INDEX
Explanations
mentions of specific individuals, particularly those with the name "Thom."
New Auto-Interp
Negative Logits
ept
-0.70
REDACTED
-0.69
gerald
-0.67
hips
-0.66
DRAG
-0.66
GROUND
-0.63
Education
-0.63
eers
-0.61
DOS
-0.59
ETF
-0.59
POSITIVE LOGITS
psons
1.48
Yor
1.26
ason
1.12
ás
1.02
ophe
1.01
aston
1.01
Browne
1.00
inational
0.95
ife
0.94
istic
0.93
Activations Density 0.002%