522
Token Pilot
Token ID21697
Feature activation+1.72e+00

Pos logit contributions
obar+3.211
 inadvert+3.128
 Sear+3.107
 XY+3.066
esty+3.029
Neg logit contributions
Msg-3.801
aida-3.768
 Belg-3.597
hess-3.527
jac-3.502
Token-
Token ID12
Feature activation-7.87e-01

Pos logit contributions
obar+1.116
 inadvert+1.084
20439+1.070
esty+1.045
 XY+1.045
Neg logit contributions
Msg-1.236
aida-1.210
 Belg-1.173
jac-1.133
hess-1.131
Token08
Token ID2919
Feature activation+2.11e-01

Pos logit contributions
Msg+0.539
aida+0.527
 Belg+0.512
jac+0.494
hess+0.489
Neg logit contributions
obar-0.541
20439-0.530
 inadvert-0.524
esty-0.503
 XY-0.498
Token Election
Token ID14219
Feature activation+1.13e+00

Pos logit contributions
obar+0.149
20439+0.146
 inadvert+0.144
esty+0.140
 XY+0.139
Neg logit contributions
Msg-0.141
aida-0.137
 Belg-0.133
jac-0.129
hess-0.127
Token-
Token ID12
Feature activation-1.67e+00

Pos logit contributions
obar+0.726
 inadvert+0.707
20439+0.702
 XY+0.682
esty+0.680
Neg logit contributions
Msg-0.820
aida-0.807
 Belg-0.778
jac-0.757
hess-0.747
Token waters
Token ID10150
Feature activation-2.04e+00

Pos logit contributions
Msg+0.115
aida+0.112
 Belg+0.109
jac+0.106
hess+0.105
Neg logit contributions
obar-0.096
20439-0.094
 inadvert-0.093
esty-0.089
 XY-0.088
Token of
Token ID286
Feature activation-1.49e-01

Pos logit contributions
Msg+1.496
aida+1.460
 Belg+1.423
jac+1.378
hess+1.362
Neg logit contributions
obar-1.310
20439-1.282
 inadvert-1.270
esty-1.214
 XY-1.198
Token Bangladesh
Token ID19483
Feature activation+8.60e-01

Pos logit contributions
Msg+0.109
aida+0.106
 Belg+0.103
jac+0.100
hess+0.099
Neg logit contributions
obar-0.097
20439-0.094
 inadvert-0.094
esty-0.089
 XY-0.089
Token's
Token ID338
Feature activation+9.44e-01

Pos logit contributions
obar+0.511
20439+0.494
 inadvert+0.492
esty+0.470
 XY+0.462
Neg logit contributions
Msg-0.673
aida-0.656
 Belg-0.641
jac-0.625
hess-0.616
Token Sund
Token ID3309
Feature activation+1.06e+00

Pos logit contributions
obar+0.632
 inadvert+0.615
20439+0.611
esty+0.585
 XY+0.582
Neg logit contributions
Msg-0.667
aida-0.650
 Belg-0.626
jac-0.616
hess-0.605
Tokenarb
Token ID38039
Feature activation+5.02e+00

Pos logit contributions
obar+0.438
 inadvert+0.402
20439+0.394
esty+0.382
 um+0.370
Neg logit contributions
Msg-1.042
 Belg-1.003
aida-1.000
jac-0.965
hess-0.954
Tokenans
Token ID504
Feature activation+1.34e-01

Pos logit contributions
obar+3.740
 inadvert+3.567
20439+3.442
esty+3.421
 mm+3.417
Neg logit contributions
Msg-3.235
 Belg-2.982
aida-2.963
jac-2.821
hess-2.805
Token,
Token ID11
Feature activation+5.43e-01

Pos logit contributions
obar+0.085
20439+0.082
 inadvert+0.082
esty+0.078
 XY+0.077
Neg logit contributions
Msg-0.101
aida-0.098
 Belg-0.096
jac-0.093
hess-0.092
Token the
Token ID262
Feature activation+2.63e-01

Pos logit contributions
obar+0.355
 inadvert+0.347
20439+0.341
esty+0.328
 accidental+0.328
Neg logit contributions
Msg-0.393
aida-0.385
 Belg-0.368
jac-0.365
hess-0.358
Token largest
Token ID4387
Feature activation+1.29e+00

Pos logit contributions
obar+0.162
 inadvert+0.157
20439+0.157
esty+0.149
 XY+0.147
Neg logit contributions
Msg-0.200
aida-0.195
 Belg-0.190
jac-0.186
hess-0.183
Token contiguous
Token ID48627
Feature activation+1.89e+00

Pos logit contributions
obar+0.793
 inadvert+0.782
20439+0.751
 accidental+0.737
 um+0.731
Neg logit contributions
Msg-0.981
aida-0.951
 Belg-0.926
jac-0.908
hess-0.896
Token Cuban
Token ID18147
Feature activation+1.88e+00

Pos logit contributions
obar+0.395
 inadvert+0.388
20439+0.384
esty+0.369
 um+0.366
Neg logit contributions
Msg-0.487
aida-0.478
 Belg-0.457
jac-0.449
hess-0.447
Token-
Token ID12
Feature activation+1.13e+00

Pos logit contributions
obar+1.222
 inadvert+1.194
20439+1.169
esty+1.143
 um+1.138
Neg logit contributions
Msg-1.363
aida-1.321
 Belg-1.276
jac-1.245
hess-1.241
Tokeninspired
Token ID24194
Feature activation+1.44e+00

Pos logit contributions
obar+0.664
20439+0.642
 inadvert+0.638
esty+0.613
 um+0.602
Neg logit contributions
Msg-0.887
aida-0.870
 Belg-0.848
jac-0.817
hess-0.815
Token coffee
Token ID6891
Feature activation+1.99e+00

Pos logit contributions
obar+0.900
 inadvert+0.885
20439+0.863
 um+0.843
esty+0.839
Neg logit contributions
Msg-1.078
aida-1.052
 Belg-0.999
jac-0.990
hess-0.987
Token-
Token ID12
Feature activation+8.60e-01

Pos logit contributions
obar+1.184
 inadvert+1.155
20439+1.110
esty+1.103
 um+1.100
Neg logit contributions
Msg-1.548
aida-1.512
 Belg-1.447
jac-1.426
hess-1.425
Tokengu
Token ID5162
Feature activation+5.01e+00

Pos logit contributions
obar+0.612
20439+0.594
 inadvert+0.591
esty+0.571
 um+0.563
Neg logit contributions
Msg-0.572
aida-0.556
 Belg-0.539
jac-0.516
hess-0.515
Tokenava
Token ID4170
Feature activation-4.25e-01

Pos logit contributions
obar+3.297
esty+3.134
 inadvert+3.122
 um+2.993
20439+2.968
Neg logit contributions
Msg-3.595
 Belg-3.416
aida-3.381
hess-3.219
jac-3.199
Token stout
Token ID39171
Feature activation+1.13e+00

Pos logit contributions
Msg+0.320
aida+0.313
 Belg+0.303
jac+0.295
hess+0.293
Neg logit contributions
obar-0.264
 inadvert-0.257
20439-0.256
esty-0.245
 XY-0.242
Token.
Token ID13
Feature activation+3.09e-01

Pos logit contributions
obar+0.696
 inadvert+0.681
20439+0.665
esty+0.649
 um+0.644
Neg logit contributions
Msg-0.858
aida-0.842
 Belg-0.805
jac-0.792
hess-0.790
Token I
Token ID314
Feature activation+3.74e-01

Pos logit contributions
obar+0.188
20439+0.184
 inadvert+0.182
esty+0.174
 XY+0.173
Neg logit contributions
Msg-0.235
aida-0.230
 Belg-0.223
jac-0.218
hess-0.216
Token think
Token ID892
Feature activation+1.31e+00

Pos logit contributions
obar+0.211
20439+0.206
 inadvert+0.203
esty+0.193
 XY+0.190
Neg logit contributions
Msg-0.303
aida-0.297
 Belg-0.290
jac-0.283
hess-0.279
Token
Token ID250
Feature activation-3.40e-01

Pos logit contributions
Msg+0.027
aida+0.026
 Belg+0.026
jac+0.024
hess+0.024
Neg logit contributions
obar-0.035
20439-0.034
 inadvert-0.034
esty-0.033
 XY-0.032
TokenIt
Token ID1026
Feature activation-1.03e-01

Pos logit contributions
Msg+0.229
aida+0.222
 Belg+0.216
jac+0.209
hess+0.206
Neg logit contributions
obar-0.239
20439-0.234
 inadvert-0.233
esty-0.223
 XY-0.220
Token was
Token ID373
Feature activation+9.05e-01

Pos logit contributions
Msg+0.080
aida+0.078
 Belg+0.076
jac+0.074
hess+0.073
Neg logit contributions
obar-0.061
20439-0.059
 inadvert-0.059
esty-0.056
 XY-0.055
Token an
Token ID281
Feature activation+1.27e-01

Pos logit contributions
obar+0.571
 inadvert+0.569
20439+0.554
esty+0.536
 accidental+0.534
Neg logit contributions
Msg-0.665
aida-0.653
 Belg-0.632
jac-0.619
hess-0.608
Token un
Token ID555
Feature activation+2.45e+00

Pos logit contributions
obar+0.077
 inadvert+0.076
20439+0.075
esty+0.072
 XY+0.071
Neg logit contributions
Msg-0.098
aida-0.095
 Belg-0.093
jac-0.090
hess-0.089
Tokengu
Token ID5162
Feature activation+5.00e+00

Pos logit contributions
obar+1.533
 inadvert+1.493
20439+1.491
esty+1.431
 XY+1.405
Neg logit contributions
Msg-1.812
aida-1.765
 Belg-1.726
jac-1.672
hess-1.651
Tokenarded
Token ID10676
Feature activation+1.23e+00

Pos logit contributions
obar+3.207
 inadvert+3.077
20439+3.038
esty+3.015
 mm+2.917
Neg logit contributions
Msg-3.684
aida-3.507
 Belg-3.499
jac-3.283
hess-3.273
Token moment
Token ID2589
Feature activation-1.29e+00

Pos logit contributions
obar+0.751
 inadvert+0.739
20439+0.735
esty+0.703
 XY+0.695
Neg logit contributions
Msg-0.930
aida-0.906
 Belg-0.883
jac-0.860
hess-0.852
Token,
Token ID11
Feature activation+2.62e-01

Pos logit contributions
Msg+0.969
aida+0.945
 Belg+0.920
jac+0.891
hess+0.883
Neg logit contributions
obar-0.804
20439-0.787
 inadvert-0.773
esty-0.738
 XY-0.730
Token
Token ID447
Feature activation+9.96e-02

Pos logit contributions
obar+0.126
20439+0.122
 inadvert+0.121
esty+0.114
 XY+0.112
Neg logit contributions
Msg-0.234
aida-0.229
 Belg-0.224
jac-0.219
hess-0.217
Token
Token ID251
Feature activation+5.61e-01

Pos logit contributions
obar+0.075
20439+0.073
 inadvert+0.073
esty+0.070
 XY+0.069
Neg logit contributions
Msg-0.062
aida-0.060
 Belg-0.059
jac-0.057
hess-0.056
Token
Token ID247
Feature activation+8.86e-02

Pos logit contributions
Msg+0.330
aida+0.318
 Belg+0.308
jac+0.292
hess+0.287
Neg logit contributions
obar-0.584
20439-0.573
 inadvert-0.571
esty-0.553
 XY-0.547
Tokens
Token ID82
Feature activation-1.79e-01

Pos logit contributions
obar+0.053
 inadvert+0.052
20439+0.052
esty+0.049
 um+0.048
Neg logit contributions
Msg-0.069
aida-0.067
 Belg-0.065
jac-0.063
hess-0.062
Token writings
Token ID19336
Feature activation+4.04e-01

Pos logit contributions
Msg+0.129
aida+0.126
 Belg+0.122
jac+0.119
hess+0.118
Neg logit contributions
obar-0.116
20439-0.113
 inadvert-0.113
esty-0.108
 XY-0.107
Token.
Token ID13
Feature activation+2.47e-01

Pos logit contributions
obar+0.232
20439+0.225
 inadvert+0.224
esty+0.213
 XY+0.210
Neg logit contributions
Msg-0.325
aida-0.317
 Belg-0.310
jac-0.300
hess-0.299
Token Ar
Token ID943
Feature activation+7.51e-01

Pos logit contributions
obar+0.150
20439+0.147
 inadvert+0.144
 XY+0.138
 Sear+0.138
Neg logit contributions
Msg-0.189
aida-0.184
 Belg-0.178
jac-0.174
hess-0.173
Tokengu
Token ID5162
Feature activation+4.85e+00

Pos logit contributions
obar+0.511
 inadvert+0.495
20439+0.494
esty+0.478
 XY+0.466
Neg logit contributions
Msg-0.523
aida-0.504
 Belg-0.493
jac-0.470
hess-0.469
Tokenably
Token ID1346
Feature activation+9.48e-02

Pos logit contributions
obar+2.711
esty+2.664
 inadvert+2.617
20439+2.547
 accidental+2.469
Neg logit contributions
Msg-3.850
 Belg-3.797
aida-3.680
jac-3.537
 Fraz-3.447
Token though
Token ID996
Feature activation-9.84e-01

Pos logit contributions
obar+0.057
 inadvert+0.056
20439+0.055
esty+0.053
 accidental+0.052
Neg logit contributions
Msg-0.073
aida-0.071
 Belg-0.069
jac-0.068
hess-0.067
Token,
Token ID11
Feature activation-2.76e-01

Pos logit contributions
Msg+0.765
aida+0.747
 Belg+0.724
jac+0.707
hess+0.698
Neg logit contributions
obar-0.590
 inadvert-0.573
20439-0.572
esty-0.544
 XY-0.537
Token the
Token ID262
Feature activation+1.60e-02

Pos logit contributions
Msg+0.199
aida+0.194
 Belg+0.187
jac+0.183
hess+0.180
Neg logit contributions
obar-0.181
 inadvert-0.177
20439-0.176
esty-0.168
 accidental-0.166
Token main
Token ID1388
Feature activation+1.72e-01

Pos logit contributions
obar+0.010
20439+0.010
 inadvert+0.010
esty+0.009
 XY+0.009
Neg logit contributions
Msg-0.012
aida-0.012
 Belg-0.011
jac-0.011
hess-0.011
Token entrance
Token ID10384
Feature activation-1.71e+00

Pos logit contributions
Msg+0.021
aida+0.020
 Belg+0.020
jac+0.019
hess+0.019
Neg logit contributions
obar-0.018
20439-0.017
 inadvert-0.017
esty-0.016
 XY-0.016
Token to
Token ID284
Feature activation-3.05e-01

Pos logit contributions
Msg+1.177
aida+1.149
 Belg+1.117
jac+1.080
hess+1.066
Neg logit contributions
obar-1.170
20439-1.151
 inadvert-1.136
esty-1.087
 XY-1.077
Token the
Token ID262
Feature activation-1.02e-01

Pos logit contributions
Msg+0.217
aida+0.211
 Belg+0.205
jac+0.199
hess+0.197
Neg logit contributions
obar-0.203
 inadvert-0.197
20439-0.197
esty-0.188
 XY-0.187
Token Bangladesh
Token ID19483
Feature activation+1.59e+00

Pos logit contributions
Msg+0.067
aida+0.066
 Belg+0.063
jac+0.062
hess+0.061
Neg logit contributions
obar-0.074
 inadvert-0.072
20439-0.071
esty-0.068
 XY-0.068
Token Sund
Token ID3309
Feature activation+1.93e+00

Pos logit contributions
obar+1.088
 inadvert+1.055
20439+1.050
esty+1.013
 XY+0.999
Neg logit contributions
Msg-1.097
aida-1.061
 Belg-1.035
jac-1.009
hess-0.991
Tokenarb
Token ID38039
Feature activation+4.77e+00

Pos logit contributions
obar+0.718
 inadvert+0.653
20439+0.651
esty+0.604
 um+0.586
Neg logit contributions
Msg-1.965
aida-1.906
 Belg-1.892
jac-1.828
hess-1.823
Tokenans
Token ID504
Feature activation+3.32e-01

Pos logit contributions
obar+3.475
 inadvert+3.226
esty+3.180
20439+3.172
 um+3.146
Neg logit contributions
Msg-3.116
 Belg-2.937
aida-2.858
jac-2.807
 Fraz-2.723
Token,
Token ID11
Feature activation+1.05e-01

Pos logit contributions
obar+0.191
 inadvert+0.187
20439+0.181
esty+0.175
 accidental+0.175
Neg logit contributions
Msg-0.265
aida-0.258
 Belg-0.252
jac-0.245
hess-0.243
Token southeast
Token ID26015
Feature activation+1.80e+00

Pos logit contributions
obar+0.069
 inadvert+0.067
20439+0.066
esty+0.064
 accidental+0.064
Neg logit contributions
Msg-0.076
aida-0.075
 Belg-0.072
jac-0.070
hess-0.069
Token of
Token ID286
Feature activation+3.35e-02

Pos logit contributions
obar+0.922
 inadvert+0.893
20439+0.871
 XY+0.845
esty+0.843
Neg logit contributions
Msg-1.550
aida-1.510
 Belg-1.468
jac-1.447
hess-1.430
Token the
Token ID262
Feature activation-3.62e-01

Pos logit contributions
obar+0.025
 inadvert+0.024
20439+0.024
esty+0.023
 XY+0.023
Neg logit contributions
Msg-0.021
aida-0.021
 Belg-0.020
jac-0.019
hess-0.019
Token forest
Token ID8222
Feature activation+8.32e-01

Pos logit contributions
obar+0.052
20439+0.051
 inadvert+0.051
esty+0.048
 XY+0.047
Neg logit contributions
Msg-0.079
aida-0.077
 Belg-0.075
jac-0.073
hess-0.072
Token official
Token ID1743
Feature activation+1.95e+00

Pos logit contributions
obar+0.486
 inadvert+0.471
20439+0.469
esty+0.447
 um+0.440
Neg logit contributions
Msg-0.657
aida-0.642
 Belg-0.627
jac-0.611
hess-0.600
Token of
Token ID286
Feature activation+1.13e+00

Pos logit contributions
obar+1.140
 inadvert+1.106
20439+1.095
esty+1.050
 um+1.039
Neg logit contributions
Msg-1.530
aida-1.497
 Belg-1.456
jac-1.427
hess-1.395
Token the
Token ID262
Feature activation+2.13e-01

Pos logit contributions
obar+0.758
 inadvert+0.736
20439+0.732
esty+0.700
 XY+0.698
Neg logit contributions
Msg-0.800
aida-0.775
 Belg-0.751
jac-0.736
hess-0.725
Token Sund
Token ID3309
Feature activation+1.57e+00

Pos logit contributions
obar+0.144
 inadvert+0.140
20439+0.140
esty+0.134
 XY+0.133
Neg logit contributions
Msg-0.148
aida-0.144
 Belg-0.140
jac-0.136
hess-0.135
Tokenarb
Token ID38039
Feature activation+4.72e+00

Pos logit contributions
obar+0.567
 inadvert+0.516
20439+0.514
esty+0.475
 um+0.460
Neg logit contributions
Msg-1.611
aida-1.564
 Belg-1.547
jac-1.501
hess-1.494
Tokenans
Token ID504
Feature activation+4.06e-01

Pos logit contributions
obar+3.418
 inadvert+3.196
20439+3.141
esty+3.139
 um+3.127
Neg logit contributions
Msg-3.088
 Belg-2.867
aida-2.810
jac-2.769
 Fraz-2.674
Token in
Token ID287
Feature activation+3.10e-01

Pos logit contributions
obar+0.252
 inadvert+0.245
20439+0.242
esty+0.232
 um+0.231
Neg logit contributions
Msg-0.306
aida-0.298
 Belg-0.290
jac-0.283
hess-0.278
Token Bangladesh
Token ID19483
Feature activation+1.80e+00

Pos logit contributions
obar+0.213
 inadvert+0.207
20439+0.206
esty+0.198
 XY+0.197
Neg logit contributions
Msg-0.213
aida-0.208
 Belg-0.200
jac-0.196
hess-0.193
Token,
Token ID11
Feature activation+6.41e-01

Pos logit contributions
obar+1.059
 inadvert+1.022
20439+1.015
esty+0.976
 XY+0.962
Neg logit contributions
Msg-1.410
aida-1.376
 Belg-1.349
jac-1.317
hess-1.290
Token told
Token ID1297
Feature activation-1.66e+00

Pos logit contributions
obar+0.418
20439+0.407
 inadvert+0.406
esty+0.388
 um+0.384
Neg logit contributions
Msg-0.463
aida-0.452
 Belg-0.436
jac-0.428
hess-0.421
Token aerial
Token ID17789
Feature activation+8.24e-01

Pos logit contributions
obar+0.916
 inadvert+0.899
20439+0.884
 accidental+0.852
esty+0.852
Neg logit contributions
Msg-0.994
aida-0.971
 Belg-0.939
jac-0.922
hess-0.911
Token photograph
Token ID8408
Feature activation+4.83e-01

Pos logit contributions
obar+0.574
 inadvert+0.558
20439+0.557
esty+0.534
 XY+0.530
Neg logit contributions
Msg-0.559
aida-0.544
 Belg-0.528
jac-0.513
hess-0.506
Token of
Token ID286
Feature activation+4.64e-01

Pos logit contributions
obar+0.278
20439+0.270
 inadvert+0.269
esty+0.256
 XY+0.253
Neg logit contributions
Msg-0.384
aida-0.375
 Belg-0.366
jac-0.358
hess-0.353
Token the
Token ID262
Feature activation-1.48e-02

Pos logit contributions
obar+0.306
 inadvert+0.297
20439+0.296
esty+0.283
 XY+0.280
Neg logit contributions
Msg-0.332
aida-0.323
 Belg-0.314
jac-0.306
hess-0.303
Token Sund
Token ID3309
Feature activation+1.31e+00

Pos logit contributions
Msg+0.011
aida+0.010
 Belg+0.010
jac+0.010
hess+0.010
Neg logit contributions
obar-0.010
20439-0.010
 inadvert-0.009
esty-0.009
 XY-0.009
Tokenarb
Token ID38039
Feature activation+4.66e+00

Pos logit contributions
obar+0.485
20439+0.449
 inadvert+0.447
esty+0.413
 XY+0.399
Neg logit contributions
Msg-1.326
aida-1.292
 Belg-1.277
jac-1.240
hess-1.233
Tokenans
Token ID504
Feature activation+3.98e-01

Pos logit contributions
obar+3.358
 inadvert+3.121
20439+3.071
esty+3.069
 um+3.049
Neg logit contributions
Msg-3.074
 Belg-2.865
aida-2.821
jac-2.745
 Fraz-2.689
Token,
Token ID11
Feature activation+5.83e-01

Pos logit contributions
obar+0.235
 inadvert+0.229
20439+0.227
esty+0.217
 accidental+0.215
Neg logit contributions
Msg-0.310
aida-0.302
 Belg-0.295
jac-0.289
hess-0.285
Token made
Token ID925
Feature activation+1.13e+00

Pos logit contributions
obar+0.379
 inadvert+0.369
20439+0.365
esty+0.351
 um+0.348
Neg logit contributions
Msg-0.423
aida-0.413
 Belg-0.399
jac-0.392
hess-0.386
Token in
Token ID287
Feature activation+7.17e-01

Pos logit contributions
obar+0.793
 inadvert+0.774
20439+0.764
esty+0.736
 accidental+0.733
Neg logit contributions
Msg-0.758
aida-0.740
 Belg-0.716
jac-0.697
hess-0.689
Token 2010
Token ID3050
Feature activation-7.62e-02

