INDEX
Explanations
latex mathematical notation and symbols
New Auto-Interp
Negative Logits
gott
-0.56
bar
-0.49
McKenna
-0.47
rang
-0.47
plik
-0.47
trion
-0.46
apin
-0.46
kon
-0.46
strada
-0.46
kh
-0.46
POSITIVE LOGITS
)}}
1.06
))}
1.06
]")]
1.05
)}
1.04
'}
1.04
}}
1.02
}}}}
1.01
]}
1.00
betweenstory
0.99
")}
0.99
Activations Density 1.476%