INDEX
Explanations
mentions of specific names like "Willie" and "Willis" within various contexts
references to specific individuals, particularly those named Willie, and concepts related to politicization
New Auto-Interp
Negative Logits
yrinth
-0.82
illin
-0.80
ariat
-0.77
iliary
-0.77
urrent
-0.76
itement
-0.70
orers
-0.70
uding
-0.70
antly
-0.69
amination
-0.68
POSITIVE LOGITS
borough
0.84
ktop
0.83
creen
0.82
ï¸
0.82
boro
0.79
oos
0.79
mic
0.77
fulness
0.77
burg
0.77
awa
0.74
Activations Density 0.038%