Pos logit contributions
obar+0.436
 inadvert+0.425
20439+0.422
esty+0.402
 XY+0.400
Neg logit contributions
Msg-0.549
aida-0.534
 Belg-0.519
jac-0.509
hess-0.502
Token's
Token ID338
Feature activation+8.08e-01

Pos logit contributions
Msg+0.086
aida+0.084
 Belg+0.082
jac+0.079
hess+0.079
Neg logit contributions
obar-0.075
 inadvert-0.073
20439-0.072
esty-0.069
 XY-0.068
Token Orange
Token ID11942
Feature activation+2.33e+00

Pos logit contributions
obar+0.504
 inadvert+0.490
20439+0.488
esty+0.466
 XY+0.462
Neg logit contributions
Msg-0.606
aida-0.591
 Belg-0.573
jac-0.558
hess-0.555
Token-
Token ID12
Feature activation+1.05e+00

Pos logit contributions
obar+1.756
 inadvert+1.708
20439+1.705
esty+1.654
 um+1.640
Neg logit contributions
Msg-1.435
aida-1.400
 Belg-1.338
jac-1.287
hess-1.287
TokenP
Token ID47
Feature activation+7.94e-01

Pos logit contributions
obar+0.736
20439+0.719
 inadvert+0.711
esty+0.687
 um+0.677
Neg logit contributions
Msg-0.711
aida-0.696
 Belg-0.676
jac-0.650
hess-0.645
Tokenine
Token ID500
Feature activation+5.70e-01

Pos logit contributions
obar+0.529
 inadvert+0.512
20439+0.511
esty+0.498
 um+0.484
Neg logit contributions
Msg-0.561
aida-0.548
 Belg-0.536
jac-0.517
hess-0.508
Tokenapple
Token ID18040
Feature activation+4.56e+00

Pos logit contributions
obar+0.285
20439+0.275
 inadvert+0.273
esty+0.259
 um+0.255
Neg logit contributions
Msg-0.498
aida-0.488
 Belg-0.475
jac-0.462
hess-0.459
Token-
Token ID12
Feature activation+7.24e-01

Pos logit contributions
obar+2.836
 inadvert+2.760
20439+2.722
 um+2.679
 XY+2.659
Neg logit contributions
Msg-3.354
aida-3.299
 Belg-3.100
hess-3.080
jac-3.059
TokenBan
Token ID30457
Feature activation+1.68e+00

Pos logit contributions
obar+0.490
20439+0.482
 inadvert+0.474
esty+0.457
 XY+0.450
Neg logit contributions
Msg-0.501
aida-0.492
 Belg-0.478
jac-0.460
hess-0.455
Tokenana
Token ID2271
Feature activation+2.48e+00

Pos logit contributions
obar+1.209
20439+1.179
 inadvert+1.172
esty+1.132
 um+1.116
Neg logit contributions
Msg-1.089
aida-1.059
 Belg-1.025
jac-0.986
hess-0.970
Token works
Token ID2499
Feature activation+2.84e-01

Pos logit contributions
obar+1.560
 inadvert+1.519
20439+1.506
esty+1.449
 um+1.449
Neg logit contributions
Msg-1.832
aida-1.796
 Belg-1.717
jac-1.676
hess-1.670
Token especially
Token ID2592
Feature activation+7.04e-01

Pos logit contributions
obar+0.153
 inadvert+0.148
20439+0.146
esty+0.139
 um+0.138
Neg logit contributions
Msg-0.237
aida-0.233
 Belg-0.226
jac-0.221
hess-0.219
Token haven
Token ID4398
Feature activation+4.09e-01

Pos logit contributions
Msg+0.596
aida+0.583
 Belg+0.569
jac+0.553
hess+0.546
Neg logit contributions
obar-0.431
20439-0.422
 inadvert-0.415
esty-0.396
 XY-0.389
Token
Token ID447
Feature activation-3.46e-01

Pos logit contributions
obar+0.259
20439+0.254
 inadvert+0.251
esty+0.240
 XY+0.237
Neg logit contributions
Msg-0.303
aida-0.296
 Belg-0.288
jac-0.279
hess-0.276
Token
Token ID247
Feature activation-4.00e-01

Pos logit contributions
Msg+0.176
aida+0.170
 Belg+0.164
jac+0.157
hess+0.154
Neg logit contributions
obar-0.299
20439-0.294
 inadvert-0.293
esty-0.283
 XY-0.280
Tokent
Token ID83
Feature activation-3.34e-01

Pos logit contributions
Msg+0.190
aida+0.183
 Belg+0.176
jac+0.167
hess+0.164
Neg logit contributions
obar-0.360
20439-0.354
 inadvert-0.352
esty-0.341
 XY-0.338
Token been
Token ID587
Feature activation-4.33e-01

Pos logit contributions
Msg+0.238
aida+0.232
 Belg+0.226
jac+0.219
hess+0.216
Neg logit contributions
obar-0.221
20439-0.216
 inadvert-0.214
esty-0.205
 XY-0.203
Token lucky
Token ID9670
Feature activation+4.56e+00

Pos logit contributions
Msg+0.297
aida+0.289
 Belg+0.281
jac+0.272
hess+0.268
Neg logit contributions
obar-0.298
20439-0.292
 inadvert-0.289
esty-0.278
 XY-0.274
Token enough
Token ID1576
Feature activation-3.91e+00

Pos logit contributions
obar+3.474
 inadvert+3.443
20439+3.402
esty+3.358
 um+3.354
Neg logit contributions
Msg-2.616
aida-2.612
 Belg-2.446
jac-2.424
hess-2.322
Token to
Token ID284
Feature activation-5.36e-01

Pos logit contributions
Msg+2.478
aida+2.400
 Belg+2.343
jac+2.243
hess+2.234
Neg logit contributions
obar-2.873
20439-2.815
 inadvert-2.775
esty-2.671
 XY-2.638
Token get
Token ID651
Feature activation+1.47e+00

Pos logit contributions
Msg+0.440
aida+0.431
 Belg+0.421
jac+0.410
hess+0.405
Neg logit contributions
obar-0.295
20439-0.288
 inadvert-0.284
esty-0.270
 XY-0.265
Token your
Token ID534
Feature activation-6.35e-01

Pos logit contributions
obar+0.999
 inadvert+0.978
20439+0.978
 XY+0.934
 accidental+0.929
Neg logit contributions
Msg-1.015
aida-0.992
 Belg-0.961
jac-0.935
hess-0.918
Token hands
Token ID2832
Feature activation+4.59e-01

Pos logit contributions
Msg+0.576
aida+0.566
 Belg+0.554
jac+0.542
hess+0.535
Neg logit contributions
obar-0.295
20439-0.285
 inadvert-0.285
esty-0.265
 XY-0.263
Token is
Token ID318
Feature activation+2.24e-01

Pos logit contributions
obar+0.239
 inadvert+0.236
20439+0.229
esty+0.221
 accidental+0.220
Neg logit contributions
Msg-0.346
aida-0.340
 Belg-0.331
jac-0.326
hess-0.317
Token unprecedented
Token ID13029
Feature activation-3.70e-02

Pos logit contributions
obar+0.143
 inadvert+0.139
20439+0.137
esty+0.131
 accidental+0.131
Neg logit contributions
Msg-0.165
aida-0.162
 Belg-0.157
jac-0.154
hess-0.150
Token in
Token ID287
Feature activation-5.41e-02

Pos logit contributions
Msg+0.027
aida+0.027
 Belg+0.026
jac+0.025
hess+0.025
Neg logit contributions
obar-0.024
 inadvert-0.023
20439-0.023
esty-0.022
 XY-0.022
Token the
Token ID262
Feature activation+2.55e-02

Pos logit contributions
Msg+0.040
aida+0.039
 Belg+0.038
jac+0.037
hess+0.036
Neg logit contributions
obar-0.035
20439-0.034
 inadvert-0.034
esty-0.032
 XY-0.032
Token Sund
Token ID3309
Feature activation+9.57e-01

Pos logit contributions
obar+0.014
20439+0.014
 inadvert+0.014
esty+0.013
 XY+0.013
Neg logit contributions
Msg-0.021
aida-0.020
 Belg-0.020
jac-0.019
hess-0.019
Tokenarb
Token ID38039
Feature activation+4.53e+00

Pos logit contributions
obar+0.347
 inadvert+0.316
20439+0.316
esty+0.291
 um+0.282
Neg logit contributions
Msg-0.983
aida-0.955
 Belg-0.945
jac-0.917
hess-0.912
Tokenans
Token ID504
Feature activation+2.99e-02

Pos logit contributions
obar+3.290
 inadvert+3.062
20439+3.024
esty+3.011
 um+2.985
Neg logit contributions
Msg-2.962
 Belg-2.778
aida-2.696
jac-2.668
 Fraz-2.567
Token,
Token ID11
Feature activation+1.56e-01

Pos logit contributions
obar+0.019
 inadvert+0.019
20439+0.018
esty+0.018
 accidental+0.018
Neg logit contributions
Msg-0.022
aida-0.021
 Belg-0.021
jac-0.020
hess-0.020
Token and
Token ID290
Feature activation+1.28e-01

Pos logit contributions
obar+0.099
 inadvert+0.097
20439+0.096
esty+0.091
 accidental+0.091
Neg logit contributions
Msg-0.115
aida-0.113
 Belg-0.109
jac-0.107
hess-0.105
Token we
Token ID356
Feature activation-5.51e-01

Pos logit contributions
obar+0.083
 inadvert+0.081
20439+0.080
esty+0.077
 accidental+0.076
Neg logit contributions
Msg-0.092
aida-0.090
 Belg-0.087
jac-0.086
hess-0.084
Token don
Token ID836
Feature activation-8.58e-02

Pos logit contributions
Msg+0.453
aida+0.443
 Belg+0.433
jac+0.422
hess+0.417
Neg logit contributions
obar-0.303
20439-0.295
 inadvert-0.292
esty-0.277
 XY-0.273
Token attempt
Token ID2230
Feature activation+1.47e+00

Pos logit contributions
obar+0.117
20439+0.115
 inadvert+0.115
esty+0.109
 XY+0.108
Neg logit contributions
Msg-0.135
aida-0.132
 Belg-0.128
jac-0.125
hess-0.123
Token to
Token ID284
Feature activation-2.50e-01

Pos logit contributions
obar+0.970
20439+0.956
 inadvert+0.949
esty+0.910
 um+0.898
Neg logit contributions
Msg-1.045
aida-1.016
 Belg-0.988
jac-0.964
hess-0.947
Token go
Token ID467
Feature activation+5.75e-01

Pos logit contributions
Msg+0.194
aida+0.189
 Belg+0.184
jac+0.179
hess+0.177
Neg logit contributions
obar-0.150
20439-0.146
 inadvert-0.146
esty-0.139
 XY-0.137
Token get
Token ID651
Feature activation+2.07e+00

Pos logit contributions
obar+0.390
20439+0.378
 inadvert+0.378
esty+0.363
 um+0.361
Neg logit contributions
Msg-0.402
aida-0.388
 Belg-0.377
jac-0.367
hess-0.365
Token Ber
Token ID4312
Feature activation-1.01e+00

Pos logit contributions
obar+1.315
20439+1.280
 inadvert+1.279
esty+1.213
 XY+1.211
Neg logit contributions
Msg-1.526
aida-1.475
 Belg-1.429
jac-1.401
hess-1.389
Tokengd
Token ID21287
Feature activation+4.48e+00

Pos logit contributions
Msg+0.921
aida+0.902
 Belg+0.885
jac+0.863
hess+0.853
Neg logit contributions
obar-0.472
20439-0.457
 inadvert-0.451
esty-0.424
 XY-0.416
Tokenahl
Token ID15668
Feature activation-1.09e+00

Pos logit contributions
obar+2.635
 inadvert+2.487
20439+2.456
esty+2.392
 um+2.381
Neg logit contributions
Msg-3.539
 Belg-3.424
aida-3.388
jac-3.260
hess-3.207
Token in
Token ID287
Feature activation+3.71e-01

Pos logit contributions
Msg+0.869
aida+0.850
 Belg+0.830
jac+0.807
hess+0.798
Neg logit contributions
obar-0.621
20439-0.607
 inadvert-0.599
esty-0.570
 XY-0.561
Token the
Token ID262
Feature activation+3.91e-01

Pos logit contributions
obar+0.231
 inadvert+0.227
20439+0.225
esty+0.215
 um+0.214
Neg logit contributions
Msg-0.279
aida-0.271
 Belg-0.263
jac-0.257
hess-0.254
Token way
Token ID835
Feature activation-1.04e+00

Pos logit contributions
obar+0.205
 inadvert+0.202
20439+0.199
 um+0.190
 XY+0.187
Neg logit contributions
Msg-0.334
aida-0.323
 Belg-0.314
jac-0.310
hess-0.309
Token that
Token ID326
Feature activation+1.28e-02

Pos logit contributions
Msg+0.829
aida+0.811
 Belg+0.793
jac+0.770
hess+0.761
Neg logit contributions
obar-0.593
20439-0.578
 inadvert-0.572
esty-0.544
 XY-0.535
Tokenert
Token ID861
Feature activation+1.07e+00

Pos logit contributions
Msg+1.154
aida+1.124
 Belg+1.094
jac+1.059
hess+1.045
Neg logit contributions
obar-1.094
20439-1.067
 inadvert-1.060
esty-1.017
 XY-1.003
Token of
Token ID286
Feature activation+6.81e-01

Pos logit contributions
obar+0.625
 inadvert+0.602
20439+0.597
esty+0.575
 um+0.564
Neg logit contributions
Msg-0.844
aida-0.823
 Belg-0.804
jac-0.776
hess-0.768
Token the
Token ID262
Feature activation+4.28e-01

Pos logit contributions
obar+0.421
 inadvert+0.409
20439+0.405
 XY+0.388
esty+0.386
Neg logit contributions
Msg-0.515
aida-0.501
 Belg-0.484
jac-0.476
hess-0.468
Token University
Token ID2059
Feature activation-6.46e-01

Pos logit contributions
obar+0.246
20439+0.238
 inadvert+0.238
esty+0.225
 XY+0.224
Neg logit contributions
Msg-0.342
aida-0.334
 Belg-0.325
jac-0.317
hess-0.314
Token of
Token ID286
Feature activation+2.69e+00

Pos logit contributions
Msg+0.516
aida+0.505
 Belg+0.495
jac+0.480
hess+0.474
Neg logit contributions
obar-0.372
20439-0.364
 inadvert-0.360
esty-0.343
 accidental-0.333
Token Gu
Token ID1962
Feature activation+4.45e+00

Pos logit contributions
obar+1.605
 inadvert+1.574
20439+1.533
 Sear+1.523
 XY+1.523
Neg logit contributions
Msg-2.076
aida-2.023
jac-1.910
 Belg-1.881
hess-1.869
Tokenel
Token ID417
Feature activation-2.33e+00

Pos logit contributions
obar+2.550
 inadvert+2.327
esty+2.301
20439+2.268
 um+2.230
Neg logit contributions
Msg-3.653
aida-3.444
 Belg-3.424
jac-3.272
hess-3.272
Tokenph
Token ID746
Feature activation+7.29e-01

Pos logit contributions
aida+1.141
Msg+1.128
 Belg+1.096
jac+1.061
hess+1.038
Neg logit contributions
20439-2.048
obar-1.998
 inadvert-1.986
esty-1.905
 accidental-1.882
Token in
Token ID287
Feature activation+6.89e-01

Pos logit contributions
obar+0.429
 inadvert+0.414
20439+0.406
esty+0.391
 XY+0.391
Neg logit contributions
Msg-0.575
aida-0.560
 Belg-0.542
jac-0.530
hess-0.523
Token Ontario
Token ID10553
Feature activation+1.52e+00

Pos logit contributions
obar+0.467
 inadvert+0.461
20439+0.442
 accidental+0.438
 Sear+0.435
Neg logit contributions
Msg-0.478
aida-0.464
jac-0.437
 Belg-0.436
hess-0.436
Token,
Token ID11
Feature activation+7.21e-01

Pos logit contributions
obar+0.850
 inadvert+0.823
20439+0.816
esty+0.775
 accidental+0.768
Neg logit contributions
Msg-1.243
aida-1.211
 Belg-1.175
jac-1.149
hess-1.141
Token horses
Token ID14260
Feature activation+1.54e+00

Pos logit contributions
Msg+0.237
aida+0.231
 Belg+0.224
jac+0.216
hess+0.213
Neg logit contributions
obar-0.261
20439-0.256
 inadvert-0.253
esty-0.244
 XY-0.241
Token.
Token ID13
Feature activation+2.23e-01

Pos logit contributions
obar+0.915
 inadvert+0.891
20439+0.879
esty+0.848
 um+0.836
Neg logit contributions
Msg-1.198
aida-1.170
 Belg-1.142
jac-1.112
hess-1.094
Token
Token ID198
Feature activation-2.59e-01

Pos logit contributions
obar+0.108
20439+0.105
 inadvert+0.103
esty+0.098
 XY+0.096
Neg logit contributions
Msg-0.198
aida-0.194
 Belg-0.190
jac-0.186
hess-0.183
Token
Token ID198
Feature activation-6.84e-02

Pos logit contributions
Msg+0.230
aida+0.225
 Belg+0.220
jac+0.215
hess+0.212
Neg logit contributions
obar-0.126
20439-0.123
 inadvert-0.122
esty-0.114
 XY-0.112
TokenAcc
Token ID17320
Feature activation+1.26e+00

Pos logit contributions
Msg+0.048
aida+0.046
 Belg+0.045
jac+0.044
hess+0.043
Neg logit contributions
obar-0.046
20439-0.045
 inadvert-0.045
esty-0.043
 XY-0.042
Tokenomp
Token ID3361
Feature activation+4.44e+00

Pos logit contributions
obar+0.650
20439+0.621
 inadvert+0.618
esty+0.591
 um+0.575
Neg logit contributions
Msg-1.082
aida-1.059
 Belg-1.038
jac-1.008
hess-0.997
Tokenan
Token ID272
Feature activation-5.84e-01

Pos logit contributions
obar+2.360
 inadvert+2.193
esty+2.158
20439+2.142
 Sear+2.091
Neg logit contributions
Msg-3.729
aida-3.594
 Belg-3.446
jac-3.433
hess-3.378
Tokenied
Token ID798
Feature activation+2.02e+00

Pos logit contributions
Msg+0.407
aida+0.397
 Belg+0.386
jac+0.374
hess+0.369
Neg logit contributions
obar-0.395
20439-0.387
 inadvert-0.383
esty-0.368
 XY-0.363
Token by
Token ID416
Feature activation+8.54e-01

Pos logit contributions
obar+1.573
 inadvert+1.543
20439+1.523
esty+1.486
 XY+1.476
Neg logit contributions
Msg-1.182
aida-1.140
 Belg-1.088
jac-1.086
hess-1.066
Token their
Token ID511
Feature activation-6.51e-02

Pos logit contributions
obar+0.530
20439+0.515
 inadvert+0.515
esty+0.490
 XY+0.485
Neg logit contributions
Msg-0.643
aida-0.627
 Belg-0.608
jac-0.595
hess-0.587
Token Bern
Token ID6206
Feature activation+1.38e+00

Pos logit contributions
Msg+0.049
aida+0.048
 Belg+0.047
jac+0.045
hess+0.045
Neg logit contributions
obar-0.040
20439-0.040
 inadvert-0.039
esty-0.037
 XY-0.037
Token cl
Token ID537
Feature activation-1.66e+00

Pos logit contributions
obar+0.045
 inadvert+0.045
20439+0.044
esty+0.043
 um+0.042
Neg logit contributions
Msg-0.050
aida-0.049
 Belg-0.048
jac-0.047
hess-0.046
Tokenapped
Token ID6320
Feature activation-7.07e-01

Pos logit contributions
Msg+0.926
aida+0.900
 Belg+0.866
jac+0.834
hess+0.818
Neg logit contributions
obar-1.350
20439-1.332
 inadvert-1.320
esty-1.272
 XY-1.262
Token during
Token ID1141
Feature activation+9.51e-01

Pos logit contributions
Msg+0.537
aida+0.525
 Belg+0.512
jac+0.497
hess+0.491
Neg logit contributions
obar-0.433
20439-0.423
 inadvert-0.420
esty-0.400
 XY-0.395
Token high
Token ID1029
Feature activation-3.24e-01

Pos logit contributions
obar+0.600
 inadvert+0.583
20439+0.582
esty+0.555
 XY+0.551
Neg logit contributions
Msg-0.706
aida-0.691
 Belg-0.672
jac-0.652
hess-0.645
Token-
Token ID12
Feature activation+2.15e+00

Pos logit contributions
Msg+0.226
aida+0.220
 Belg+0.213
hess+0.206
jac+0.206
Neg logit contributions
obar-0.220
 inadvert-0.216
20439-0.212
esty-0.205
 um-0.204
Tokenprofile
Token ID13317
Feature activation+4.42e+00

Pos logit contributions
obar+0.856
 inadvert+0.801
20439+0.799
esty+0.741
 um+0.727
Neg logit contributions
Msg-2.105
aida-2.056
 Belg-2.034
hess-1.951
jac-1.941
Token Senate
Token ID3845
Feature activation-3.65e-01

Pos logit contributions
obar+2.390
 inadvert+2.380
20439+2.278
 um+2.245
 XY+2.236
Neg logit contributions
Msg-3.590
aida-3.550
 Belg-3.437
jac-3.354
hess-3.329
Token committee
Token ID5583
Feature activation+1.87e+00

Pos logit contributions
Msg+0.311
aida+0.304
 Belg+0.298
jac+0.291
hess+0.287
Neg logit contributions
obar-0.191
20439-0.186
 inadvert-0.182
esty-0.172
 XY-0.170
Token hearings
Token ID18921
Feature activation+1.32e+00

Pos logit contributions
obar+0.734
 inadvert+0.708
20439+0.705
esty+0.663
 um+0.648
Neg logit contributions
Msg-1.827
aida-1.804
 Belg-1.765
jac-1.722
hess-1.705
Token.
Token ID13
Feature activation+1.99e-01

Pos logit contributions
obar+0.788
 inadvert+0.764
20439+0.764
esty+0.728
 XY+0.720
Neg logit contributions
Msg-1.029
aida-1.009
 Belg-0.982
jac-0.959
hess-0.945
Token
Token ID198
Feature activation-4.84e-01

Pos logit contributions
obar+0.096
20439+0.093
 inadvert+0.092
esty+0.087
 XY+0.086
Neg logit contributions
Msg-0.177
aida-0.174
 Belg-0.170
jac-0.166
hess-0.164
Token W
Token ID370
Feature activation+5.59e-01

Pos logit contributions
obar+0.575
 inadvert+0.546
 XY+0.524
20439+0.520
esty+0.513
Neg logit contributions
Msg-0.994
aida-0.972
 Belg-0.939
jac-0.927
hess-0.924
Tokenaz
Token ID1031
Feature activation-5.81e-01

Pos logit contributions
obar+0.298
20439+0.291
 inadvert+0.288
esty+0.272
 XY+0.268
Neg logit contributions
Msg-0.469
aida-0.460
 Belg-0.448
jac-0.437
hess-0.432
Tokenir
Token ID343
Feature activation-1.34e+00

Pos logit contributions
Msg+0.625
aida+0.619
 Belg+0.603
jac+0.594
hess+0.590
Neg logit contributions
obar-0.169
20439-0.166
 inadvert-0.160
esty-0.142
 XY-0.140
Tokenistan
Token ID4103
Feature activation-1.86e+00

Pos logit contributions
Msg+1.338
aida+1.298
 Belg+1.286
jac+1.257
hess+1.245
Neg logit contributions
obar-0.513
 inadvert-0.482
20439-0.478
esty-0.456
 um-0.437
Token air
Token ID1633
Feature activation+1.04e+00

