INDEX
Explanations
information related to online forums
references to online forums
New Auto-Interp
Negative Logits
birds
-0.67
Ballistic
-0.67
xon
-0.66
lys
-0.65
Lilly
-0.63
lust
-0.61
meter
-0.61
efe
-0.60
ograp
-0.59
osition
-0.58
POSITIVE LOGITS
forums
0.93
forum
0.92
postings
0.87
moderators
0.84
thread
0.80
moderator
0.79
forum
0.78
threads
0.74
forums
0.73
Forums
0.73
Activations Density 0.011%