INDEX
Explanations
mentions of Donald Trump in various contexts
New Auto-Interp
Negative Logits
ania
-0.17
iale
-0.16
introdu
-0.16
OfFile
-0.15
ICON
-0.14
mium
-0.14
okie
-0.14
utom
-0.14
uffs
-0.13
ndata
-0.13
POSITIVE LOGITS
/light
0.15
SK
0.14
åħī
0.14
icans
0.14
kins
0.14
åύ
0.14
illin
0.14
åŀ
0.14
_bh
0.13
ollider
0.13
Activations Density 0.022%