Pos logit contributions
Msg+1.272
aida+1.239
 Belg+1.205
jac+1.162
hess+1.149
Neg logit contributions
obar-1.284
20439-1.264
 inadvert-1.244
esty-1.197
 XY-1.180
Token raids
Token ID20371
Feature activation+4.40e+00

Pos logit contributions
obar+0.541
20439+0.521
 inadvert+0.521
esty+0.493
 XY+0.485
Neg logit contributions
Msg-0.885
aida-0.865
 Belg-0.849
jac-0.827
hess-0.819
Token.
Token ID13
Feature activation+3.64e-01

Pos logit contributions
obar+2.272
 inadvert+2.187
20439+2.118
 um+2.051
esty+2.049
Neg logit contributions
Msg-3.736
aida-3.666
 Belg-3.549
jac-3.537
hess-3.448
Token
Token ID198
Feature activation-3.86e-01

Pos logit contributions
obar+0.175
20439+0.170
 inadvert+0.167
esty+0.158
 XY+0.156
Neg logit contributions
Msg-0.325
aida-0.318
 Belg-0.310
jac-0.304
hess-0.302
Token
Token ID198
Feature activation-1.32e-01

Pos logit contributions
Msg+0.340
aida+0.332
 Belg+0.326
jac+0.318
hess+0.314
Neg logit contributions
obar-0.191
20439-0.185
 inadvert-0.184
esty-0.173
 accidental-0.168
TokenK
Token ID42
Feature activation-8.04e-01

Pos logit contributions
Msg+0.091
aida+0.089
 Belg+0.087
jac+0.084
hess+0.083
Neg logit contributions
obar-0.090
20439-0.088
 inadvert-0.087
esty-0.084
 XY-0.083
Tokenhy
Token ID12114
Feature activation+4.08e-01

Pos logit contributions
Msg+0.552
aida+0.541
 Belg+0.521
jac+0.508
hess+0.500
Neg logit contributions
obar-0.548
20439-0.545
 inadvert-0.537
esty-0.513
 XY-0.509
Token to
Token ID284
Feature activation+8.17e-01

Pos logit contributions
obar+0.019
 inadvert+0.018
20439+0.018
esty+0.017
 XY+0.017
Neg logit contributions
Msg-0.025
aida-0.025
 Belg-0.024
jac-0.024
hess-0.023
Token make
Token ID787
Feature activation+1.63e+00

Pos logit contributions
obar+0.462
 inadvert+0.449
20439+0.443
esty+0.423
 XY+0.419
Neg logit contributions
Msg-0.660
aida-0.646
 Belg-0.630
jac-0.615
hess-0.609
Token employee
Token ID6538
Feature activation+1.21e+00

Pos logit contributions
obar+0.998
 inadvert+0.987
20439+0.955
esty+0.930
 accidental+0.921
Neg logit contributions
Msg-1.232
aida-1.213
 Belg-1.173
jac-1.147
hess-1.135
Token protections
Token ID15018
Feature activation+2.33e+00

Pos logit contributions
obar+0.719
 inadvert+0.711
20439+0.700
esty+0.671
 XY+0.668
Neg logit contributions
Msg-0.939
aida-0.924
 Belg-0.896
jac-0.874
hess-0.864
Token more
Token ID517
Feature activation+7.10e-02

Pos logit contributions
obar+1.347
 inadvert+1.321
20439+1.302
esty+1.245
 XY+1.236
Neg logit contributions
Msg-1.842
aida-1.808
 Belg-1.757
jac-1.720
hess-1.698
Token explicit
Token ID7952
Feature activation+4.39e+00

Pos logit contributions
obar+0.043
20439+0.042
 inadvert+0.041
esty+0.039
 XY+0.039
Neg logit contributions
Msg-0.055
aida-0.054
 Belg-0.052
jac-0.051
hess-0.050
Token.
Token ID13
Feature activation+7.08e-02

Pos logit contributions
obar+2.241
 inadvert+2.188
20439+2.114
esty+2.082
 um+2.072
Neg logit contributions
Msg-3.686
aida-3.640
 Belg-3.546
jac-3.484
hess-3.406
Token
Token ID198
Feature activation-3.66e-01

Pos logit contributions
obar+0.038
20439+0.037
 inadvert+0.037
esty+0.035
 XY+0.034
Neg logit contributions
Msg-0.059
aida-0.058
 Belg-0.057
jac-0.055
hess-0.055
Token
Token ID198
Feature activation-6.51e-02

Pos logit contributions
Msg+0.321
aida+0.314
 Belg+0.307
jac+0.300
hess+0.296
Neg logit contributions
obar-0.183
20439-0.179
 inadvert-0.177
esty-0.166
 accidental-0.162
TokenDoes
Token ID13921
Feature activation+2.59e-01

Pos logit contributions
Msg+0.045
aida+0.044
 Belg+0.043
jac+0.042
hess+0.041
Neg logit contributions
obar-0.044
20439-0.043
 inadvert-0.043
esty-0.041
 XY-0.041
Tokenn
Token ID77
Feature activation-3.84e-02

Pos logit contributions
obar+0.171
 inadvert+0.167
20439+0.165
esty+0.160
 XY+0.157
Neg logit contributions
Msg-0.185
aida-0.182
 Belg-0.176
jac-0.170
hess-0.169
Token Wash
Token ID22892
Feature activation-8.27e-01

Pos logit contributions
obar+1.491
 inadvert+1.456
20439+1.443
esty+1.398
 Sear+1.386
Neg logit contributions
Msg-1.579
aida-1.540
 Belg-1.493
jac-1.445
hess-1.444
Token,
Token ID11
Feature activation+6.94e-02

Pos logit contributions
Msg+0.658
aida+0.644
 Belg+0.628
jac+0.611
hess+0.605
Neg logit contributions
obar-0.476
20439-0.464
 inadvert-0.462
esty-0.440
 XY-0.434
Token Steven
Token ID8239
Feature activation+5.10e-02

Pos logit contributions
obar+0.044
20439+0.043
 inadvert+0.043
esty+0.041
 XY+0.041
Neg logit contributions
Msg-0.051
aida-0.050
 Belg-0.048
jac-0.047
hess-0.047
Token La
Token ID4689
Feature activation-6.52e-01

Pos logit contributions
obar+0.034
20439+0.033
 inadvert+0.033
esty+0.031
 XY+0.031
Neg logit contributions
Msg-0.036
aida-0.035
 Belg-0.034
jac-0.033
hess-0.033
TokenM
Token ID44
Feature activation-6.01e-01

Pos logit contributions
Msg+0.451
aida+0.439
 Belg+0.427
jac+0.414
hess+0.408
Neg logit contributions
obar-0.445
20439-0.436
 inadvert-0.432
esty-0.415
 XY-0.410
Tokenears
Token ID4127
Feature activation+4.36e+00

Pos logit contributions
Msg+0.393
aida+0.381
 Belg+0.371
jac+0.358
hess+0.353
Neg logit contributions
obar-0.433
20439-0.424
 inadvert-0.421
esty-0.405
 XY-0.400
Token,
Token ID11
Feature activation+2.38e-01

Pos logit contributions
obar+2.399
 inadvert+2.344
20439+2.300
esty+2.269
 mm+2.219
Neg logit contributions
Msg-3.502
aida-3.384
 Belg-3.320
hess-3.196
jac-3.195
Token U
Token ID471
Feature activation+2.23e-01

Pos logit contributions
obar+0.152
20439+0.149
 inadvert+0.148
esty+0.141
 XY+0.140
Neg logit contributions
Msg-0.175
aida-0.171
 Belg-0.166
jac-0.161
hess-0.159
Token.
Token ID13
Feature activation+1.13e+00

Pos logit contributions
obar+0.146
20439+0.143
 inadvert+0.142
esty+0.136
 XY+0.134
Neg logit contributions
Msg-0.160
aida-0.156
 Belg-0.152
jac-0.148
hess-0.146
TokenS
Token ID50
Feature activation+7.76e-01

Pos logit contributions
obar+0.724
20439+0.704
 inadvert+0.698
esty+0.671
 um+0.660
Neg logit contributions
Msg-0.833
aida-0.813
 Belg-0.792
jac-0.771
hess-0.759
Token.
Token ID13
Feature activation+1.73e+00

Pos logit contributions
obar+0.424
20439+0.411
 inadvert+0.410
esty+0.391
 XY+0.384
Neg logit contributions
Msg-0.638
aida-0.622
 Belg-0.610
jac-0.595
hess-0.588
Token from
Token ID422
Feature activation-3.07e-01

Pos logit contributions
obar+1.275
 inadvert+1.260
20439+1.235
esty+1.193
 um+1.185
Neg logit contributions
Msg-1.711
aida-1.687
 Belg-1.629
jac-1.595
hess-1.573
Token the
Token ID262
Feature activation+5.33e-01

Pos logit contributions
Msg+0.226
aida+0.221
 Belg+0.216
jac+0.208
hess+0.206
Neg logit contributions
obar-0.195
20439-0.190
 inadvert-0.187
esty-0.180
 XY-0.177
Token beginning
Token ID3726
Feature activation+1.33e+00

Pos logit contributions
obar+0.276
20439+0.268
 inadvert+0.265
esty+0.251
 XY+0.247
Neg logit contributions
Msg-0.456
aida-0.446
 Belg-0.436
jac-0.425
hess-0.421
Token that
Token ID326
Feature activation+2.47e-01

Pos logit contributions
obar+0.889
20439+0.880
 inadvert+0.877
esty+0.840
 XY+0.831
Neg logit contributions
Msg-0.935
aida-0.904
 Belg-0.873
jac-0.859
hess-0.848
Token Ber
Token ID4312
Feature activation-1.37e+00

Pos logit contributions
obar+0.132
20439+0.128
 inadvert+0.127
esty+0.120
 XY+0.118
Neg logit contributions
Msg-0.208
aida-0.204
 Belg-0.199
jac-0.194
hess-0.192
Tokengd
Token ID21287
Feature activation+4.32e+00

Pos logit contributions
Msg+1.234
aida+1.209
 Belg+1.185
jac+1.156
hess+1.144
Neg logit contributions
obar-0.642
20439-0.622
 inadvert-0.615
esty-0.578
 XY-0.567
Tokenahl
Token ID15668
Feature activation-1.37e+00

Pos logit contributions
obar+2.523
 inadvert+2.365
20439+2.333
esty+2.287
 um+2.261
Neg logit contributions
Msg-3.433
 Belg-3.322
aida-3.287
jac-3.167
hess-3.114
Token had
Token ID550
Feature activation+4.75e-01

Pos logit contributions
Msg+1.018
aida+0.995
 Belg+0.969
jac+0.940
hess+0.928
Neg logit contributions
obar-0.860
20439-0.843
 inadvert-0.832
esty-0.796
 XY-0.784
Token not
Token ID407
Feature activation+6.24e-03

Pos logit contributions
obar+0.299
 inadvert+0.295
20439+0.290
esty+0.278
 um+0.277
Neg logit contributions
Msg-0.352
aida-0.344
 Belg-0.333
jac-0.329
hess-0.322
Token been
Token ID587
Feature activation-4.85e-01

Pos logit contributions
obar+0.004
20439+0.004
 inadvert+0.004
esty+0.004
 XY+0.004
Neg logit contributions
Msg-0.005
aida-0.005
 Belg-0.004
jac-0.004
hess-0.004
Token captured
Token ID7907
Feature activation+3.40e-01

Pos logit contributions
Msg+0.375
aida+0.366
 Belg+0.357
jac+0.348
hess+0.343
Neg logit contributions
obar-0.291
20439-0.284
 inadvert-0.283
esty-0.269
 XY-0.265
Token Marine
Token ID11000
Feature activation+8.94e-01

Pos logit contributions
obar+0.025
20439+0.025
 inadvert+0.024
esty+0.023
 XY+0.023
Neg logit contributions
Msg-0.029
aida-0.028
 Belg-0.027
jac-0.027
hess-0.027
Token Division
Token ID7458
Feature activation+2.70e+00

Pos logit contributions
obar+0.661
20439+0.649
 inadvert+0.646
esty+0.622
 mm+0.619
Neg logit contributions
Msg-0.566
aida-0.545
 Belg-0.523
jac-0.508
hess-0.501
Token,
Token ID11
Feature activation-6.15e-02

Pos logit contributions
obar+1.545
 inadvert+1.530
20439+1.505
esty+1.452
 XY+1.443
Neg logit contributions
Msg-2.139
aida-2.087
 Belg-1.974
jac-1.960
hess-1.946
Token participated
Token ID14888
Feature activation+6.96e-01

Pos logit contributions
Msg+0.045
aida+0.044
 Belg+0.042
jac+0.041
hess+0.041
Neg logit contributions
obar-0.040
 inadvert-0.039
20439-0.039
esty-0.037
 XY-0.036
Token in
Token ID287
Feature activation+5.50e-01

Pos logit contributions
obar+0.436
 inadvert+0.423
20439+0.420
esty+0.402
 XY+0.400
Neg logit contributions
Msg-0.521
aida-0.509
 Belg-0.494
jac-0.481
hess-0.476
Token Operation
Token ID14680
Feature activation+4.30e+00

Pos logit contributions
obar+0.352
20439+0.343
 inadvert+0.341
esty+0.326
 XY+0.322
Neg logit contributions
Msg-0.404
aida-0.394
 Belg-0.383
jac-0.372
hess-0.368
Token Winter
Token ID10633
Feature activation+2.01e-01

Pos logit contributions
obar+2.741
20439+2.668
 inadvert+2.648
 XY+2.605
 Sear+2.586
Neg logit contributions
Msg-3.108
aida-3.058
jac-2.855
hess-2.833
 Belg-2.822
Token Storm
Token ID8865
Feature activation+3.05e-01

Pos logit contributions
obar+0.141
20439+0.137
 inadvert+0.136
esty+0.131
 XY+0.130
Neg logit contributions
Msg-0.136
aida-0.133
 Belg-0.128
jac-0.124
hess-0.122
Token.
Token ID13
Feature activation+1.56e-01

Pos logit contributions
obar+0.186
20439+0.181
 inadvert+0.180
esty+0.172
 XY+0.169
Neg logit contributions
Msg-0.234
aida-0.228
 Belg-0.222
jac-0.216
hess-0.213
Token This
Token ID770
Feature activation+1.01e-01

Pos logit contributions
obar+0.096
20439+0.094
 inadvert+0.093
esty+0.089
 XY+0.088
Neg logit contributions
Msg-0.118
aida-0.116
 Belg-0.112
jac-0.109
hess-0.108
Token was
Token ID373
Feature activation+5.11e-01

Pos logit contributions
obar+0.057
20439+0.055
 inadvert+0.055
esty+0.052
 XY+0.052
Neg logit contributions
Msg-0.082
aida-0.080
 Belg-0.078
jac-0.076
hess-0.075
Token immigrant
Token ID15773
Feature activation-6.53e-01

Pos logit contributions
obar+0.413
 inadvert+0.407
20439+0.401
 accidental+0.386
 XY+0.385
Neg logit contributions
Msg-0.426
aida-0.414
 Belg-0.398
jac-0.392
hess-0.388
Token argued
Token ID7189
Feature activation-1.16e+00

Pos logit contributions
Msg+0.483
aida+0.472
 Belg+0.455
jac+0.449
hess+0.440
Neg logit contributions
obar-0.413
 inadvert-0.406
20439-0.399
 XY-0.382
esty-0.382
Token that
Token ID326
Feature activation-1.54e-01

Pos logit contributions
Msg+0.774
aida+0.754
 Belg+0.724
jac+0.710
hess+0.699
Neg logit contributions
obar-0.818
 inadvert-0.799
20439-0.791
esty-0.767
 XY-0.760
Token the
Token ID262
Feature activation-2.33e-01

Pos logit contributions
Msg+0.105
aida+0.102
 Belg+0.098
jac+0.096
hess+0.094
Neg logit contributions
obar-0.107
 inadvert-0.105
20439-0.103
esty-0.100
 XY-0.099
Token tattoo
Token ID18785
Feature activation-2.69e+00

Pos logit contributions
Msg+0.157
aida+0.153
 Belg+0.147
jac+0.145
hess+0.143
Neg logit contributions
obar-0.162
 inadvert-0.160
20439-0.157
 accidental-0.152
 XY-0.152
Token sign
Token ID1051
Feature activation-6.14e+00

Pos logit contributions
Msg+2.012
aida+1.964
 Belg+1.914
jac+1.857
hess+1.834
Neg logit contributions
obar-1.682
20439-1.647
 inadvert-1.625
esty-1.553
 XY-1.532
Tokenified
Token ID1431
Feature activation-1.88e+00

Pos logit contributions
Msg+4.517
aida+4.398
 Belg+4.195
hess+4.104
jac+4.102
Neg logit contributions
20439-3.940
obar-3.749
 inadvert-3.577
 XY-3.456
 um-3.403
Token his
Token ID465
Feature activation-4.96e-01

Pos logit contributions
Msg+1.293
aida+1.259
 Belg+1.226
jac+1.185
hess+1.169
Neg logit contributions
obar-1.286
20439-1.261
 inadvert-1.247
esty-1.198
 XY-1.182
Token place
Token ID1295
Feature activation-1.14e+00

Pos logit contributions
Msg+0.374
aida+0.365
 Belg+0.356
jac+0.346
hess+0.342
Neg logit contributions
obar-0.307
20439-0.299
 inadvert-0.298
esty-0.284
 XY-0.281
Token of
Token ID286
Feature activation-6.47e-02

Pos logit contributions
Msg+0.889
aida+0.869
 Belg+0.848
jac+0.823
hess+0.813
Neg logit contributions
obar-0.668
20439-0.656
 inadvert-0.645
esty-0.615
 XY-0.604
Token birth
Token ID4082
Feature activation-5.44e-01

Pos logit contributions
Msg+0.057
aida+0.056
 Belg+0.054
jac+0.053
hess+0.052
Neg logit contributions
obar-0.032
20439-0.031
 inadvert-0.031
esty-0.029
 XY-0.029
Token-
Token ID12
Feature activation-1.63e-01

Pos logit contributions
Msg+0.762
aida+0.742
 Belg+0.722
jac+0.699
hess+0.689
Neg logit contributions
obar-0.754
20439-0.738
 inadvert-0.734
esty-0.703
 XY-0.695
Token11
Token ID1157
Feature activation+8.85e-01

Pos logit contributions
Msg+0.121
aida+0.118
 Belg+0.117
jac+0.111
hess+0.109
Neg logit contributions
obar-0.103
20439-0.101
 inadvert-0.100
esty-0.096
 um-0.095
Token season
Token ID1622
Feature activation-3.51e-01

Pos logit contributions
obar+0.531
 inadvert+0.522
20439+0.515
esty+0.494
 um+0.493
Neg logit contributions
Msg-0.681
aida-0.661
 Belg-0.643
jac-0.630
hess-0.622
Token.
Token ID13
Feature activation-2.34e-01

Pos logit contributions
Msg+0.282
aida+0.275
 Belg+0.269
jac+0.262
hess+0.258
Neg logit contributions
obar-0.200
 inadvert-0.195
20439-0.194
esty-0.184
 um-0.182
Token He
Token ID679
Feature activation-8.35e-02

Pos logit contributions
Msg+0.175
aida+0.171
 Belg+0.166
jac+0.162
hess+0.160
Neg logit contributions
obar-0.145
20439-0.142
 inadvert-0.141
esty-0.134
 XY-0.134
Token signed
Token ID4488
Feature activation-5.90e+00

Pos logit contributions
Msg+0.061
aida+0.059
 Belg+0.058
jac+0.056
hess+0.055
Neg logit contributions
obar-0.054
 inadvert-0.052
20439-0.052
esty-0.050
 XY-0.049
Token a
Token ID257
Feature activation-1.03e+00

Pos logit contributions
Msg+3.580
aida+3.486
 Belg+3.430
jac+3.243
hess+3.224
Neg logit contributions
obar-4.386
20439-4.381
 inadvert-4.207
esty-4.100
 XY-4.020
Token five
Token ID1936
Feature activation-4.30e-01

Pos logit contributions
Msg+0.735
aida+0.718
 Belg+0.694
jac+0.678
hess+0.666
Neg logit contributions
obar-0.676
 inadvert-0.663
20439-0.661
esty-0.632
 um-0.625
Token-
Token ID12
Feature activation-1.98e-02

Pos logit contributions
Msg+0.291
aida+0.284
 Belg+0.276
jac+0.269
hess+0.264
Neg logit contributions
obar-0.299
20439-0.291
 inadvert-0.291
esty-0.280
 um-0.276
Tokenyear
Token ID1941
Feature activation+3.40e-01

Pos logit contributions
Msg+0.015
aida+0.014
 Belg+0.014
jac+0.013
hess+0.013
Neg logit contributions
obar-0.012
20439-0.012
 inadvert-0.012
esty-0.012
 XY-0.011
Token contract
Token ID2775
Feature activation-1.67e+00

Pos logit contributions
obar+0.203
 inadvert+0.200
20439+0.197
esty+0.188
 um+0.187
Neg logit contributions
Msg-0.264
aida-0.258
 Belg-0.248
jac-0.246
hess-0.241
Token she
Token ID673
Feature activation-6.61e-01

Pos logit contributions
Msg+0.353
aida+0.344
 Belg+0.332
jac+0.324
hess+0.320
Neg logit contributions
obar-0.345
 inadvert-0.340
20439-0.334
esty-0.321
 accidental-0.321
Token apparently
Token ID5729
Feature activation+2.35e-01

Pos logit contributions
Msg+0.490
aida+0.478
 Belg+0.465
jac+0.452
hess+0.447
Neg logit contributions
obar-0.418
 inadvert-0.408
20439-0.407
esty-0.388
 XY-0.383
Token ran
Token ID4966
Feature activation+5.17e-02

Pos logit contributions
obar+0.147
 inadvert+0.145
20439+0.142
esty+0.137
 um+0.136
Neg logit contributions
Msg-0.176
aida-0.172
 Belg-0.166
jac-0.162
hess-0.160
Token a
Token ID257
Feature activation-9.39e-02

Pos logit contributions
obar+0.034
 inadvert+0.033
20439+0.033
esty+0.032
 accidental+0.031
Neg logit contributions
Msg-0.037
aida-0.036
 Belg-0.035
jac-0.034
hess-0.034
Token stop
Token ID2245
Feature activation+1.95e+00

Pos logit contributions
Msg+0.076
aida+0.075
 Belg+0.072
jac+0.071
hess+0.070
Neg logit contributions
obar-0.052
 inadvert-0.052
20439-0.050
 um-0.048
 accidental-0.048
Token sign
Token ID1051
Feature activation-5.84e+00

Pos logit contributions
obar+1.544
 inadvert+1.496
20439+1.471
esty+1.444
 um+1.443
Neg logit contributions
Msg-1.121
aida-1.088
 Belg-1.062
jac-1.021
hess-1.011
Token and
Token ID290
Feature activation-7.23e-01

Pos logit contributions
Msg+3.868
aida+3.757
 Belg+3.696
jac+3.471
hess+3.467
Neg logit contributions
20439-4.097
obar-3.981
 inadvert-3.742
esty-3.675
 XY-3.628
Token slammed
Token ID21376
Feature activation-2.99e+00

Pos logit contributions
Msg+0.541
aida+0.529
 Belg+0.510
jac+0.501
hess+0.495
Neg logit contributions
obar-0.452
 inadvert-0.446
20439-0.436
esty-0.420
 accidental-0.417
Token into
Token ID656
Feature activation+2.81e-01

Pos logit contributions
Msg+1.988
aida+1.935
 Belg+1.882
jac+1.818
hess+1.791
Neg logit contributions
obar-2.111
20439-2.072
 inadvert-2.052
esty-1.972
 XY-1.948
Token the
Token ID262
Feature activation-1.12e-01

