INDEX
Explanations
occurrences of the word "ur"
the term "cur" in various contexts
New Auto-Interp
Negative Logits
otle
-0.76
ept
-0.66
Schultz
-0.62
ophers
-0.62
eah
-0.61
aan
-0.61
Feder
-0.61
Benedict
-0.60
eller
-0.60
ophe
-0.59
POSITIVE LOGITS
geon
1.35
geons
1.28
rences
1.06
thur
1.05
andom
0.97
Rahman
0.96
geoning
0.92
ricane
0.91
assic
0.91
iosity
0.89
Activations Density 0.042%