Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    PP
    1.00
     PP
    0.96
    KP
    0.95
     Pati
    0.91
     KP
    0.90
     PIP
    0.89
    PI
    0.89
    Pip
    0.86
    Pad
    0.86
    P
    0.85
    POSITIVE LOGITS
     Withers
    1.11
     Hellen
    1.06
     Chau
    1.04
     Yel
    1.00
     Lazarus
    1.00
    oglou
    0.98
     Gord
    0.98
     Yol
    0.98
     Andree
    0.96
     limousine
    0.96
    Act Density 2.071%

    No Known Activations