Pos logit contributions
obar+0.187
 inadvert+0.183
20439+0.178
 um+0.174
esty+0.174
Neg logit contributions
Msg-0.199
aida-0.195
 Belg-0.186
hess-0.183
jac-0.183
Token side
Token ID1735
Feature activation-1.71e+00

Pos logit contributions
Msg+0.080
aida+0.079
 Belg+0.076
jac+0.074
hess+0.073
Neg logit contributions
obar-0.073
 inadvert-0.071
20439-0.071
esty-0.068
 um-0.068
Tokenacious
Token ID14209
Feature activation-1.03e+00

Pos logit contributions
Msg+0.635
aida+0.616
 Belg+0.597
jac+0.573
hess+0.562
Neg logit contributions
obar-0.867
20439-0.850
 inadvert-0.845
esty-0.817
 XY-0.806
Token goal
Token ID3061
Feature activation-3.57e+00

Pos logit contributions
Msg+0.768
aida+0.750
 Belg+0.730
jac+0.709
hess+0.700
Neg logit contributions
obar-0.648
20439-0.633
 inadvert-0.629
esty-0.601
 XY-0.593
Token of
Token ID286
Feature activation-6.46e-01

Pos logit contributions
Msg+2.722
aida+2.652
 Belg+2.593
jac+2.516
hess+2.489
Neg logit contributions
obar-2.173
20439-2.133
 inadvert-2.093
esty-1.988
 XY-1.964
Token cities
Token ID4736
Feature activation-3.12e-01

Pos logit contributions
Msg+0.474
aida+0.463
 Belg+0.449
jac+0.437
hess+0.433
Neg logit contributions
obar-0.415
20439-0.404
 inadvert-0.403
esty-0.384
 XY-0.381
Token who
Token ID508
Feature activation+6.43e-01

Pos logit contributions
Msg+0.238
aida+0.232
 Belg+0.226
jac+0.220
hess+0.217
Neg logit contributions
obar-0.191
20439-0.186
 inadvert-0.185
esty-0.176
 XY-0.174
Token sign
Token ID1051
Feature activation-5.80e+00

Pos logit contributions
obar+0.371
 inadvert+0.362
20439+0.357
esty+0.341
 um+0.339
Neg logit contributions
Msg-0.512
aida-0.499
 Belg-0.487
jac-0.475
hess-0.470
Token up
Token ID510
Feature activation-1.74e+00

Pos logit contributions
Msg+4.017
aida+3.882
 Belg+3.835
jac+3.682
hess+3.634
Neg logit contributions
obar-3.838
20439-3.824
 inadvert-3.705
esty-3.549
 XY-3.544
Token to
Token ID284
Feature activation-6.35e-02

Pos logit contributions
Msg+1.282
aida+1.252
 Belg+1.219
jac+1.184
hess+1.168
Neg logit contributions
obar-1.102
20439-1.077
 inadvert-1.068
esty-1.021
 XY-1.008
Token be
Token ID307
Feature activation-4.19e-01

Pos logit contributions
Msg+0.048
aida+0.047
 Belg+0.046
jac+0.045
hess+0.044
Neg logit contributions
obar-0.039
20439-0.038
 inadvert-0.038
esty-0.036
 XY-0.036
Token part
Token ID636
Feature activation-5.32e-01

Pos logit contributions
Msg+0.309
aida+0.302
 Belg+0.293
jac+0.286
hess+0.282
Neg logit contributions
obar-0.268
20439-0.261
 inadvert-0.259
esty-0.248
 XY-0.245
Token of
Token ID286
Feature activation-9.16e-01

Pos logit contributions
Msg+0.432
aida+0.423
 Belg+0.413
jac+0.402
hess+0.397
Neg logit contributions
obar-0.299
20439-0.291
 inadvert-0.288
esty-0.273
 XY-0.269
Token going
Token ID1016
Feature activation-4.91e-02

Pos logit contributions
Msg+0.015
aida+0.014
 Belg+0.014
jac+0.014
hess+0.013
Neg logit contributions
obar-0.015
20439-0.015
 inadvert-0.015
esty-0.014
 XY-0.014
Token back
Token ID736
Feature activation-1.09e-01

Pos logit contributions
Msg+0.034
aida+0.033
 Belg+0.033
jac+0.032
hess+0.031
Neg logit contributions
obar-0.033
20439-0.032
 inadvert-0.032
esty-0.031
 XY-0.031
Token unless
Token ID4556
Feature activation-5.34e-01

Pos logit contributions
Msg+0.074
aida+0.072
 Belg+0.070
jac+0.067
hess+0.066
Neg logit contributions
obar-0.076
20439-0.074
 inadvert-0.073
esty-0.070
 XY-0.070
Token
Token ID564
Feature activation+2.82e-01

Pos logit contributions
Msg+0.372
aida+0.363
 Belg+0.353
jac+0.343
hess+0.338
Neg logit contributions
obar-0.361
20439-0.353
 inadvert-0.351
esty-0.336
 XY-0.332
Token
Token ID250
Feature activation-4.65e-01

Pos logit contributions
obar+0.215
20439+0.210
 inadvert+0.209
esty+0.202
 XY+0.199
Neg logit contributions
Msg-0.173
aida-0.167
 Belg-0.164
jac-0.157
hess-0.155
Tokensign
Token ID12683
Feature activation-5.64e+00

Pos logit contributions
Msg+0.281
aida+0.273
 Belg+0.264
jac+0.255
hess+0.251
Neg logit contributions
obar-0.358
20439-0.351
 inadvert-0.349
esty-0.336
 XY-0.332
Tokenals
Token ID874
Feature activation-2.27e+00

Pos logit contributions
Msg+4.573
aida+4.469
 Belg+4.323
jac+4.245
hess+4.206
Neg logit contributions
obar-3.020
20439-3.008
 inadvert-2.922
 accidental-2.739
 XY-2.734
Token are
Token ID389
Feature activation-2.32e-01

Pos logit contributions
Msg+1.765
aida+1.732
 Belg+1.682
jac+1.628
hess+1.605
Neg logit contributions
obar-1.351
20439-1.316
 inadvert-1.284
esty-1.231
 XY-1.208
Token sent
Token ID1908
Feature activation-7.55e-01

Pos logit contributions
Msg+0.180
aida+0.176
 Belg+0.172
jac+0.167
hess+0.165
Neg logit contributions
obar-0.138
20439-0.135
 inadvert-0.134
esty-0.127
 XY-0.126
Token
Token ID447
Feature activation+4.91e-01

Pos logit contributions
Msg+0.534
aida+0.521
 Belg+0.507
jac+0.491
hess+0.484
Neg logit contributions
obar-0.503
20439-0.492
 inadvert-0.488
esty-0.467
 XY-0.462
Token
Token ID251
Feature activation+3.84e-01

Pos logit contributions
obar+0.392
20439+0.384
 inadvert+0.384
esty+0.371
 XY+0.366
Neg logit contributions
Msg-0.282
aida-0.271
 Belg-0.266
jac-0.255
hess-0.250
Token three
Token ID1115
Feature activation-4.74e-01

Pos logit contributions
Msg+1.079
aida+1.050
 Belg+1.022
jac+0.988
hess+0.974
Neg logit contributions
obar-1.109
20439-1.087
 inadvert-1.076
esty-1.034
 XY-1.020
Token thousand
Token ID7319
Feature activation+1.46e+00

Pos logit contributions
Msg+0.323
aida+0.315
 Belg+0.305
jac+0.297
hess+0.294
Neg logit contributions
obar-0.329
 inadvert-0.320
20439-0.319
esty-0.306
 um-0.303
Token IB
Token ID34782
Feature activation+2.35e-01

Pos logit contributions
obar+0.922
 inadvert+0.903
20439+0.890
esty+0.856
 um+0.855
Neg logit contributions
Msg-1.076
aida-1.052
 Belg-1.017
jac-0.994
hess-0.991
TokenEW
Token ID6217
Feature activation+1.40e-01

Pos logit contributions
obar+0.207
20439+0.204
 inadvert+0.203
esty+0.196
 XY+0.194
Neg logit contributions
Msg-0.116
aida-0.111
 Belg-0.107
jac-0.103
hess-0.100
Token members
Token ID1866
Feature activation-2.09e+00

Pos logit contributions
obar+0.081
20439+0.079
 inadvert+0.079
esty+0.075
 XY+0.074
Neg logit contributions
Msg-0.110
aida-0.108
 Belg-0.105
jac-0.102
hess-0.101
Token signed
Token ID4488
Feature activation-5.59e+00

Pos logit contributions
Msg+1.651
aida+1.619
 Belg+1.579
jac+1.532
hess+1.507
Neg logit contributions
obar-1.226
20439-1.206
 inadvert-1.174
esty-1.120
 XY-1.100
Token a
Token ID257
Feature activation-1.13e+00

Pos logit contributions
Msg+3.559
aida+3.430
 Belg+3.316
jac+3.206
hess+3.128
Neg logit contributions
obar-4.041
20439-4.023
 inadvert-3.919
esty-3.745
 XY-3.716
Token new
Token ID649
Feature activation-1.51e-01

Pos logit contributions
Msg+0.723
aida+0.705
 Belg+0.683
jac+0.661
hess+0.652
Neg logit contributions
obar-0.825
20439-0.808
 inadvert-0.807
esty-0.775
 XY-0.767
Token contract
Token ID2775
Feature activation-2.00e+00

Pos logit contributions
Msg+0.118
aida+0.115
 Belg+0.112
jac+0.109
hess+0.108
Neg logit contributions
obar-0.089
 inadvert-0.087
20439-0.087
esty-0.083
 um-0.082
Token with
Token ID351
Feature activation-1.42e+00

Pos logit contributions
Msg+1.359
aida+1.323
 Belg+1.287
jac+1.244
hess+1.227
Neg logit contributions
obar-1.383
20439-1.354
 inadvert-1.340
esty-1.288
 XY-1.271
Token Hydro
Token ID32116
Feature activation-1.64e+00

Pos logit contributions
Msg+0.902
aida+0.877
 Belg+0.850
jac+0.821
hess+0.809
Neg logit contributions
obar-1.046
20439-1.025
 inadvert-1.018
esty-0.979
 XY-0.968
Token announced
Token ID3414
Feature activation-1.28e+00

Pos logit contributions
Msg+0.567
aida+0.554
 Belg+0.540
jac+0.524
hess+0.518
Neg logit contributions
obar-0.467
20439-0.456
 inadvert-0.452
esty-0.431
 XY-0.426
Token that
Token ID326
Feature activation-3.61e-01

Pos logit contributions
Msg+0.874
aida+0.852
 Belg+0.826
jac+0.802
hess+0.790
Neg logit contributions
obar-0.882
20439-0.864
 inadvert-0.857
esty-0.821
 XY-0.814
Token the
Token ID262
Feature activation-6.48e-01

Pos logit contributions
Msg+0.241
aida+0.235
 Belg+0.227
jac+0.221
hess+0.217
Neg logit contributions
obar-0.255
20439-0.250
 inadvert-0.248
esty-0.237
 XY-0.237
Token company
Token ID1664
Feature activation-4.77e-01

Pos logit contributions
Msg+0.496
aida+0.484
 Belg+0.472
jac+0.459
hess+0.453
Neg logit contributions
obar-0.395
20439-0.385
 inadvert-0.382
esty-0.364
 XY-0.359
Token has
Token ID468
Feature activation-4.26e-01

Pos logit contributions
Msg+0.374
aida+0.366
 Belg+0.356
jac+0.347
hess+0.343
Neg logit contributions
obar-0.281
20439-0.274
 inadvert-0.272
esty-0.259
 XY-0.256
Token signed
Token ID4488
Feature activation-5.52e+00

Pos logit contributions
Msg+0.287
aida+0.280
 Belg+0.270
jac+0.263
hess+0.260
Neg logit contributions
obar-0.299
 inadvert-0.292
20439-0.291
esty-0.278
 XY-0.277
Token a
Token ID257
Feature activation-1.18e+00

Pos logit contributions
Msg+3.510
aida+3.386
 Belg+3.344
jac+3.176
hess+3.141
Neg logit contributions
obar-3.941
20439-3.869
 inadvert-3.821
esty-3.718
 um-3.623
Token deal
Token ID1730
Feature activation-2.22e+00

Pos logit contributions
Msg+0.802
aida+0.781
 Belg+0.758
jac+0.735
hess+0.724
Neg logit contributions
obar-0.819
20439-0.803
 inadvert-0.797
esty-0.764
 XY-0.756
Token with
Token ID351
Feature activation-1.43e+00

Pos logit contributions
Msg+1.420
aida+1.382
 Belg+1.339
jac+1.294
hess+1.273
Neg logit contributions
obar-1.625
20439-1.593
 inadvert-1.582
esty-1.520
 XY-1.505
Token Japan
Token ID2869
Feature activation-5.81e-01

Pos logit contributions
Msg+1.121
aida+1.096
 Belg+1.072
jac+1.039
hess+1.026
Neg logit contributions
obar-0.847
20439-0.827
 inadvert-0.818
esty-0.781
 XY-0.766
Token financial
Token ID3176
Feature activation+2.87e-01

Pos logit contributions
Msg+0.434
aida+0.425
 Belg+0.412
jac+0.403
hess+0.395
Neg logit contributions
obar-0.367
 inadvert-0.353
20439-0.352
esty-0.337
 XY-0.335
Token,
Token ID11
Feature activation-1.08e+00

Pos logit contributions
obar+0.431
20439+0.423
 inadvert+0.423
esty+0.401
 um+0.398
Neg logit contributions
Msg-0.526
aida-0.515
 Belg-0.503
jac-0.486
hess-0.484
Token 2004
Token ID5472
Feature activation-1.34e+00

Pos logit contributions
Msg+0.879
aida+0.859
 Belg+0.840
jac+0.816
hess+0.807
Neg logit contributions
obar-0.599
20439-0.583
 inadvert-0.576
esty-0.549
 XY-0.538
Token joint
Token ID6466
Feature activation+8.90e-01

Pos logit contributions
Msg+0.956
aida+0.933
 Belg+0.908
jac+0.879
hess+0.869
Neg logit contributions
obar-0.889
20439-0.871
 inadvert-0.865
esty-0.827
 XY-0.818
Token venture
Token ID13189
Feature activation-1.94e+00

Pos logit contributions
obar+0.610
20439+0.598
 inadvert+0.598
esty+0.568
 XY+0.566
Neg logit contributions
Msg-0.610
aida-0.597
 Belg-0.577
jac-0.558
hess-0.554
Token agreement
Token ID4381
Feature activation-1.47e+00

Pos logit contributions
Msg+1.278
aida+1.244
 Belg+1.207
jac+1.167
hess+1.150
Neg logit contributions
obar-1.390
20439-1.363
 inadvert-1.352
esty-1.299
 XY-1.285
Token signed
Token ID4488
Feature activation-5.51e+00

Pos logit contributions
Msg+1.096
aida+1.070
 Belg+1.040
jac+1.011
hess+0.998
Neg logit contributions
obar-0.924
20439-0.903
 inadvert-0.897
esty-0.855
 XY-0.846
Token between
Token ID1022
Feature activation+2.37e-01

Pos logit contributions
Msg+3.282
aida+3.166
 Belg+3.134
jac+2.988
hess+2.937
Neg logit contributions
obar-4.137
20439-4.095
 inadvert-4.014
esty-3.925
 XY-3.829
Token his
Token ID465
Feature activation-7.99e-01

Pos logit contributions
obar+0.156
 inadvert+0.152
20439+0.150
 XY+0.145
 um+0.143
Neg logit contributions
Msg-0.171
aida-0.166
 Belg-0.160
jac-0.157
hess-0.156
Token Muk
Token ID31509
Feature activation-5.05e-01

Pos logit contributions
Msg+0.609
aida+0.594
 Belg+0.577
jac+0.562
hess+0.556
Neg logit contributions
obar-0.490
 inadvert-0.476
20439-0.476
esty-0.451
 XY-0.448
Tokenta
Token ID8326
Feature activation-1.37e+00

Pos logit contributions
Msg+0.253
aida+0.240
 Belg+0.234
jac+0.221
hess+0.218
Neg logit contributions
obar-0.442
20439-0.430
 inadvert-0.429
esty-0.419
 um-0.413
Token Arts
Token ID11536
Feature activation-6.78e-01

Pos logit contributions
Msg+0.840
aida+0.812
 Belg+0.786
jac+0.759
hess+0.749
Neg logit contributions
obar-1.042
20439-1.016
 inadvert-1.014
esty-0.975
 XY-0.967
Token playoff
Token ID13119
Feature activation-1.38e+00

Pos logit contributions
obar+0.111
 inadvert+0.108
20439+0.107
esty+0.102
 XY+0.101
Neg logit contributions
Msg-0.151
aida-0.148
 Belg-0.144
jac-0.140
hess-0.139
Token round
Token ID2835
Feature activation+2.41e+00

Pos logit contributions
Msg+1.014
aida+0.989
 Belg+0.963
jac+0.935
hess+0.922
Neg logit contributions
obar-0.878
20439-0.861
 inadvert-0.849
esty-0.814
 XY-0.801
Token or
Token ID393
Feature activation+3.46e-01

Pos logit contributions
obar+1.410
 inadvert+1.372
20439+1.341
 XY+1.292
esty+1.288
Neg logit contributions
Msg-1.894
aida-1.860
 Belg-1.812
jac-1.761
hess-1.731
Token re
Token ID302
Feature activation+2.07e-01

Pos logit contributions
 inadvert+0.217
obar+0.217
20439+0.211
 XY+0.204
 accidental+0.204
Neg logit contributions
Msg-0.255
aida-0.250
 Belg-0.240
jac-0.238
hess-0.231
Token-
Token ID12
Feature activation-9.59e-01

Pos logit contributions
obar+0.151
 inadvert+0.145
20439+0.145
esty+0.141
 XY+0.139
Neg logit contributions
Msg-0.135
aida-0.130
 Belg-0.127
jac-0.122
hess-0.119
Tokensign
Token ID12683
Feature activation-5.47e+00

Pos logit contributions
Msg+0.310
aida+0.291
 Belg+0.277
jac+0.251
hess+0.242
Neg logit contributions
obar-1.011
20439-0.993
 inadvert-0.990
esty-0.966
 XY-0.956
Tokens
Token ID82
Feature activation-6.19e-01

Pos logit contributions
Msg+2.798
aida+2.686
 Belg+2.643
jac+2.519
hess+2.518
Neg logit contributions
obar-4.575
20439-4.566
 inadvert-4.476
esty-4.285
 accidental-4.276
Token Lang
Token ID16332
Feature activation-1.17e+00

Pos logit contributions
Msg+0.432
aida+0.421
 Belg+0.410
jac+0.397
hess+0.392
Neg logit contributions
obar-0.418
20439-0.409
 inadvert-0.406
esty-0.389
 XY-0.384
Tokenen
Token ID268
Feature activation+7.74e-01

Pos logit contributions
Msg+0.828
aida+0.811
 Belg+0.786
jac+0.765
hess+0.754
Neg logit contributions
obar-0.777
20439-0.763
 inadvert-0.756
esty-0.721
 XY-0.715
Tokenbr
Token ID1671
Feature activation-5.48e-01

Pos logit contributions
obar+0.600
20439+0.585
 inadvert+0.578
esty+0.561
 XY+0.554
Neg logit contributions
Msg-0.466
aida-0.452
 Belg-0.439
jac-0.417
hess-0.413
Tokenun
Token ID403
Feature activation+4.76e-01

Pos logit contributions
Msg+0.342
aida+0.337
 Belg+0.322
jac+0.314
hess+0.309
Neg logit contributions
obar-0.404
20439-0.403
 inadvert-0.400
esty-0.383
 XY-0.381
Token major
Token ID1688
Feature activation-6.76e-01

Pos logit contributions
obar+0.057
20439+0.055
 inadvert+0.055
esty+0.052
 XY+0.052
Neg logit contributions
Msg-0.068
aida-0.066
 Belg-0.064
jac-0.063
hess-0.062
Token tenants
Token ID21445
Feature activation-5.35e-01

Pos logit contributions
Msg+0.475
aida+0.461
 Belg+0.446
jac+0.437
hess+0.429
Neg logit contributions
obar-0.455
 inadvert-0.442
20439-0.442
esty-0.423
 XY-0.420
Token.
Token ID13
Feature activation-4.79e-01

Pos logit contributions
Msg+0.436
aida+0.427
 Belg+0.417
jac+0.406
hess+0.401
Neg logit contributions
obar-0.299
20439-0.290
 inadvert-0.288
esty-0.274
 XY-0.270
Token Google
Token ID3012
Feature activation+2.71e+00

Pos logit contributions
Msg+0.373
aida+0.365
 Belg+0.356
jac+0.346
hess+0.342
Neg logit contributions
obar-0.284
20439-0.277
 inadvert-0.274
esty-0.261
 XY-0.258
Token has
Token ID468
Feature activation-6.93e-01

Pos logit contributions
obar+1.649
 inadvert+1.594
20439+1.572
esty+1.523
 Sear+1.512
Neg logit contributions
Msg-2.066
aida-2.008
 Belg-1.942
jac-1.909
hess-1.878
Token signed
Token ID4488
Feature activation-5.47e+00

Pos logit contributions
Msg+0.506
aida+0.494
 Belg+0.480
jac+0.468
hess+0.461
Neg logit contributions
obar-0.447
20439-0.435
 inadvert-0.434
esty-0.414
 XY-0.410
Token on
Token ID319
Feature activation-1.07e+00

Pos logit contributions
Msg+3.473
aida+3.390
 Belg+3.329
jac+3.166
hess+3.125
Neg logit contributions
obar-3.896
20439-3.841
 inadvert-3.763
esty-3.611
 XY-3.575
Token to
Token ID284
Feature activation-4.22e-01

Pos logit contributions
Msg+0.788
aida+0.769
 Belg+0.750
jac+0.727
hess+0.718
Neg logit contributions
obar-0.678
20439-0.662
 inadvert-0.656
esty-0.627
 XY-0.619
Token take
Token ID1011
Feature activation+4.57e-01

Pos logit contributions
Msg+0.326
aida+0.318
 Belg+0.310
jac+0.302
hess+0.298
Neg logit contributions
obar-0.254
20439-0.246
 inadvert-0.246
esty-0.234
 XY-0.232
Token over
Token ID625
Feature activation+9.95e-02

Pos logit contributions
obar+0.289
 inadvert+0.279
20439+0.278
esty+0.266
 um+0.263
Neg logit contributions
Msg-0.341
aida-0.331
 Belg-0.323
jac-0.314
hess-0.312
Token a
Token ID257
Feature activation-6.79e-01

Pos logit contributions
obar+0.064
20439+0.063
 inadvert+0.062
esty+0.059
 XY+0.058
Neg logit contributions
Msg-0.073
aida-0.071
 Belg-0.069
jac-0.067
hess-0.066
Token intersection
Token ID16246
Feature activation+5.88e-01

Pos logit contributions
Msg+0.604
aida+0.590
 Belg+0.570
jac+0.559
hess+0.551
Neg logit contributions
obar-0.516
 inadvert-0.504
20439-0.501
esty-0.479
 um-0.476
Token while
Token ID981
Feature activation-6.07e-02

Pos logit contributions
obar+0.341
 inadvert+0.333
20439+0.331
esty+0.316
 um+0.312
Neg logit contributions
Msg-0.466
aida-0.455
 Belg-0.444
jac-0.432
hess-0.426
Token holding
Token ID4769
Feature activation-1.25e+00

Pos logit contributions
Msg+0.043
aida+0.042
 Belg+0.041
jac+0.040
hess+0.039
Neg logit contributions
obar-0.040
 inadvert-0.039
20439-0.039
esty-0.037
 um-0.037
Token his
Token ID465
Feature activation+4.94e-02

Pos logit contributions
Msg+0.902
aida+0.880
 Belg+0.856
jac+0.831
hess+0.821
Neg logit contributions
obar-0.818
20439-0.799
 inadvert-0.795
esty-0.760
 XY-0.750
Token stop
Token ID2245
Feature activation+2.07e+00

Pos logit contributions
obar+0.031
 inadvert+0.030
20439+0.030
esty+0.029
 XY+0.028
Neg logit contributions
Msg-0.037
aida-0.036
 Belg-0.035
jac-0.034
hess-0.034
Token sign
Token ID1051
Feature activation-5.44e+00

Pos logit contributions
obar+1.681
 inadvert+1.642
20439+1.628
esty+1.587
 um+1.580
Neg logit contributions
Msg-1.143
aida-1.099
 Belg-1.058
jac-1.032
hess-1.010
Token al
Token ID435
Feature activation-2.84e+00

Pos logit contributions
Msg+4.001
aida+3.896
 Belg+3.806
jac+3.661
hess+3.622
Neg logit contributions
20439-3.421
obar-3.351
 inadvert-3.220
esty-3.090
 XY-3.059
Tokenoft
Token ID11205
Feature activation+8.82e-01

Pos logit contributions
Msg+1.842
aida+1.791
 Belg+1.738
jac+1.679
hess+1.654
Neg logit contributions
obar-2.063
20439-2.024
 inadvert-2.008
esty-1.930
 XY-1.909
Token.
Token ID13
Feature activation-3.28e-01

Pos logit contributions
obar+0.489
 inadvert+0.473
20439+0.467
esty+0.449
 um+0.444
Neg logit contributions
Msg-0.720
aida-0.708
 Belg-0.689
jac-0.671
hess-0.666
Token While
Token ID2893
Feature activation+3.28e-01

Pos logit contributions
Msg+0.279
aida+0.273
 Belg+0.267
jac+0.261
hess+0.258
Neg logit contributions
obar-0.171
20439-0.166
 inadvert-0.164
esty-0.155
 XY-0.154
Token he
Token ID339
Feature activation-3.74e-01

Pos logit contributions
obar+0.213
 inadvert+0.210
20439+0.206
esty+0.199
 accidental+0.198
Neg logit contributions
Msg-0.235
aida-0.231
 Belg-0.221
jac-0.217
hess-0.215
Token story
Token ID1621
Feature activation-8.49e-01

Pos logit contributions
obar+0.360
20439+0.350
 inadvert+0.348
esty+0.332
 XY+0.328
Neg logit contributions
Msg-0.490
aida-0.480
 Belg-0.468
jac-0.456
hess-0.450
Token<|endoftext|>
Token ID50256
Feature activation+2.50e-01

Pos logit contributions
Msg+0.658
aida+0.643
 Belg+0.627
jac+0.610
hess+0.602
Neg logit contributions
obar-0.508
20439-0.495
 inadvert-0.491
esty-0.468
 XY-0.462
TokenGoogle
Token ID11708
Feature activation+2.90e+00

Pos logit contributions
obar+0.169
20439+0.166
 inadvert+0.163
esty+0.157
 XY+0.155
Neg logit contributions
Msg-0.173
aida-0.170
 Belg-0.166
jac-0.159
hess-0.158
Token has
Token ID468
Feature activation+7.47e-02

Pos logit contributions
obar+1.751
 inadvert+1.724
20439+1.690
esty+1.630
 Sear+1.620
Neg logit contributions
Msg-2.186
aida-2.156
 Belg-2.073
jac-2.051
hess-2.002
Token finally
Token ID3443
Feature activation+4.44e-01

Pos logit contributions
obar+0.048
 inadvert+0.047
20439+0.047
esty+0.044
 XY+0.044
Neg logit contributions
Msg-0.055
aida-0.054
 Belg-0.052
jac-0.051
hess-0.050
Token signed
Token ID4488
Feature activation-5.43e+00

Pos logit contributions
obar+0.274
20439+0.267
 inadvert+0.266
esty+0.253
 XY+0.250
Neg logit contributions
Msg-0.336
aida-0.328
 Belg-0.320
jac-0.311
hess-0.307
Token a
Token ID257
Feature activation-1.07e+00

Pos logit contributions
Msg+3.679
aida+3.543
 Belg+3.515
jac+3.331
hess+3.310
Neg logit contributions
obar-3.693
20439-3.636
 inadvert-3.547
esty-3.419
 XY-3.377
Token deal
Token ID1730
Feature activation-2.05e+00

Pos logit contributions
Msg+0.725
aida+0.708
 Belg+0.684
jac+0.665
hess+0.656
Neg logit contributions
obar-0.750
20439-0.736
 inadvert-0.734
esty-0.701
 XY-0.694
Token to
Token ID284
Feature activation-6.62e-01

Pos logit contributions
Msg+1.309
aida+1.276
 Belg+1.235
jac+1.195
hess+1.175
Neg logit contributions
obar-1.502
20439-1.473
 inadvert-1.464
esty-1.407
 XY-1.392
Token purchase
Token ID5001
Feature activation-3.80e+00

Pos logit contributions
Msg+0.495
aida+0.483
 Belg+0.471
jac+0.457
hess+0.452
Neg logit contributions
obar-0.415
20439-0.405
 inadvert-0.401
esty-0.384
 XY-0.378
Token live
Token ID2107
Feature activation+6.84e-01

Pos logit contributions
Msg+2.852
aida+2.788
 Belg+2.778
jac+2.616
hess+2.592
Neg logit contributions
obar-2.323
20439-2.306
 inadvert-2.237
esty-2.162
 um-2.074
TokenToday
Token ID8888
Feature activation-1.16e-01

Pos logit contributions
Msg+0.435
aida+0.425
 Belg+0.413
jac+0.401
hess+0.395
Neg logit contributions
obar-0.398
20439-0.390
 inadvert-0.386
esty-0.370
 XY-0.365
Token,
Token ID11
Feature activation+1.29e-01

Pos logit contributions
Msg+0.090
aida+0.088
 Belg+0.085
jac+0.083
hess+0.082
Neg logit contributions
obar-0.070
20439-0.068
 inadvert-0.068
esty-0.064
 XY-0.064
Token there
Token ID612
Feature activation-2.23e-01

Pos logit contributions
obar+0.084
 inadvert+0.081
20439+0.081
esty+0.077
 XY+0.077
Neg logit contributions
Msg-0.093
aida-0.091
 Belg-0.089
jac-0.086
hess-0.085
Token is
Token ID318
Feature activation+4.93e-01

Pos logit contributions
Msg+0.188
aida+0.184
 Belg+0.180
jac+0.175
hess+0.173
Neg logit contributions
obar-0.118
20439-0.115
 inadvert-0.114
esty-0.108
 XY-0.106
Token little
Token ID1310
Feature activation+4.35e-02

Pos logit contributions
obar+0.323
 inadvert+0.316
20439+0.310
esty+0.298
 um+0.298
Neg logit contributions
Msg-0.355
aida-0.345
 Belg-0.337
jac-0.325
hess-0.323
Token sign
Token ID1051
Feature activation-5.38e+00

Pos logit contributions
obar+0.027
 inadvert+0.027
20439+0.026
esty+0.025
 accidental+0.025
Neg logit contributions
Msg-0.032
aida-0.032
 Belg-0.031
jac-0.030
hess-0.030
Token of
Token ID286
Feature activation-7.50e-01

Pos logit contributions
Msg+3.937
aida+3.831
 Belg+3.710
jac+3.615
hess+3.577
Neg logit contributions
obar-3.375
20439-3.340
 inadvert-3.258
esty-3.129
 XY-3.095
Token basketball
Token ID9669
Feature activation-1.42e+00

Pos logit contributions
Msg+0.561
aida+0.548
 Belg+0.534
jac+0.519
hess+0.512
Neg logit contributions
obar-0.468
20439-0.458
 inadvert-0.453
esty-0.433
 XY-0.427
Token
Token ID447
Feature activation-3.32e-02

Pos logit contributions
Msg+1.066
aida+1.038
 Belg+1.013
jac+0.983
hess+0.976
Neg logit contributions
obar-0.887
20439-0.877
 inadvert-0.854
esty-0.823
 XY-0.809
Token
Token ID247
Feature activation-6.55e-02

Pos logit contributions
Msg+0.017
aida+0.016
 Belg+0.016
jac+0.015
hess+0.015
Neg logit contributions
obar-0.029
20439-0.028
 inadvert-0.028
esty-0.027
 XY-0.027
Tokens
Token ID82
Feature activation+3.19e-01

Pos logit contributions
Msg+0.041
aida+0.039
 Belg+0.038
jac+0.037
hess+0.036
Neg logit contributions
obar-0.049
20439-0.048
 inadvert-0.048
esty-0.046
 XY-0.046
Token[
Token ID58
Feature activation+3.83e-01

Pos logit contributions
Msg+0.093
aida+0.091
 Belg+0.089
jac+0.086
hess+0.085
Neg logit contributions
obar-0.066
20439-0.065
 inadvert-0.064
esty-0.061
 XY-0.060
Token8
Token ID23
Feature activation-3.06e-01

Pos logit contributions
obar+0.288
20439+0.282
 inadvert+0.280
esty+0.268
 XY+0.268
Neg logit contributions
Msg-0.235
aida-0.230
 Belg-0.224
jac-0.213
hess-0.213
Token]
Token ID60
Feature activation+2.78e-02

Pos logit contributions
Msg+0.235
aida+0.230
 Belg+0.224
jac+0.218
hess+0.215
Neg logit contributions
obar-0.185
20439-0.180
 inadvert-0.179
esty-0.171
 XY-0.168
Token Chevron
Token ID50083
Feature activation+1.08e+00

Pos logit contributions
obar+0.015
20439+0.015
 inadvert+0.014
esty+0.014
 XY+0.013
Neg logit contributions
Msg-0.023
aida-0.023
 Belg-0.022
jac-0.022
hess-0.021
Token eventually
Token ID4191
Feature activation-1.73e+00

Pos logit contributions
obar+0.645
20439+0.628
 inadvert+0.625
esty+0.595
 XY+0.587
Neg logit contributions
Msg-0.845
aida-0.824
 Belg-0.804
jac-0.783
hess-0.774
Token signed
Token ID4488
Feature activation-5.36e+00

Pos logit contributions
Msg+1.192
aida+1.172
 Belg+1.147
jac+1.096
hess+1.075
Neg logit contributions
obar-1.168
20439-1.163
 inadvert-1.119
esty-1.081
 XY-1.066
Token the
Token ID262
Feature activation-1.05e+00

Pos logit contributions
Msg+3.468
aida+3.365
 Belg+3.325
jac+3.164
hess+3.105
Neg logit contributions
obar-3.774
20439-3.701
 inadvert-3.630
esty-3.499
 XY-3.465
Token agreement
Token ID4381
Feature activation-2.08e+00

Pos logit contributions
Msg+0.698
aida+0.679
 Belg+0.658
jac+0.639
hess+0.631
Neg logit contributions
obar-0.740
20439-0.725
 inadvert-0.722
esty-0.691
 XY-0.684
Token in
Token ID287
Feature activation-9.29e-01

Pos logit contributions
Msg+1.464
aida+1.425
 Belg+1.393
jac+1.346
hess+1.329
Neg logit contributions
obar-1.384
20439-1.356
 inadvert-1.337
esty-1.285
 XY-1.267
Token 2008
Token ID3648
Feature activation-1.16e+00

Pos logit contributions
Msg+0.742
aida+0.726
 Belg+0.708
jac+0.689
hess+0.681
Neg logit contributions
obar-0.534
20439-0.520
 inadvert-0.516
esty-0.490
 XY-0.484
Token,
Token ID11
Feature activation-6.36e-01

Pos logit contributions
Msg+0.895
aida+0.875
 Belg+0.853
jac+0.829
hess+0.819
Neg logit contributions
obar-0.696
20439-0.680
 inadvert-0.674
esty-0.642
 XY-0.633
Token developer
Token ID8517
Feature activation-1.36e+00

Pos logit contributions
Msg+0.726
aida+0.710
 Belg+0.693
jac+0.674
hess+0.666
Neg logit contributions
obar-0.523
20439-0.510
 inadvert-0.505
esty-0.480
 XY-0.473
Token Nerd
Token ID44031
Feature activation-2.01e-01

Pos logit contributions
Msg+0.984
aida+0.959
 Belg+0.933
jac+0.906
hess+0.894
Neg logit contributions
obar-0.891
20439-0.871
 inadvert-0.864
esty-0.827
 XY-0.817
Token Kingdom
Token ID7526
Feature activation-8.96e-01

Pos logit contributions
Msg+0.120
aida+0.115
 Belg+0.111
jac+0.107
hess+0.106
Neg logit contributions
obar-0.157
 inadvert-0.152
20439-0.152
esty-0.148
 XY-0.146
Token last
Token ID938
Feature activation+3.20e-01

Pos logit contributions
Msg+0.709
aida+0.693
 Belg+0.676
jac+0.657
hess+0.650
Neg logit contributions
obar-0.523
20439-0.510
 inadvert-0.505
esty-0.481
 XY-0.473
Token week
Token ID1285
Feature activation-6.28e-01

Pos logit contributions
obar+0.205
 inadvert+0.200
20439+0.200
esty+0.191
 XY+0.189
Neg logit contributions
Msg-0.233
aida-0.228
 Belg-0.221
jac-0.216
hess-0.214
Token signed
Token ID4488
Feature activation-5.34e+00

Pos logit contributions
Msg+0.441
aida+0.430
 Belg+0.419
jac+0.406
hess+0.400
Neg logit contributions
obar-0.421
20439-0.412
 inadvert-0.408
esty-0.391
 XY-0.386
Token an
Token ID281
Feature activation-1.91e+00

Pos logit contributions
Msg+3.478
aida+3.335
 Belg+3.283
jac+3.119
hess+3.105
Neg logit contributions
obar-3.787
20439-3.701
 inadvert-3.616
esty-3.506
 XY-3.465
Token agreement
Token ID4381
Feature activation-2.47e+00

Pos logit contributions
Msg+1.223
aida+1.192
 Belg+1.159
jac+1.114
hess+1.103
Neg logit contributions
obar-1.396
20439-1.370
 inadvert-1.348
esty-1.305
 XY-1.285
Token to
Token ID284
Feature activation-1.01e+00

Pos logit contributions
Msg+1.691
aida+1.649
 Belg+1.601
jac+1.551
hess+1.529
Neg logit contributions
obar-1.707
20439-1.671
 inadvert-1.659
esty-1.591
 XY-1.573
Token become
Token ID1716
Feature activation+2.06e-02

Pos logit contributions
Msg+0.794
aida+0.777
 Belg+0.755
jac+0.738
hess+0.729
Neg logit contributions
obar-0.595
 inadvert-0.579
20439-0.577
esty-0.547
 XY-0.543
Token partners
Token ID4887
Feature activation-8.07e-01

Pos logit contributions
obar+0.013
 inadvert+0.013
20439+0.013
esty+0.012
 XY+0.012
Neg logit contributions
Msg-0.015
aida-0.015
 Belg-0.015
jac-0.014
hess-0.014
Token advertisement
Token ID15422
Feature activation+2.18e-01

Pos logit contributions
Msg+0.630
aida+0.609
 Belg+0.588
jac+0.561
hess+0.548
Neg logit contributions
obar-1.008
20439-0.995
 inadvert-0.982
esty-0.953
 XY-0.941
Token
Token ID198
Feature activation+3.61e-01

Pos logit contributions
obar+0.104
20439+0.101
 inadvert+0.099
esty+0.093
 XY+0.092
Neg logit contributions
Msg-0.196
aida-0.192
 Belg-0.188
jac-0.184
hess-0.182
Token
Token ID198
Feature activation+4.31e-01

Pos logit contributions
obar+0.173
20439+0.168
 inadvert+0.166
esty+0.156
 XY+0.153
Neg logit contributions
Msg-0.323
aida-0.317
 Belg-0.310
jac-0.303
hess-0.300
Token"
Token ID1
Feature activation-3.24e-01

Pos logit contributions
obar+0.293
20439+0.288
 inadvert+0.283
esty+0.272
 XY+0.269
Neg logit contributions
Msg-0.296
aida-0.290
 Belg-0.285
jac-0.272
hess-0.271
TokenInterestingly
Token ID33092
Feature activation-5.46e-01

Pos logit contributions
Msg+0.216
aida+0.210
 Belg+0.204
jac+0.197
hess+0.194
Neg logit contributions
obar-0.229
20439-0.224
 inadvert-0.223
esty-0.214
 XY-0.211
Token enough
Token ID1576
Feature activation-5.33e+00

Pos logit contributions
Msg+0.400
aida+0.391
 Belg+0.379
jac+0.369
hess+0.364
Neg logit contributions
obar-0.350
20439-0.341
 inadvert-0.341
esty-0.326
 XY-0.322
Token,
Token ID11
Feature activation-5.99e-01

Pos logit contributions
Msg+3.799
aida+3.698
 Belg+3.657
jac+3.475
hess+3.447
Neg logit contributions
obar-3.486
20439-3.437
 inadvert-3.315
esty-3.190
 XY-3.110
Token [
Token ID685
Feature activation+2.40e-01

Pos logit contributions
Msg+0.432
aida+0.422
 Belg+0.409
jac+0.399
hess+0.393
Neg logit contributions
obar-0.391
 inadvert-0.381
20439-0.380
esty-0.363
 XY-0.360
TokenTuesday
Token ID26133
Feature activation-1.32e+00

Pos logit contributions
obar+0.174
20439+0.170
 inadvert+0.169
esty+0.163
 XY+0.160
Neg logit contributions
Msg-0.155
aida-0.151
 Belg-0.148
jac-0.141
hess-0.140
Token],
Token ID4357
Feature activation-7.63e-02

Pos logit contributions
Msg+1.008
aida+0.983
 Belg+0.960
jac+0.932
hess+0.921
Neg logit contributions
obar-0.799
20439-0.780
 inadvert-0.774
esty-0.738
 XY-0.728
Token Mor
Token ID3461
Feature activation-3.64e-01

Pos logit contributions
Msg+0.055
aida+0.054
 Belg+0.052
jac+0.051
hess+0.050
Neg logit contributions
obar-0.050
 inadvert-0.049
20439-0.048
esty-0.046
 XY-0.046
Tokenal
Token ID282
Feature activation-1.29e-01

Pos logit contributions
obar+0.307
20439+0.298
 inadvert+0.295
esty+0.279
 XY+0.274
Neg logit contributions
Msg-0.508
aida-0.498
 Belg-0.487
jac-0.475
hess-0.469
Token maps
Token ID8739
Feature activation+1.46e+00

Pos logit contributions
Msg+0.085
aida+0.082
 Belg+0.080
jac+0.077
hess+0.076
Neg logit contributions
obar-0.092
20439-0.090
 inadvert-0.090
esty-0.086
 XY-0.085
Token like
Token ID588
Feature activation+6.78e-01

Pos logit contributions
obar+0.786
 inadvert+0.769
20439+0.754
esty+0.723
 XY+0.718
Neg logit contributions
Msg-1.215
aida-1.188
 Belg-1.162
jac-1.130
hess-1.121
Token
Token ID564
Feature activation+4.90e-01

Pos logit contributions
obar+0.449
20439+0.438
 inadvert+0.437
esty+0.418
 XY+0.414
Neg logit contributions
Msg-0.481
aida-0.470
 Belg-0.456
jac-0.443
hess-0.438
Token
Token ID250
Feature activation+6.46e-01

Pos logit contributions
obar+0.397
20439+0.389
 inadvert+0.387
esty+0.375
 XY+0.371
Neg logit contributions
Msg-0.275
aida-0.266
 Belg-0.260
jac-0.248
hess-0.244
Tokensign
Token ID12683
Feature activation-5.32e+00

Pos logit contributions
obar+0.432
20439+0.423
 inadvert+0.418
esty+0.401
 XY+0.396
Neg logit contributions
Msg-0.455
aida-0.444
 Belg-0.432
jac-0.418
hess-0.413
Tokenature
Token ID1300
Feature activation-9.67e-01

Pos logit contributions
Msg+4.357
aida+4.253
 Belg+4.062
jac+4.028
hess+3.966
Neg logit contributions
20439-2.841
obar-2.798
 inadvert-2.748
 XY-2.545
 accidental-2.542
Token food
Token ID2057
Feature activation-3.54e-01

Pos logit contributions
Msg+0.718
aida+0.701
 Belg+0.683
jac+0.663
hess+0.655
Neg logit contributions
obar-0.610
20439-0.596
 inadvert-0.591
esty-0.564
 XY-0.557
Token from
Token ID422
Feature activation-3.23e-03

Pos logit contributions
Msg+0.291
aida+0.285
 Belg+0.278
jac+0.271
hess+0.268
Neg logit contributions
obar-0.195
20439-0.190
 inadvert-0.188
esty-0.179
 XY-0.176
Token each
Token ID1123
Feature activation-1.03e+00

Pos logit contributions
Msg+0.002
aida+0.002
 Belg+0.002
jac+0.002
hess+0.002
Neg logit contributions
obar-0.002
20439-0.002
 inadvert-0.002
esty-0.002
 XY-0.002
Token state
Token ID1181
Feature activation+2.29e-02

Pos logit contributions
Msg+0.738
aida+0.722
 Belg+0.702
jac+0.680
hess+0.670
Neg logit contributions
obar-0.679
20439-0.668
 inadvert-0.657
esty-0.631
 XY-0.619
TokenHowever
Token ID4864
Feature activation-7.34e-01

Pos logit contributions
Msg+0.101
aida+0.099
 Belg+0.096
jac+0.093
hess+0.092
Neg logit contributions
obar-0.099
20439-0.096
 inadvert-0.096
esty-0.092
 XY-0.091
Token,
Token ID11
Feature activation-5.39e-01

Pos logit contributions
Msg+0.570
aida+0.557
 Belg+0.543
jac+0.529
hess+0.522
Neg logit contributions
obar-0.438
20439-0.426
 inadvert-0.426
esty-0.404
 XY-0.399
Token this
Token ID428
Feature activation-8.50e-02

Pos logit contributions
Msg+0.391
aida+0.382
 Belg+0.372
jac+0.360
hess+0.356
Neg logit contributions
obar-0.349
20439-0.342
 inadvert-0.339
esty-0.324
 XY-0.320
Token is
Token ID318
Feature activation+3.85e-01

Pos logit contributions
Msg+0.066
aida+0.064
 Belg+0.063
jac+0.061
hess+0.060
Neg logit contributions
obar-0.051
20439-0.050
 inadvert-0.049
esty-0.047
 XY-0.046
Token barely
Token ID8523
Feature activation-1.23e+00

Pos logit contributions
obar+0.249
 inadvert+0.245
20439+0.239
 accidental+0.230
esty+0.230
Neg logit contributions
Msg-0.281
aida-0.275
 Belg-0.265
jac-0.261
hess-0.257
Token enough
Token ID1576
Feature activation-5.31e+00

Pos logit contributions
Msg+0.894
aida+0.872
 Belg+0.852
jac+0.821
hess+0.816
Neg logit contributions
obar-0.796
20439-0.782
 inadvert-0.767
esty-0.739
 XY-0.729
Token for
Token ID329
Feature activation-6.38e-01

Pos logit contributions
Msg+3.511
aida+3.400
 Belg+3.327
hess+3.180
jac+3.145
Neg logit contributions
20439-3.685
obar-3.681
 inadvert-3.507
esty-3.454
 XY-3.370
Token any
Token ID597
Feature activation+2.04e-01

Pos logit contributions
Msg+0.471
aida+0.460
 Belg+0.448
jac+0.434
hess+0.428
Neg logit contributions
obar-0.405
20439-0.397
 inadvert-0.392
esty-0.376
 XY-0.370
Token realistic
Token ID12653
Feature activation+1.21e+00

Pos logit contributions
obar+0.122
 inadvert+0.119
20439+0.119
esty+0.113
 XY+0.111
Neg logit contributions
Msg-0.158
aida-0.154
 Belg-0.151
jac-0.147
hess-0.145
Token optimism
Token ID24323
Feature activation-3.02e-01

Pos logit contributions
obar+0.780
20439+0.761
 inadvert+0.760
esty+0.723
 XY+0.717
Neg logit contributions
Msg-0.874
aida-0.850
 Belg-0.828
jac-0.806
hess-0.794
Token.
Token ID13
Feature activation-5.26e-01

Pos logit contributions
Msg+0.228
aida+0.222
 Belg+0.217
jac+0.211
hess+0.208
Neg logit contributions
obar-0.186
20439-0.182
 inadvert-0.180
esty-0.172
 XY-0.170
Token 6
Token ID718
Feature activation-4.93e-01

Pos logit contributions
Msg+1.016
aida+0.987
 Belg+0.968
jac+0.930
hess+0.917
Neg logit contributions
obar-1.049
20439-1.028
 inadvert-1.019
esty-0.979
 accidental-0.957
Token,
Token ID11
Feature activation-9.75e-01

Pos logit contributions
Msg+0.378
aida+0.368
 Belg+0.361
jac+0.348
hess+0.343
Neg logit contributions
obar-0.303
20439-0.294
 inadvert-0.293
esty-0.280
 um-0.276
Token O
Token ID440
Feature activation-7.91e-01

Pos logit contributions
Msg+0.729
aida+0.708
 Belg+0.689
jac+0.671
hess+0.661
Neg logit contributions
obar-0.615
 inadvert-0.598
20439-0.596
esty-0.571
 XY-0.565
Tokenka
Token ID4914
Feature activation-9.05e-01

Pos logit contributions
Msg+0.311
aida+0.294
 Belg+0.285
jac+0.263
hess+0.259
Neg logit contributions
obar-0.777
20439-0.760
 inadvert-0.757
esty-0.739
 XY-0.731
Tokenfor
Token ID1640
Feature activation-7.97e-01

Pos logit contributions
Msg+0.586
aida+0.571
 Belg+0.552
jac+0.536
hess+0.527
Neg logit contributions
obar-0.655
20439-0.644
 inadvert-0.639
esty-0.613
 XY-0.607
Token signed
Token ID4488
Feature activation-5.31e+00

Pos logit contributions
Msg+0.576
aida+0.562
 Belg+0.547
jac+0.530
hess+0.525
Neg logit contributions
obar-0.520
 inadvert-0.506
20439-0.502
esty-0.483
 XY-0.477
Token a
Token ID257
Feature activation-1.07e+00

Pos logit contributions
Msg+3.218
aida+3.141
 Belg+3.075
jac+2.931
hess+2.899
Neg logit contributions
20439-3.939
obar-3.938
 inadvert-3.809
esty-3.683
 XY-3.639
Token two
Token ID734
Feature activation+3.69e-01

Pos logit contributions
Msg+0.770
aida+0.751
 Belg+0.727
jac+0.708
hess+0.698
Neg logit contributions
obar-0.699
20439-0.682
 inadvert-0.682
esty-0.651
 XY-0.642
Token-
Token ID12
Feature activation-6.03e-02

Pos logit contributions
obar+0.249
 inadvert+0.245
20439+0.242
esty+0.234
 mm+0.232
Neg logit contributions
Msg-0.256
aida-0.251
 Belg-0.243
jac-0.237
hess-0.234
Tokenyear
Token ID1941
Feature activation+4.65e-01

Pos logit contributions
Msg+0.044
aida+0.043
 Belg+0.042
jac+0.041
hess+0.040
Neg logit contributions
obar-0.038
20439-0.038
 inadvert-0.037
esty-0.036
 XY-0.035
Token contract
Token ID2775
Feature activation-1.65e+00

Pos logit contributions
obar+0.281
 inadvert+0.276
20439+0.273
esty+0.261
 um+0.259
Neg logit contributions
Msg-0.357
aida-0.348
 Belg-0.334
jac-0.331
hess-0.327
Token her
Token ID607
Feature activation-6.06e-01

Pos logit contributions
obar+0.428
 inadvert+0.417
20439+0.411
esty+0.397
 um+0.394
Neg logit contributions
Msg-0.459
aida-0.445
 Belg-0.430
jac-0.424
hess-0.416
Token bike
Token ID7161
Feature activation+7.36e-01

Pos logit contributions
Msg+0.433
aida+0.422
 Belg+0.410
jac+0.398
hess+0.393
Neg logit contributions
obar-0.400
20439-0.391
 inadvert-0.389
esty-0.371
 XY-0.368
Token through
Token ID832
Feature activation+1.18e+00

Pos logit contributions
obar+0.511
 inadvert+0.501
20439+0.492
esty+0.478
 XY+0.474
Neg logit contributions
Msg-0.500
aida-0.487
 Belg-0.470
jac-0.458
hess-0.452
Token the
Token ID262
Feature activation-5.27e-01

Pos logit contributions
obar+0.752
 inadvert+0.738
20439+0.717
esty+0.706
 accidental+0.702
Neg logit contributions
Msg-0.864
aida-0.839
 Belg-0.799
jac-0.797
hess-0.791
Token stop
Token ID2245
Feature activation+2.96e+00

Pos logit contributions
Msg+0.383
aida+0.373
 Belg+0.360
jac+0.354
hess+0.350
Neg logit contributions
obar-0.340
 inadvert-0.333
20439-0.330
esty-0.317
 um-0.315
Token sign
Token ID1051
Feature activation-5.30e+00

Pos logit contributions
obar+2.258
 inadvert+2.197
esty+2.144
20439+2.116
 um+2.112
Neg logit contributions
Msg-1.768
aida-1.721
 Belg-1.679
jac-1.636
hess-1.603
Token and
Token ID290
Feature activation-7.06e-01

Pos logit contributions
Msg+3.844
aida+3.731
 Belg+3.665
jac+3.508
hess+3.499
Neg logit contributions
20439-3.402
obar-3.356
 inadvert-3.176
esty-3.064
 XY-3.024
Token collided
Token ID43449
Feature activation-8.50e-01

Pos logit contributions
Msg+0.517
aida+0.504
 Belg+0.486
jac+0.477
hess+0.471
Neg logit contributions
obar-0.454
 inadvert-0.447
20439-0.437
esty-0.422
 um-0.420
Token with
Token ID351
Feature activation-9.46e-01

Pos logit contributions
Msg+0.543
aida+0.530
 Belg+0.509
jac+0.499
hess+0.491
Neg logit contributions
obar-0.627
 inadvert-0.616
20439-0.602
esty-0.586
 um-0.583
Token a
Token ID257
Feature activation-1.45e-01

Pos logit contributions
Msg+0.680
aida+0.664
 Belg+0.641
jac+0.624
hess+0.622
Neg logit contributions
obar-0.622
 inadvert-0.604
20439-0.602
esty-0.579
 XY-0.573
Token patrol
Token ID13969
Feature activation-3.98e-01

Pos logit contributions
Msg+0.098
aida+0.096
 Belg+0.092
jac+0.090
hess+0.089
Neg logit contributions
obar-0.101
 inadvert-0.098
20439-0.098
esty-0.095
 XY-0.094
Token you
Token ID345
Feature activation+7.18e-01

Pos logit contributions
obar+0.146
20439+0.142
 inadvert+0.142
esty+0.136
 XY+0.135
Neg logit contributions
Msg-0.147
aida-0.143
 Belg-0.138
jac-0.134
hess-0.133
Token get
Token ID651
Feature activation+1.88e+00

Pos logit contributions
obar+0.406
20439+0.394
 inadvert+0.392
esty+0.372
 XY+0.367
Neg logit contributions
Msg-0.580
aida-0.568
 Belg-0.553
jac-0.540
hess-0.534
Token from
Token ID422
Feature activation-3.52e-01

Pos logit contributions
obar+1.183
 inadvert+1.140
20439+1.136
esty+1.082
 XY+1.077
Neg logit contributions
Msg-1.404
aida-1.370
 Belg-1.325
jac-1.296
hess-1.281
Token this
Token ID428
Feature activation+8.93e-01

Pos logit contributions
Msg+0.251
aida+0.244
 Belg+0.238
jac+0.231
hess+0.228
Neg logit contributions
obar-0.234
20439-0.228
 inadvert-0.227
esty-0.217
 XY-0.214
Token sub
Token ID850
Feature activation+2.78e+00

Pos logit contributions
obar+0.531
 inadvert+0.515
20439+0.511
esty+0.487
 XY+0.486
Neg logit contributions
Msg-0.700
aida-0.682
 Belg-0.661
jac-0.646
hess-0.640
Tokenwo
Token ID21638
Feature activation+2.42e+00

Pos logit contributions
obar+1.676
 inadvert+1.604
20439+1.585
esty+1.534
 mm+1.516
Neg logit contributions
Msg-2.160
aida-2.094
 Belg-2.044
jac-1.985
hess-1.971
Tokenofer
Token ID30288
Feature activation+2.03e+00

Pos logit contributions
obar+1.035
 inadvert+0.952
20439+0.937
esty+0.906
 XY+0.875
Neg logit contributions
Msg-2.328
aida-2.255
 Belg-2.239
jac-2.170
hess-2.146
Token.
Token ID13
Feature activation+3.38e-01

Pos logit contributions
obar+1.137
 inadvert+1.089
20439+1.081
esty+1.032
 XY+1.031
Neg logit contributions
Msg-1.653
aida-1.622
 Belg-1.571
jac-1.536
hess-1.522
Token I
Token ID314
Feature activation+8.23e-01

Pos logit contributions
obar+0.202
20439+0.196
 inadvert+0.195
esty+0.186
 XY+0.184
Neg logit contributions
Msg-0.263
aida-0.257
 Belg-0.250
jac-0.244
hess-0.241
Token have
Token ID423
Feature activation+2.98e-01

Pos logit contributions
obar+0.465
20439+0.452
 inadvert+0.449
esty+0.426
 XY+0.420
Neg logit contributions
Msg-0.666
aida-0.651
 Belg-0.636
jac-0.619
hess-0.612
Token this
Token ID428
Feature activation+3.51e-01

Pos logit contributions
obar+0.188
 inadvert+0.183
20439+0.182
esty+0.174
 XY+0.173
Neg logit contributions
Msg-0.221
aida-0.217
 Belg-0.209
jac-0.204
hess-0.201
Token machine
Token ID4572
Feature activation+1.66e-01

Pos logit contributions
Msg+0.573
aida+0.559
 Belg+0.545
jac+0.529
hess+0.522
Neg logit contributions
obar-0.488
20439-0.477
 inadvert-0.472
esty-0.451
 XY-0.445
Token can
Token ID460
Feature activation+3.79e-02

Pos logit contributions
obar+0.098
20439+0.096
 inadvert+0.095
esty+0.091
 XY+0.089
Neg logit contributions
Msg-0.130
aida-0.127
 Belg-0.124
jac-0.120
hess-0.119
Token,
Token ID11
Feature activation+3.98e-01

Pos logit contributions
obar+0.022
20439+0.021
 inadvert+0.021
esty+0.020
 XY+0.020
Neg logit contributions
Msg-0.030
aida-0.029
 Belg-0.029
jac-0.028
hess-0.028
Token despite
Token ID3805
Feature activation-3.98e-01

Pos logit contributions
obar+0.233
20439+0.227
 inadvert+0.225
esty+0.214
 XY+0.212
Neg logit contributions
Msg-0.313
aida-0.306
 Belg-0.299
jac-0.290
hess-0.287
Token software
Token ID3788
Feature activation-1.58e+00

Pos logit contributions
Msg+0.290
aida+0.284
 Belg+0.275
jac+0.268
hess+0.264
Neg logit contributions
obar-0.257
 inadvert-0.251
20439-0.249
esty-0.238
 XY-0.237
Token virtual
Token ID7166
Feature activation+3.47e+00

Pos logit contributions
Msg+1.179
aida+1.145
 Belg+1.122
jac+1.086
hess+1.076
Neg logit contributions
obar-0.992
20439-0.981
 inadvert-0.951
esty-0.916
 XY-0.896
Tokenization
Token ID1634
Feature activation+4.25e-01

Pos logit contributions
obar+1.147
 inadvert+1.082
20439+1.028
esty+1.007
 mm+0.968
Neg logit contributions
Msg-3.576
aida-3.524
 Belg-3.463
jac-3.375
hess-3.358
Token.
Token ID13
Feature activation-1.44e-02

Pos logit contributions
obar+0.258
 inadvert+0.253
20439+0.250
esty+0.239
 XY+0.238
Neg logit contributions
Msg-0.325
aida-0.318
 Belg-0.308
jac-0.301
hess-0.297
Token
Token ID198
Feature activation-1.93e-01

Pos logit contributions
Msg+0.012
aida+0.012
 Belg+0.011
jac+0.011
hess+0.011
Neg logit contributions
obar-0.008
20439-0.008
 inadvert-0.008
esty-0.007
 XY-0.007
Token
Token ID198
Feature activation+1.25e-01

Pos logit contributions
Msg+0.170
aida+0.166
 Belg+0.162
jac+0.158
hess+0.156
Neg logit contributions
obar-0.096
20439-0.094
 inadvert-0.093
esty-0.087
 accidental-0.085
Token4
Token ID19
Feature activation-4.86e-02

Pos logit contributions
obar+0.086
20439+0.084
 inadvert+0.083
esty+0.080
 XY+0.079
Neg logit contributions
Msg-0.085
aida-0.083
 Belg-0.081
jac-0.078
hess-0.077
Tokenuse
Token ID1904
Feature activation-1.25e+00

Pos logit contributions
Msg+0.146
aida+0.140
 Belg+0.138
jac+0.137
archs+0.131
Neg logit contributions
obar-0.164
20439-0.163
 inadvert-0.157
esty-0.152
 XY-0.150
Token.
Token ID13
Feature activation+5.14e-01

Pos logit contributions
Msg+0.877
aida+0.843
 Belg+0.812
 Fraz+0.781
jac+0.774
Neg logit contributions
obar-0.872
20439-0.870
 inadvert-0.794
esty-0.784
 Sear-0.760
Token Here
Token ID3423
Feature activation-1.74e-01

Pos logit contributions
obar+0.408
20439+0.402
 inadvert+0.396
esty+0.388
 accidental+0.373
Neg logit contributions
Msg-0.305
aida-0.290
 Belg-0.286
jac-0.267
hess-0.266
Token is
Token ID318
Feature activation+7.59e-01

Pos logit contributions
Msg+0.132
aida+0.129
 Belg+0.125
jac+0.121
hess+0.120
Neg logit contributions
20439-0.107
obar-0.107
 inadvert-0.103
esty-0.099
 XY-0.096
Token the
Token ID262
Feature activation+3.67e-01

Pos logit contributions
obar+0.501
20439+0.491
 inadvert+0.486
esty+0.465
 XY+0.459
Neg logit contributions
Msg-0.541
aida-0.527
 Belg-0.513
jac-0.498
hess-0.490
Token link
Token ID2792
Feature activation+2.43e+00

Pos logit contributions
obar+0.185
20439+0.179
 inadvert+0.179
esty+0.168
 XY+0.165
Neg logit contributions
Msg-0.318
aida-0.312
 Belg-0.305
jac-0.297
hess-0.295
Token for
Token ID329
Feature activation+1.70e-03

Pos logit contributions
obar+1.339
20439+1.279
 inadvert+1.275
esty+1.203
 um+1.197
Neg logit contributions
Msg-2.009
aida-1.970
 Belg-1.916
jac-1.876
hess-1.843
Token buying
Token ID7067
Feature activation-1.30e+00

Pos logit contributions
obar+0.001
 inadvert+0.001
20439+0.001
 um+0.001
 XY+0.001
Neg logit contributions
Msg-0.001
aida-0.001
 Belg-0.001
jac-0.001
hess-0.001
Token the
Token ID262
Feature activation+1.20e-01

Pos logit contributions
Msg+0.876
aida+0.858
 Belg+0.837
jac+0.806
hess+0.797
Neg logit contributions
obar-0.890
20439-0.881
 inadvert-0.863
esty-0.840
 mm-0.811
Token second
Token ID1218
Feature activation+3.82e-01

Pos logit contributions
obar+0.069
20439+0.068
 inadvert+0.066
esty+0.063
 XY+0.061
Neg logit contributions
Msg-0.095
aida-0.094
 Belg-0.091
jac-0.088
hess-0.087
Token edition
Token ID8313
Feature activation+3.75e-01

Pos logit contributions
obar+0.269
 inadvert+0.268
20439+0.264
 accidental+0.257
 XY+0.256
Neg logit contributions
Msg-0.254
aida-0.243
 Belg-0.237
jac-0.231
hess-0.225
Token most
Token ID749
Feature activation-2.68e-01

Pos logit contributions
obar+0.058
 inadvert+0.057
20439+0.057
esty+0.054
 accidental+0.054
Neg logit contributions
Msg-0.059
aida-0.057
 Belg-0.056
jac-0.054
hess-0.054
Token damning
Token ID36706
Feature activation-1.49e-01

Pos logit contributions
Msg+0.217
aida+0.212
 Belg+0.207
jac+0.202
hess+0.199
Neg logit contributions
obar-0.152
20439-0.147
 inadvert-0.147
esty-0.139
 XY-0.137
Token of
Token ID286
Feature activation+5.49e-01

Pos logit contributions
Msg+0.108
aida+0.106
 Belg+0.103
jac+0.100
hess+0.099
Neg logit contributions
obar-0.095
20439-0.093
 inadvert-0.093
esty-0.089
 XY-0.088
Token which
Token ID543
Feature activation-1.60e+00

Pos logit contributions
obar+0.351
20439+0.344
 inadvert+0.342
esty+0.326
 XY+0.322
Neg logit contributions
Msg-0.401
aida-0.393
 Belg-0.381
jac-0.372
hess-0.367
Token was
Token ID373
Feature activation+4.95e-01

Pos logit contributions
Msg+1.208
aida+1.179
 Belg+1.153
jac+1.113
hess+1.101
Neg logit contributions
obar-0.987
20439-0.965
 inadvert-0.948
esty-0.907
 XY-0.894
Token arguably
Token ID15242
Feature activation+2.47e+00

Pos logit contributions
obar+0.324
 inadvert+0.319
20439+0.315
esty+0.301
 accidental+0.301
Neg logit contributions
Msg-0.355
aida-0.350
 Belg-0.335
jac-0.329
hess-0.326
Token an
Token ID281
Feature activation-6.35e-01

Pos logit contributions
obar+1.582
 inadvert+1.571
20439+1.532
 accidental+1.485
esty+1.466
Neg logit contributions
Msg-1.791
aida-1.757
 Belg-1.687
jac-1.663
hess-1.648
Token officer
Token ID3818
Feature activation+1.68e-01

Pos logit contributions
Msg+0.500
aida+0.490
 Belg+0.478
jac+0.464
hess+0.459
Neg logit contributions
obar-0.371
20439-0.362
 inadvert-0.356
esty-0.341
 XY-0.335
Token eating
Token ID6600
Feature activation+1.53e-01

Pos logit contributions
obar+0.107
 inadvert+0.105
20439+0.104
esty+0.099
 accidental+0.099
Neg logit contributions
Msg-0.124
aida-0.121
 Belg-0.118
jac-0.114
hess-0.113
Token what
Token ID644
Feature activation+1.76e-01

Pos logit contributions
obar+0.101
 inadvert+0.099
20439+0.096
 XY+0.093
 um+0.093
Neg logit contributions
Msg-0.110
aida-0.108
 Belg-0.104
jac-0.101
hess-0.101
Token appears
Token ID3568
Feature activation+1.79e+00

Pos logit contributions
obar+0.119
 inadvert+0.115
20439+0.114
esty+0.110
 XY+0.109
Neg logit contributions
Msg-0.124
aida-0.122
 Belg-0.118
jac-0.115
hess-0.113
Token-
Token ID12
Feature activation-5.43e-01

Pos logit contributions
obar+0.041
20439+0.040
 inadvert+0.040
esty+0.038
 XY+0.038
Neg logit contributions
Msg-0.045
aida-0.044
 Belg-0.042
jac-0.041
hess-0.041
Tokenwe
Token ID732
Feature activation+3.60e-01

Pos logit contributions
Msg+0.373
aida+0.363
 Belg+0.353
jac+0.342
hess+0.337
Neg logit contributions
obar-0.373
20439-0.365
 inadvert-0.362
esty-0.347
 XY-0.343
Tokenird
Token ID1447
Feature activation-3.89e-01

Pos logit contributions
obar+0.232
20439+0.227
 inadvert+0.225
esty+0.215
 XY+0.213
Neg logit contributions
Msg-0.262
aida-0.255
 Belg-0.249
jac-0.241
hess-0.238
Token black
Token ID2042
Feature activation-4.09e-01

Pos logit contributions
Msg+0.278
aida+0.271
 Belg+0.263
jac+0.256
hess+0.252
Neg logit contributions
obar-0.256
20439-0.250
 inadvert-0.249
esty-0.239
 XY-0.236
Token-
Token ID12
Feature activation+7.09e-01

Pos logit contributions
Msg+0.288
aida+0.282
 Belg+0.272
jac+0.264
hess+0.262
Neg logit contributions
obar-0.273
20439-0.267
 inadvert-0.265
esty-0.255
 XY-0.252
Tokenborder
Token ID20192
Feature activation+3.04e+00

Pos logit contributions
obar+0.499
20439+0.486
 inadvert+0.483
esty+0.467
 XY+0.460
Neg logit contributions
Msg-0.475
aida-0.461
 Belg-0.449
jac-0.431
hess-0.427
Token cards
Token ID4116
Feature activation+2.21e+00

Pos logit contributions
obar+2.062
 inadvert+2.039
20439+2.019
 XY+1.968
esty+1.964
Neg logit contributions
Msg-2.042
aida-2.015
 Belg-1.911
jac-1.876
hess-1.849
Token:
Token ID25
Feature activation+9.18e-01

Pos logit contributions
obar+1.360
 inadvert+1.314
20439+1.313
esty+1.261
 XY+1.256
Neg logit contributions
Msg-1.667
aida-1.629
 Belg-1.582
jac-1.536
hess-1.510
Token Block
Token ID9726
Feature activation+1.26e+00

Pos logit contributions
obar+0.524
20439+0.508
 inadvert+0.506
 XY+0.483
esty+0.483
Neg logit contributions
Msg-0.734
aida-0.721
 Belg-0.698
jac-0.681
hess-0.677
Tokenbuster
Token ID24899
Feature activation-4.70e-01

Pos logit contributions
obar+0.808
20439+0.787
 inadvert+0.780
esty+0.756
 XY+0.751
Neg logit contributions
Msg-0.924
aida-0.902
 Belg-0.878
jac-0.852
hess-0.841
Token is
Token ID318
Feature activation+1.96e-01

Pos logit contributions
Msg+0.370
aida+0.362
 Belg+0.353
jac+0.343
hess+0.340
Neg logit contributions
obar-0.274
20439-0.268
 inadvert-0.266
esty-0.253
 XY-0.250
Token
Token ID198
Feature activation+1.10e-01

Pos logit contributions
obar+0.048
20439+0.047
 inadvert+0.046
esty+0.044
 XY+0.043
Neg logit contributions
Msg-0.079
aida-0.078
 Belg-0.076
jac-0.074
hess-0.073
Token
Token ID198
Feature activation+3.68e-01

Pos logit contributions
obar+0.053
20439+0.052
 inadvert+0.051
esty+0.048
 XY+0.047
Neg logit contributions
Msg-0.097
aida-0.095
 Belg-0.093
jac-0.091
hess-0.090
TokenAt
Token ID2953
Feature activation+6.25e-01

Pos logit contributions
obar+0.253
20439+0.247
 inadvert+0.246
esty+0.236
 XY+0.233
Neg logit contributions
Msg-0.248
aida-0.245
 Belg-0.239
jac-0.228
hess-0.226
Tokenomic
Token ID10179
Feature activation+1.09e+00

Pos logit contributions
obar+0.259
20439+0.248
 inadvert+0.245
esty+0.229
 XY+0.224
Neg logit contributions
Msg-0.600
aida-0.590
 Belg-0.578
jac-0.565
hess-0.560
Token
Token ID198
Feature activation+5.03e-01

Pos logit contributions
obar+0.669
20439+0.653
 inadvert+0.649
esty+0.618
 XY+0.612
Neg logit contributions
Msg-0.825
aida-0.814
 Belg-0.790
jac-0.766
hess-0.754
Token
Token ID198
Feature activation+5.36e-01

Pos logit contributions
obar+0.238
20439+0.230
 inadvert+0.228
esty+0.214
 XY+0.212
Neg logit contributions
Msg-0.452
aida-0.444
 Belg-0.435
jac-0.424
hess-0.420
TokenThe
Token ID464
Feature activation+1.16e+00

Pos logit contributions
obar+0.362
20439+0.352
 inadvert+0.349
esty+0.335
 XY+0.332
Neg logit contributions
Msg-0.371
aida-0.365
 Belg-0.355
jac-0.342
hess-0.338
Token heart
Token ID2612
Feature activation+1.48e+00

Pos logit contributions
obar+0.660
20439+0.641
 inadvert+0.640
esty+0.606
 XY+0.602
Neg logit contributions
Msg-0.932
aida-0.913
 Belg-0.887
jac-0.867
hess-0.855
Token of
Token ID286
Feature activation+9.63e-01

Pos logit contributions
obar+0.784
20439+0.753
 inadvert+0.744
esty+0.723
 XY+0.707
Neg logit contributions
Msg-1.240
aida-1.216
 Belg-1.192
jac-1.165
hess-1.144
Token the
Token ID262
Feature activation-1.46e-01

Pos logit contributions
obar+0.611
 inadvert+0.596
20439+0.592
esty+0.567
 XY+0.564
Neg logit contributions
Msg-0.708
aida-0.696
 Belg-0.672
jac-0.653
hess-0.643
Token library
Token ID5888
Feature activation-9.45e-01

Pos logit contributions
Msg+0.111
aida+0.109
 Belg+0.106
jac+0.103
hess+0.102
Neg logit contributions
obar-0.089
20439-0.087
 inadvert-0.086
esty-0.082
 XY-0.081
Token by
Token ID416
Feature activation+7.69e-02

Pos logit contributions
obar+0.355
 inadvert+0.349
20439+0.340
 um+0.327
esty+0.326
Neg logit contributions
Msg-0.440
aida-0.431
 Belg-0.417
jac-0.409
hess-0.404
Token the
Token ID262
Feature activation-4.01e-01

Pos logit contributions
obar+0.049
20439+0.048
 inadvert+0.047
esty+0.045
 XY+0.045
Neg logit contributions
Msg-0.057
aida-0.056
 Belg-0.054
jac-0.053
hess-0.052
Token fourth
Token ID5544
Feature activation-5.51e-01

Pos logit contributions
Msg+0.311
aida+0.304
 Belg+0.296
jac+0.289
hess+0.285
Neg logit contributions
obar-0.240
20439-0.234
 inadvert-0.233
esty-0.221
 XY-0.219
Token volume
Token ID6115
Feature activation-2.33e-01

Pos logit contributions
Msg+0.416
aida+0.407
 Belg+0.397
jac+0.385
hess+0.380
Neg logit contributions
obar-0.341
20439-0.333
 inadvert-0.329
esty-0.315
 XY-0.310
Token settles
Token ID43684
Feature activation-1.72e+00

Pos logit contributions
Msg+0.181
aida+0.177
 Belg+0.172
jac+0.169
hess+0.166
Neg logit contributions
obar-0.139
 inadvert-0.136
20439-0.134
esty-0.128
 XY-0.127
Token into
Token ID656
Feature activation+5.43e-01

Pos logit contributions
Msg+1.239
aida+1.209
 Belg+1.174
jac+1.143
hess+1.125
Neg logit contributions
obar-1.127
 inadvert-1.097
20439-1.095
esty-1.046
 XY-1.035
Token a
Token ID257
Feature activation-8.41e-02

Pos logit contributions
obar+0.360
 inadvert+0.354
20439+0.346
 accidental+0.334
esty+0.333
Neg logit contributions
Msg-0.386
aida-0.376
 Belg-0.363
jac-0.354
hess-0.350
Token compl
Token ID2299
Feature activation+2.21e-02

Pos logit contributions
Msg+0.067
aida+0.065
 Belg+0.063
jac+0.062
hess+0.061
Neg logit contributions
obar-0.049
20439-0.048
 inadvert-0.048
esty-0.045
 XY-0.045
Tokenacent
Token ID12643
Feature activation-8.80e-01

Pos logit contributions
obar+0.008
20439+0.008
 inadvert+0.008
esty+0.007
 XY+0.007
Neg logit contributions
Msg-0.022
aida-0.021
 Belg-0.021
jac-0.021
hess-0.020
Token marriage
Token ID4845
Feature activation+6.79e-01

Pos logit contributions
Msg+0.688
aida+0.672
 Belg+0.658
jac+0.637
hess+0.630
Neg logit contributions
obar-0.521
20439-0.511
 inadvert-0.502
esty-0.480
 XY-0.471
Token with
Token ID351
Feature activation-4.20e-01

Pos logit contributions
obar+0.434
 inadvert+0.423
20439+0.417
esty+0.402
 um+0.398
Neg logit contributions
Msg-0.500
aida-0.491
 Belg-0.473
jac-0.462
hess-0.452
Token as
Token ID355
Feature activation+8.75e-02

Pos logit contributions
obar+0.090
20439+0.087
 inadvert+0.087
esty+0.083
 XY+0.082
Neg logit contributions
Msg-0.115
aida-0.112
 Belg-0.109
jac-0.106
hess-0.105
Token observed
Token ID6515
Feature activation+5.78e-01

Pos logit contributions
obar+0.053
 inadvert+0.051
20439+0.051
esty+0.048
 XY+0.048
Neg logit contributions
Msg-0.068
aida-0.066
 Belg-0.064
jac-0.063
hess-0.062
Token in
Token ID287
Feature activation+2.70e-01

Pos logit contributions
obar+0.415
 inadvert+0.405
20439+0.405
esty+0.386
 XY+0.384
Neg logit contributions
Msg-0.381
aida-0.371
 Belg-0.360
jac-0.347
hess-0.341
Token our
Token ID674
Feature activation+1.18e-01

Pos logit contributions
obar+0.174
20439+0.170
 inadvert+0.169
esty+0.161
 XY+0.160
Neg logit contributions
Msg-0.198
aida-0.193
 Belg-0.187
jac-0.182
hess-0.180
Token seismic
Token ID37463
Feature activation+2.43e+00

Pos logit contributions
obar+0.072
20439+0.070
 inadvert+0.070
esty+0.066
 XY+0.066
Neg logit contributions
Msg-0.091
aida-0.089
 Belg-0.087
jac-0.084
hess-0.083
Token analysis
Token ID3781
Feature activation-4.07e-01

Pos logit contributions
obar+1.451
 inadvert+1.416
20439+1.395
 XY+1.339
 um+1.333
Neg logit contributions
Msg-1.891
aida-1.835
 Belg-1.788
jac-1.748
hess-1.729
Token,
Token ID11
Feature activation+1.19e-01

Pos logit contributions
Msg+0.325
aida+0.317
 Belg+0.310
jac+0.302
hess+0.298
Neg logit contributions
obar-0.235
20439-0.229
 inadvert-0.227
esty-0.216
 XY-0.213
Token
Token ID447
Feature activation-9.06e-02

Pos logit contributions
obar+0.072
20439+0.070
 inadvert+0.070
esty+0.066
 XY+0.065
Neg logit contributions
Msg-0.092
aida-0.089
 Belg-0.087
jac-0.085
hess-0.084
Token
Token ID251
Feature activation+5.76e-01

Pos logit contributions
Msg+0.056
aida+0.054
 Belg+0.053
jac+0.051
hess+0.050
Neg logit contributions
obar-0.069
20439-0.067
 inadvert-0.067
esty-0.065
 XY-0.064
Token note
Token ID3465
Feature activation-2.59e-01

Pos logit contributions
obar+0.365
 inadvert+0.356
20439+0.356
esty+0.338
 XY+0.334
Neg logit contributions
Msg-0.427
aida-0.416
 Belg-0.405
jac-0.393
hess-0.387
Token the
Token ID262
Feature activation-1.55e-01

Pos logit contributions
Msg+0.196
aida+0.190
 Belg+0.186
jac+0.181
hess+0.178
Neg logit contributions
obar-0.160
20439-0.156
 inadvert-0.155
esty-0.148
 XY-0.146
Token
Token ID198
Feature activation-9.25e-02

Pos logit contributions
obar+0.158
20439+0.154
 inadvert+0.152
esty+0.145
 XY+0.143
Neg logit contributions
Msg-0.231
aida-0.226
 Belg-0.220
jac-0.214
hess-0.212
Token
Token ID198
Feature activation+9.21e-02

Pos logit contributions
Msg+0.082
aida+0.080
 Belg+0.079
jac+0.077
hess+0.076
Neg logit contributions
obar-0.045
20439-0.044
 inadvert-0.043
esty-0.041
 XY-0.040
TokenThe
Token ID464
Feature activation+9.29e-01

Pos logit contributions
obar+0.062
20439+0.061
 inadvert+0.060
esty+0.058
 XY+0.057
Neg logit contributions
Msg-0.064
aida-0.063
 Belg-0.061
jac-0.059
hess-0.058
Token shorts
Token ID22078
Feature activation+6.30e-01

Pos logit contributions
obar+0.561
20439+0.546
 inadvert+0.545
esty+0.518
 XY+0.514
Neg logit contributions
Msg-0.715
aida-0.697
 Belg-0.677
jac-0.661
hess-0.654
Token are
Token ID389
Feature activation+4.64e-01

Pos logit contributions
obar+0.345
 inadvert+0.334
20439+0.331
esty+0.315
 XY+0.312
Neg logit contributions
Msg-0.521
aida-0.508
 Belg-0.496
jac-0.483
hess-0.480
Token modeled
Token ID29563
Feature activation+2.38e+00

Pos logit contributions
obar+0.283
20439+0.274
 inadvert+0.274
esty+0.260
 XY+0.258
Neg logit contributions
Msg-0.356
aida-0.347
 Belg-0.337
jac-0.329
hess-0.326
Token on
Token ID319
Feature activation+3.31e-01

Pos logit contributions
obar+1.488
 inadvert+1.463
20439+1.436
 XY+1.392
 mm+1.390
Neg logit contributions
Msg-1.767
aida-1.719
 Belg-1.669
jac-1.621
hess-1.607
Token the
Token ID262
Feature activation+2.30e-01

Pos logit contributions
obar+0.211
20439+0.206
 inadvert+0.205
esty+0.196
 XY+0.194
Neg logit contributions
Msg-0.244
aida-0.238
 Belg-0.231
jac-0.225
hess-0.223
Token Body
Token ID12290
Feature activation-2.01e-01

Pos logit contributions
obar+0.139
20439+0.136
 inadvert+0.135
esty+0.129
 XY+0.127
Neg logit contributions
Msg-0.177
aida-0.173
 Belg-0.168
jac-0.164
hess-0.162
Token Paint
Token ID23467
Feature activation+2.64e+00

Pos logit contributions
Msg+0.151
aida+0.147
 Belg+0.144
jac+0.139
hess+0.138
Neg logit contributions
obar-0.125
20439-0.121
 inadvert-0.120
esty-0.115
 XY-0.114
Token line
Token ID1627
Feature activation+5.64e-01

Pos logit contributions
obar+1.648
20439+1.604
 inadvert+1.602
esty+1.542
 XY+1.527
Neg logit contributions
Msg-1.962
aida-1.901
 Belg-1.849
hess-1.803
jac-1.790
Token projects
Token ID4493
Feature activation+2.41e+00

Pos logit contributions
Msg+0.616
aida+0.601
 Belg+0.586
jac+0.569
hess+0.562
Neg logit contributions
obar-0.509
20439-0.497
 inadvert-0.493
esty-0.471
 XY-0.465
Token,
Token ID11
Feature activation+4.74e-01

Pos logit contributions
obar+1.473
 inadvert+1.447
20439+1.434
esty+1.370
 XY+1.368
Neg logit contributions
Msg-1.822
aida-1.773
 Belg-1.726
jac-1.676
hess-1.659
Token especially
Token ID2592
Feature activation-4.12e-01

Pos logit contributions
obar+0.281
20439+0.274
 inadvert+0.273
esty+0.259
 XY+0.258
Neg logit contributions
Msg-0.369
aida-0.361
 Belg-0.352
jac-0.342
hess-0.338
Token for
Token ID329
Feature activation+4.05e-01

Pos logit contributions
Msg+0.304
aida+0.297
 Belg+0.289
jac+0.281
hess+0.277
Neg logit contributions
obar-0.262
 inadvert-0.256
20439-0.255
esty-0.242
 XY-0.242
Token Burning
Token ID21460
Feature activation+5.55e-01

Pos logit contributions
obar+0.249
 inadvert+0.243
20439+0.242
esty+0.230
 XY+0.229
Neg logit contributions
Msg-0.308
aida-0.300
 Belg-0.292
jac-0.285
hess-0.281
Token Man
Token ID1869
Feature activation+3.83e-01

Pos logit contributions
obar+0.363
20439+0.356
 inadvert+0.353
esty+0.338
 XY+0.336
Neg logit contributions
Msg-0.398
aida-0.387
 Belg-0.377
jac-0.366
hess-0.362
Token.
Token ID13
Feature activation+1.75e-01

Pos logit contributions
obar+0.216
20439+0.210
 inadvert+0.209
esty+0.198
 XY+0.196
Neg logit contributions
Msg-0.310
aida-0.303
 Belg-0.296
jac-0.288
hess-0.284
Token
Token ID198
Feature activation+1.78e-01

Pos logit contributions
obar+0.097
20439+0.094
 inadvert+0.093
esty+0.088
 XY+0.087
Neg logit contributions
Msg-0.144
aida-0.141
 Belg-0.138
jac-0.134
hess-0.133
Token
Token ID198
Feature activation+3.92e-01

Pos logit contributions
obar+0.087
20439+0.084
 inadvert+0.084
esty+0.079
 XY+0.077
Neg logit contributions
Msg-0.157
aida-0.154
 Belg-0.151
jac-0.147
hess-0.145
Token[
Token ID58
Feature activation+8.54e-01

Pos logit contributions
obar+0.266
20439+0.260
 inadvert+0.258
esty+0.247
 XY+0.245
Neg logit contributions
Msg-0.272
aida-0.266
 Belg-0.259
jac-0.250
hess-0.247
TokenMath
Token ID37372
Feature activation+4.88e-01

Pos logit contributions
obar+0.582
20439+0.569
 inadvert+0.564
esty+0.542
 XY+0.537
Neg logit contributions
Msg-0.586
aida-0.573
 Belg-0.561
jac-0.536
hess-0.534
Token x
Token ID2124
Feature activation-1.62e-01

Pos logit contributions
obar+0.222
20439+0.214
 inadvert+0.211
esty+0.196
 XY+0.191
Neg logit contributions
Msg-0.549
aida-0.539
 Belg-0.528
jac-0.517
hess-0.512
Token.
Token ID13
Feature activation-1.46e+00

Pos logit contributions
Msg+0.129
aida+0.126
 Belg+0.123
jac+0.120
hess+0.118
Neg logit contributions
obar-0.095
20439-0.092
 inadvert-0.092
esty-0.087
 accidental-0.085
Tokenx
Token ID87
Feature activation-3.38e-01

Pos logit contributions
Msg+1.105
aida+1.069
 Belg+1.030
jac+1.024
hess+1.002
Neg logit contributions
obar-0.907
 inadvert-0.898
20439-0.893
esty-0.842
 accidental-0.838
Token.
Token ID13
Feature activation-1.45e+00

Pos logit contributions
Msg+0.269
aida+0.262
 Belg+0.256
jac+0.250
hess+0.246
Neg logit contributions
obar-0.196
20439-0.191
 inadvert-0.190
esty-0.180
 accidental-0.176
Tokenx
Token ID87
Feature activation-3.80e-01

Pos logit contributions
Msg+1.102
aida+1.068
 Belg+1.028
jac+1.021
hess+1.001
Neg logit contributions
obar-0.900
 inadvert-0.891
20439-0.886
esty-0.832
 accidental-0.831
Token.
Token ID13
Feature activation-1.51e+00

Pos logit contributions
Msg+0.307
aida+0.300
 Belg+0.293
jac+0.285
hess+0.282
Neg logit contributions
obar-0.216
20439-0.210
 inadvert-0.208
esty-0.198
 XY-0.195
Token151
Token ID24309
Feature activation+4.51e-01

Pos logit contributions
Msg+0.775
aida+0.750
 Belg+0.722
jac+0.689
hess+0.676
Neg logit contributions
obar-1.294
20439-1.273
 inadvert-1.265
esty-1.224
 XY-1.212
Token 103
Token ID15349
Feature activation+6.86e-01

Pos logit contributions
obar+0.282
20439+0.275
 inadvert+0.273
esty+0.260
 XY+0.258
Neg logit contributions
Msg-0.338
aida-0.330
 Belg-0.321
jac-0.312
hess-0.308
Token30
Token ID1270
Feature activation+8.34e-02

Pos logit contributions
obar+0.490
20439+0.485
 inadvert+0.475
esty+0.456
 XY+0.456
Neg logit contributions
Msg-0.449
aida-0.438
 Belg-0.425
jac-0.410
hess-0.405
Token29
Token ID1959
Feature activation-5.40e-02

Pos logit contributions
obar+0.057
20439+0.056
 inadvert+0.055
esty+0.053
 XY+0.052
Neg logit contributions
Msg-0.058
aida-0.056
 Belg-0.055
jac-0.053
hess-0.052
Token x
Token ID2124
Feature activation-5.32e-01

Pos logit contributions
Msg+0.052
aida+0.051
 Belg+0.050
jac+0.049
hess+0.049
Neg logit contributions
obar-0.022
20439-0.021
 inadvert-0.021
esty-0.019
 accidental-0.019
Token curb
Token ID20799
Feature activation+9.64e-01

Pos logit contributions
Msg+0.119
aida+0.115
 Belg+0.112
jac+0.109
hess+0.108
Neg logit contributions
obar-0.115
 inadvert-0.113
20439-0.112
esty-0.107
 XY-0.106
Token,
Token ID11
Feature activation-2.53e-01

Pos logit contributions
obar+0.549
 inadvert+0.536
20439+0.535
esty+0.505
 XY+0.499
Neg logit contributions
Msg-0.774
aida-0.752
 Belg-0.739
jac-0.716
hess-0.710
Token g
Token ID308
Feature activation+8.94e-01

Pos logit contributions
Msg+0.185
aida+0.181
 Belg+0.175
jac+0.170
hess+0.169
Neg logit contributions
obar-0.163
 inadvert-0.160
20439-0.159
esty-0.151
 um-0.151
Tokenutter
Token ID10381
Feature activation-1.84e+00

Pos logit contributions
obar+0.526
20439+0.506
 inadvert+0.505
esty+0.483
 um+0.473
Neg logit contributions
Msg-0.709
aida-0.687
 Belg-0.675
jac-0.650
hess-0.644
Token,
Token ID11
Feature activation-5.30e-01

Pos logit contributions
Msg+1.592
aida+1.566
 Belg+1.531
jac+1.491
hess+1.470
Neg logit contributions
obar-0.931
20439-0.910
 inadvert-0.889
esty-0.847
 XY-0.824
Token and
Token ID290
Feature activation-4.77e-01

Pos logit contributions
Msg+0.497
aida+0.487
 Belg+0.476
jac+0.466
hess+0.462
Neg logit contributions
obar-0.232
 inadvert-0.223
20439-0.223
esty-0.208
 XY-0.204
Token sidewalk
Token ID24058
Feature activation+3.88e-01

Pos logit contributions
Msg+0.348
aida+0.340
 Belg+0.328
jac+0.320
hess+0.318
Neg logit contributions
obar-0.308
 inadvert-0.301
20439-0.299
esty-0.285
 XY-0.284
Token are
Token ID389
Feature activation-6.51e-01

Pos logit contributions
obar+0.213
 inadvert+0.209
20439+0.207
esty+0.195
 XY+0.195
Neg logit contributions
Msg-0.318
aida-0.310
 Belg-0.304
jac-0.296
hess-0.293
Token all
Token ID477
Feature activation-2.99e-01

Pos logit contributions
Msg+0.456
aida+0.444
 Belg+0.431
jac+0.419
hess+0.413
Neg logit contributions
obar-0.439
20439-0.428
 inadvert-0.427
esty-0.408
 XY-0.404
Token raised
Token ID4376
Feature activation-1.10e+00

Pos logit contributions
Msg+0.221
aida+0.215
 Belg+0.210
jac+0.204
hess+0.201
Neg logit contributions
obar-0.191
20439-0.186
 inadvert-0.185
esty-0.176
 XY-0.174
Token by
Token ID416
Feature activation+2.80e-01

Pos logit contributions
Msg+0.842
aida+0.822
 Belg+0.801
jac+0.780
hess+0.770
Neg logit contributions
obar-0.672
20439-0.655
 inadvert-0.651
esty-0.620
 XY-0.613
TokenQuery
Token ID20746
Feature activation-2.94e-01

Pos logit contributions
Msg+0.503
aida+0.492
 Belg+0.479
jac+0.465
hess+0.459
Neg logit contributions
obar-0.439
20439-0.431
 inadvert-0.426
esty-0.406
 XY-0.401
Token and
Token ID290
Feature activation+5.40e-01

Pos logit contributions
Msg+0.225
aida+0.220
 Belg+0.214
jac+0.208
hess+0.206
Neg logit contributions
obar-0.179
20439-0.175
 inadvert-0.173
esty-0.165
 XY-0.163
Token the
Token ID262
Feature activation+3.27e-01

Pos logit contributions
obar+0.332
20439+0.323
 inadvert+0.322
esty+0.307
 XY+0.306
Neg logit contributions
Msg-0.409
aida-0.402
 Belg-0.388
jac-0.380
hess-0.375
Token public
Token ID1171
Feature activation+1.22e-01

Pos logit contributions
obar+0.197
20439+0.192
 inadvert+0.191
esty+0.182
 XY+0.181
Neg logit contributions
Msg-0.252
aida-0.247
 Belg-0.240
jac-0.234
hess-0.231
Token GitHub
Token ID21722
Feature activation+8.25e-01

Pos logit contributions
obar+0.078
20439+0.076
 inadvert+0.076
esty+0.073
 XY+0.072
Neg logit contributions
Msg-0.089
aida-0.087
 Belg-0.085
jac-0.082
hess-0.082
Token dataset
Token ID27039
Feature activation-5.97e-01

Pos logit contributions
obar+0.475
20439+0.464
 inadvert+0.459
esty+0.437
 XY+0.432
Neg logit contributions
Msg-0.657
aida-0.644
 Belg-0.627
jac-0.611
hess-0.603
Token to
Token ID284
Feature activation+2.16e-01

Pos logit contributions
Msg+0.466
aida+0.455
 Belg+0.444
jac+0.432
hess+0.426
Neg logit contributions
obar-0.354
20439-0.345
 inadvert-0.342
esty-0.326
 XY-0.321
Token discover
Token ID7073
Feature activation-6.23e-01

Pos logit contributions
obar+0.124
20439+0.120
 inadvert+0.120
esty+0.113
 XY+0.112
Neg logit contributions
Msg-0.173
aida-0.169
 Belg-0.165
jac-0.160
hess-0.159
Token the
Token ID262
Feature activation-7.02e-01

Pos logit contributions
Msg+0.460
aida+0.450
 Belg+0.438
jac+0.425
hess+0.419
Neg logit contributions
obar-0.395
20439-0.386
 inadvert-0.383
esty-0.366
 XY-0.361
Token most
Token ID749
Feature activation-6.03e-01

Pos logit contributions
Msg+0.563
aida+0.550
 Belg+0.538
jac+0.522
hess+0.516
Neg logit contributions
obar-0.402
20439-0.392
 inadvert-0.386
esty-0.368
 XY-0.361
Token used
Token ID973
Feature activation-1.94e+00

Pos logit contributions
Msg+0.491
aida+0.480
 Belg+0.469
jac+0.456
hess+0.451
Neg logit contributions
obar-0.338
20439-0.330
 inadvert-0.325
esty-0.310
 XY-0.304
Token of
Token ID286
Feature activation-2.10e-01

Pos logit contributions
Msg+0.496
aida+0.484
 Belg+0.472
jac+0.459
hess+0.455
Neg logit contributions
obar-0.364
 inadvert-0.353
20439-0.353
esty-0.338
 XY-0.331
Token the
Token ID262
Feature activation-4.08e-01

Pos logit contributions
Msg+0.152
aida+0.148
 Belg+0.143
jac+0.139
hess+0.139
Neg logit contributions
obar-0.137
 inadvert-0.134
20439-0.132
esty-0.127
 accidental-0.126
Token herd
Token ID27638
Feature activation-9.96e-01

Pos logit contributions
Msg+0.270
aida+0.263
 Belg+0.253
jac+0.247
hess+0.243
Neg logit contributions
obar-0.289
 inadvert-0.284
20439-0.283
esty-0.271
 XY-0.269
Token manifests
Token ID42190
Feature activation-2.51e+00

Pos logit contributions
Msg+0.780
aida+0.761
 Belg+0.743
jac+0.722
hess+0.714
Neg logit contributions
obar-0.589
20439-0.575
 inadvert-0.571
esty-0.543
 XY-0.536
Token a
Token ID257
Feature activation-3.54e-01

Pos logit contributions
Msg+1.686
aida+1.640
 Belg+1.598
jac+1.544
hess+1.521
Neg logit contributions
obar-1.749
20439-1.722
 inadvert-1.695
esty-1.629
 XY-1.610
Token form
Token ID1296
Feature activation-9.99e-01

Pos logit contributions
Msg+0.266
aida+0.260
 Belg+0.253
jac+0.246
hess+0.243
Neg logit contributions
obar-0.220
20439-0.214
 inadvert-0.213
esty-0.203
 XY-0.201
Token of
Token ID286
Feature activation+1.75e-01

Pos logit contributions
Msg+0.807
aida+0.789
 Belg+0.771
jac+0.750
hess+0.741
Neg logit contributions
obar-0.564
20439-0.551
 inadvert-0.545
esty-0.518
 XY-0.510
Token illness
Token ID8526
Feature activation-6.71e-01

Pos logit contributions
obar+0.112
 inadvert+0.110
20439+0.108
esty+0.104
 um+0.103
Neg logit contributions
Msg-0.128
aida-0.125
 Belg-0.121
jac-0.118
hess-0.117
Token.
Token ID13
Feature activation-3.57e-01

Pos logit contributions
Msg+0.533
aida+0.521
 Belg+0.508
jac+0.495
hess+0.489
Neg logit contributions
obar-0.390
20439-0.380
 inadvert-0.377
esty-0.358
 XY-0.353
Token Nonetheless
Token ID27251
Feature activation-1.36e+00

Pos logit contributions
Msg+0.272
aida+0.267
 Belg+0.257
jac+0.252
hess+0.250
Neg logit contributions
obar-0.217
20439-0.212
 inadvert-0.210
esty-0.199
 XY-0.199
Token,
Token ID11
Feature activation-3.78e-01

Pos logit contributions
Msg+1.060
aida+1.037
 Belg+1.008
jac+0.982
hess+0.970
Neg logit contributions
obar-0.814
20439-0.793
 inadvert-0.790
esty-0.751
 XY-0.741
Token dirty
Token ID11841
Feature activation-6.21e-01

Pos logit contributions
Msg+1.047
aida+1.023
 Belg+0.998
jac+0.969
hess+0.957
Neg logit contributions
obar-0.832
20439-0.812
 inadvert-0.804
esty-0.767
 XY-0.756
Token trick
Token ID6908
Feature activation-7.30e-01

Pos logit contributions
Msg+0.421
aida+0.411
 Belg+0.400
jac+0.386
hess+0.381
Neg logit contributions
obar-0.432
20439-0.422
 inadvert-0.418
esty-0.402
 XY-0.397
Token he
Token ID339
Feature activation-6.61e-01

Pos logit contributions
Msg+0.529
aida+0.516
 Belg+0.502
jac+0.488
hess+0.481
Neg logit contributions
obar-0.474
20439-0.464
 inadvert-0.461
esty-0.441
 um-0.434
Token could
Token ID714
Feature activation+1.56e-01

Pos logit contributions
Msg+0.525
aida+0.513
 Belg+0.501
jac+0.488
hess+0.483
Neg logit contributions
obar-0.382
20439-0.371
 inadvert-0.371
esty-0.351
 um-0.346
Token think
Token ID892
Feature activation+8.84e-01

Pos logit contributions
obar+0.099
 inadvert+0.096
20439+0.096
esty+0.091
 um+0.090
Neg logit contributions
Msg-0.117
aida-0.113
 Belg-0.110
jac-0.108
hess-0.107
Token of
Token ID286
Feature activation-5.89e-01

Pos logit contributions
obar+0.476
 inadvert+0.455
20439+0.454
esty+0.429
 accidental+0.429
Neg logit contributions
Msg-0.743
aida-0.726
 Belg-0.710
jac-0.694
hess-0.686
Token to
Token ID284
Feature activation-8.54e-02

Pos logit contributions
Msg+0.413
aida+0.402
 Belg+0.390
jac+0.379
hess+0.374
Neg logit contributions
obar-0.397
20439-0.389
 inadvert-0.386
esty-0.369
 XY-0.365
Token secure
Token ID5713
Feature activation+5.43e-01

Pos logit contributions
Msg+0.067
aida+0.065
 Belg+0.063
jac+0.062
hess+0.062
Neg logit contributions
obar-0.050
 inadvert-0.049
20439-0.049
esty-0.046
 um-0.046
Token his
Token ID465
Feature activation+2.88e-01

Pos logit contributions
obar+0.364
 inadvert+0.357
20439+0.356
esty+0.339
 um+0.338
Neg logit contributions
Msg-0.381
aida-0.372
 Belg-0.358
jac-0.348
hess-0.346
Token re
Token ID302
Feature activation+1.43e+00

Pos logit contributions
obar+0.169
 inadvert+0.165
20439+0.165
esty+0.156
 XY+0.154
Neg logit contributions
Msg-0.226
aida-0.221
 Belg-0.215
jac-0.210
hess-0.208
Token-
Token ID12
Feature activation-5.16e-01

Pos logit contributions
obar+1.008
 inadvert+0.976
20439+0.974
esty+0.945
 um+0.925
Neg logit contributions
Msg-0.972
aida-0.938
 Belg-0.911
jac-0.878
hess-0.867
Token playoff
Token ID13119
Feature activation-1.38e+00

Pos logit contributions
obar+0.111
 inadvert+0.108
20439+0.107
esty+0.102
 XY+0.101
Neg logit contributions
Msg-0.151
aida-0.148
 Belg-0.144
jac-0.140
hess-0.139
Token round
Token ID2835
Feature activation+2.41e+00

Pos logit contributions
Msg+1.014
aida+0.989
 Belg+0.963
jac+0.935
hess+0.922
Neg logit contributions
obar-0.878
20439-0.861
 inadvert-0.849
esty-0.814
 XY-0.801
Token or
Token ID393
Feature activation+3.46e-01

Pos logit contributions
obar+1.410
 inadvert+1.372
20439+1.341
 XY+1.292
esty+1.288
Neg logit contributions
Msg-1.894
aida-1.860
 Belg-1.812
jac-1.761
hess-1.731
Token re
Token ID302
Feature activation+2.07e-01

Pos logit contributions
 inadvert+0.217
obar+0.217
20439+0.211
 XY+0.204
 accidental+0.204
Neg logit contributions
Msg-0.255
aida-0.250
 Belg-0.240
jac-0.238
hess-0.231
Token-
Token ID12
Feature activation-9.59e-01

Pos logit contributions
obar+0.151
 inadvert+0.145
20439+0.145
esty+0.141
 XY+0.139
Neg logit contributions
Msg-0.135
aida-0.130
 Belg-0.127
jac-0.122
hess-0.119
Tokensign
Token ID12683
Feature activation-5.47e+00

Pos logit contributions
Msg+0.310
aida+0.291
 Belg+0.277
jac+0.251
hess+0.242
Neg logit contributions
obar-1.011
20439-0.993
 inadvert-0.990
esty-0.966
 XY-0.956
Tokens
Token ID82
Feature activation-6.19e-01

Pos logit contributions
Msg+2.798
aida+2.686
 Belg+2.643
jac+2.519
hess+2.518
Neg logit contributions
obar-4.575
20439-4.566
 inadvert-4.476
esty-4.285
 accidental-4.276
Token Lang
Token ID16332
Feature activation-1.17e+00

Pos logit contributions
Msg+0.432
aida+0.421
 Belg+0.410
jac+0.397
hess+0.392
Neg logit contributions
obar-0.418
20439-0.409
 inadvert-0.406
esty-0.389
 XY-0.384
Tokenen
Token ID268
Feature activation+7.74e-01

Pos logit contributions
Msg+0.828
aida+0.811
 Belg+0.786
jac+0.765
hess+0.754
Neg logit contributions
obar-0.777
20439-0.763
 inadvert-0.756
esty-0.721
 XY-0.715
Tokenbr
Token ID1671
Feature activation-5.48e-01

Pos logit contributions
obar+0.600
20439+0.585
 inadvert+0.578
esty+0.561
 XY+0.554
Neg logit contributions
Msg-0.466
aida-0.452
 Belg-0.439
jac-0.417
hess-0.413
Tokenun
Token ID403
Feature activation+4.76e-01

Pos logit contributions
Msg+0.342
aida+0.337
 Belg+0.322
jac+0.314
hess+0.309
Neg logit contributions
obar-0.404
20439-0.403
 inadvert-0.400
esty-0.383
 XY-0.381
Token players
Token ID1938
Feature activation-1.18e+00

Pos logit contributions
Msg+0.239
aida+0.233
 Belg+0.226
jac+0.220
hess+0.217
Neg logit contributions
obar-0.225
20439-0.220
 inadvert-0.220
esty-0.209
 XY-0.207
Token were
Token ID547
Feature activation-2.11e-01

Pos logit contributions
Msg+0.875
aida+0.854
 Belg+0.833
jac+0.808
hess+0.798
Neg logit contributions
obar-0.739
20439-0.722
 inadvert-0.716
esty-0.684
 XY-0.675
Token traded
Token ID14018
Feature activation+3.26e-01

Pos logit contributions
Msg+0.160
aida+0.156
 Belg+0.152
jac+0.148
hess+0.146
Neg logit contributions
obar-0.130
20439-0.127
 inadvert-0.126
esty-0.120
 XY-0.118
Token for
Token ID329
Feature activation+1.30e-01

Pos logit contributions
obar+0.202
 inadvert+0.197
20439+0.197
esty+0.187
 XY+0.185
Neg logit contributions
Msg-0.245
aida-0.239
 Belg-0.233
jac-0.227
hess-0.224
Token and
Token ID290
Feature activation+3.89e-01

Pos logit contributions
obar+0.082
 inadvert+0.080
20439+0.080
esty+0.076
 XY+0.076
Neg logit contributions
Msg-0.097
aida-0.095
 Belg-0.092
jac-0.089
hess-0.088
Token signed
Token ID4488
Feature activation-4.37e+00

Pos logit contributions
obar+0.246
 inadvert+0.240
20439+0.240
esty+0.227
 um+0.226
Neg logit contributions
Msg-0.288
aida-0.280
 Belg-0.273
jac-0.266
hess-0.262
Token by
Token ID416
Feature activation-2.51e-01

Pos logit contributions
Msg+2.887
aida+2.800
 Belg+2.741
jac+2.629
hess+2.614
Neg logit contributions
obar-3.069
20439-3.020
 inadvert-2.954
esty-2.870
 XY-2.806
Token the
Token ID262
Feature activation-4.24e-01

Pos logit contributions
Msg+0.180
aida+0.175
 Belg+0.170
jac+0.165
hess+0.163
Neg logit contributions
obar-0.166
20439-0.162
 inadvert-0.161
esty-0.154
 XY-0.153
Token sophomore
Token ID24505
Feature activation-5.85e-01

Pos logit contributions
Msg+0.310
aida+0.302
 Belg+0.294
jac+0.285
hess+0.282
Neg logit contributions
obar-0.272
20439-0.266
 inadvert-0.264
esty-0.252
 XY-0.250
Token General
Token ID3611
Feature activation-1.25e+00

Pos logit contributions
Msg+0.428
aida+0.416
 Belg+0.403
jac+0.393
hess+0.388
Neg logit contributions
obar-0.376
 inadvert-0.367
20439-0.363
esty-0.347
 XY-0.346
Token Manager
Token ID9142
Feature activation-1.71e+00

Pos logit contributions
Msg+1.177
aida+1.154
 Belg+1.130
jac+1.105
hess+1.095
Neg logit contributions
obar-0.539
20439-0.517
 inadvert-0.515
esty-0.480
 XY-0.472
Token had
Token ID550
Feature activation-6.71e-01

Pos logit contributions
Msg+0.361
aida+0.353
 Belg+0.344
jac+0.334
hess+0.330
Neg logit contributions
obar-0.285
20439-0.279
 inadvert-0.276
esty-0.263
 XY-0.259
Token sex
Token ID1714
Feature activation-2.50e-01

Pos logit contributions
Msg+0.500
aida+0.488
 Belg+0.475
jac+0.462
hess+0.456
Neg logit contributions
obar-0.421
20439-0.411
 inadvert-0.408
esty-0.390
 XY-0.385
Token sex
Token ID1714
Feature activation-5.71e-02

Pos logit contributions
Msg+0.182
aida+0.177
 Belg+0.173
jac+0.168
hess+0.165
Neg logit contributions
obar-0.162
 inadvert-0.157
20439-0.157
esty-0.150
 XY-0.149
Token.
Token ID13
Feature activation-3.04e-01

Pos logit contributions
Msg+0.041
aida+0.040
 Belg+0.039
jac+0.038
hess+0.037
Neg logit contributions
obar-0.038
20439-0.037
 inadvert-0.037
esty-0.035
 XY-0.035
Token I
Token ID314
Feature activation+1.43e-01

Pos logit contributions
Msg+0.220
aida+0.215
 Belg+0.209
jac+0.203
hess+0.200
Neg logit contributions
obar-0.197
20439-0.193
 inadvert-0.191
esty-0.183
 XY-0.181
Token bought
Token ID5839
Feature activation-3.73e+00

Pos logit contributions
obar+0.081
20439+0.079
 inadvert+0.078
esty+0.074
 XY+0.073
Neg logit contributions
Msg-0.115
aida-0.113
 Belg-0.110
jac-0.107
hess-0.106
Token drugs
Token ID5010
Feature activation-1.76e-01

Pos logit contributions
Msg+2.499
aida+2.428
 Belg+2.384
jac+2.298
hess+2.237
Neg logit contributions
obar-2.593
20439-2.578
 inadvert-2.502
esty-2.420
 XY-2.358
Token and
Token ID290
Feature activation-3.42e-01

Pos logit contributions
Msg+0.135
aida+0.131
 Belg+0.128
jac+0.124
hess+0.123
Neg logit contributions
obar-0.108
 inadvert-0.105
20439-0.105
esty-0.100
 XY-0.098
Token a
Token ID257
Feature activation-3.65e-01

Pos logit contributions
Msg+0.245
aida+0.241
 Belg+0.231
jac+0.226
hess+0.224
Neg logit contributions
obar-0.225
 inadvert-0.221
20439-0.217
esty-0.209
 um-0.209
Token massage
Token ID26900
Feature activation-1.36e+00

Pos logit contributions
Msg+0.271
aida+0.264
 Belg+0.256
jac+0.249
hess+0.247
Neg logit contributions
obar-0.230
 inadvert-0.224
20439-0.223
esty-0.213
 XY-0.211
Token from
Token ID422
Feature activation-1.06e+00

Pos logit contributions
Msg+1.038
aida+1.018
 Belg+0.991
jac+0.965
hess+0.951
Neg logit contributions
obar-0.820
20439-0.814
 inadvert-0.794
esty-0.761
 XY-0.748
Token activity
Token ID3842
Feature activation+8.03e-01

Pos logit contributions
Msg+0.539
aida+0.526
 Belg+0.512
jac+0.498
hess+0.492
Neg logit contributions
obar-0.446
20439-0.435
 inadvert-0.432
esty-0.412
 XY-0.407
Token elsewhere
Token ID8057
Feature activation-8.46e-01

Pos logit contributions
obar+0.509
 inadvert+0.502
20439+0.494
esty+0.476
 XY+0.473
Neg logit contributions
Msg-0.593
aida-0.573
 Belg-0.559
jac-0.547
hess-0.537
Token includes
Token ID3407
Feature activation-2.17e+00

Pos logit contributions
Msg+0.632
aida+0.616
 Belg+0.601
jac+0.584
hess+0.576
Neg logit contributions
obar-0.530
20439-0.517
 inadvert-0.514
esty-0.490
 XY-0.484
Token a
Token ID257
Feature activation-3.68e-01

Pos logit contributions
Msg+1.544
aida+1.517
 Belg+1.478
jac+1.426
hess+1.402
Neg logit contributions
obar-1.426
20439-1.396
 inadvert-1.371
esty-1.322
 XY-1.300
Token new
Token ID649
Feature activation+2.05e-01

Pos logit contributions
Msg+0.270
aida+0.262
 Belg+0.255
jac+0.249
hess+0.246
Neg logit contributions
obar-0.236
20439-0.230
 inadvert-0.230
esty-0.219
 XY-0.216
Token settlement
Token ID9443
Feature activation-3.42e+00

Pos logit contributions
obar+0.134
 inadvert+0.131
20439+0.131
esty+0.124
 XY+0.124
Neg logit contributions
Msg-0.148
aida-0.142
 Belg-0.139
jac-0.135
hess-0.134
Token (
Token ID357
Feature activation-4.96e-01

Pos logit contributions
Msg+2.400
aida+2.349
 Belg+2.289
jac+2.204
hess+2.171
Neg logit contributions
obar-2.282
20439-2.258
 inadvert-2.198
esty-2.125
 XY-2.081
Tokenwith
Token ID4480
Feature activation-1.00e+00

Pos logit contributions
Msg+0.326
aida+0.318
 Belg+0.309
jac+0.297
hess+0.294
Neg logit contributions
obar-0.355
20439-0.346
 inadvert-0.344
esty-0.331
 XY-0.327
Token private
Token ID2839
Feature activation-6.65e-01

Pos logit contributions
Msg+0.716
aida+0.699
 Belg+0.681
jac+0.660
hess+0.651
Neg logit contributions
obar-0.657
20439-0.643
 inadvert-0.636
esty-0.610
 XY-0.601
Token foreign
Token ID3215
Feature activation-1.34e+00

Pos logit contributions
Msg+0.451
aida+0.439
 Belg+0.425
jac+0.413
hess+0.407
Neg logit contributions
obar-0.462
20439-0.452
 inadvert-0.451
esty-0.431
 XY-0.428
Token funding
Token ID4918
Feature activation+1.59e+00

Pos logit contributions
Msg+1.002
aida+0.979
 Belg+0.954
jac+0.926
hess+0.914
Neg logit contributions
obar-0.838
20439-0.819
 inadvert-0.811
esty-0.775
 XY-0.764
Token Or
Token ID1471
Feature activation-4.21e-02

Pos logit contributions
Msg+0.132
aida+0.129
 Belg+0.127
jac+0.123
hess+0.121
Neg logit contributions
obar-0.095
20439-0.092
 inadvert-0.091
esty-0.087
 XY-0.085
Token at
Token ID379
Feature activation-5.22e-02

Pos logit contributions
Msg+0.032
aida+0.031
 Belg+0.031
jac+0.030
hess+0.029
Neg logit contributions
obar-0.026
20439-0.025
 inadvert-0.025
esty-0.024
 XY-0.024
Token least
Token ID1551
Feature activation+9.36e-01

Pos logit contributions
Msg+0.048
aida+0.048
 Belg+0.047
jac+0.045
hess+0.045
Neg logit contributions
obar-0.023
20439-0.022
 inadvert-0.022
esty-0.021
 XY-0.020
Token,
Token ID11
Feature activation+9.31e-02

Pos logit contributions
obar+0.561
 inadvert+0.555
20439+0.545
esty+0.526
 XY+0.524
Neg logit contributions
Msg-0.719
aida-0.704
 Belg-0.679
jac-0.667
hess-0.663
Token know
Token ID760
Feature activation+1.10e+00

Pos logit contributions
obar+0.060
20439+0.059
 inadvert+0.058
esty+0.056
 XY+0.055
Neg logit contributions
Msg-0.068
aida-0.066
 Belg-0.064
jac-0.062
hess-0.062
Token enough
Token ID1576
Feature activation-4.54e+00

Pos logit contributions
obar+0.746
 inadvert+0.731
20439+0.721
esty+0.706
 XY+0.703
Neg logit contributions
Msg-0.755
aida-0.742
 Belg-0.713
jac-0.700
hess-0.692
Token about
Token ID546
Feature activation-7.87e-01

Pos logit contributions
Msg+3.051
aida+2.965
 Belg+2.923
jac+2.761
hess+2.733
Neg logit contributions
obar-3.164
20439-3.115
 inadvert-3.036
esty-2.869
 accidental-2.849
Token each
Token ID1123
Feature activation-2.22e+00

Pos logit contributions
Msg+0.536
aida+0.522
 Belg+0.506
jac+0.492
hess+0.486
Neg logit contributions
obar-0.545
 inadvert-0.532
20439-0.531
esty-0.509
 XY-0.507
Token culture
Token ID3968
Feature activation-4.63e-01

Pos logit contributions
Msg+1.698
aida+1.662
 Belg+1.620
jac+1.567
hess+1.551
Neg logit contributions
obar-1.355
20439-1.325
 inadvert-1.304
esty-1.242
 XY-1.222
Token so
Token ID523
Feature activation-6.20e-01

Pos logit contributions
Msg+0.340
aida+0.332
 Belg+0.323
jac+0.313
hess+0.309
Neg logit contributions
obar-0.296
20439-0.289
 inadvert-0.287
esty-0.275
 XY-0.272
Token that
Token ID326
Feature activation-2.65e-01

Pos logit contributions
Msg+0.414
aida+0.403
 Belg+0.391
jac+0.378
hess+0.374
Neg logit contributions
obar-0.439
20439-0.429
 inadvert-0.428
esty-0.411
 XY-0.408