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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     rul
    -0.84
    agall
    -0.76
     oun
    -0.73
     destro
    -0.73
     Moff
    -0.70
     acknow
    -0.69
     Mub
    -0.69
     confir
    -0.68
    ypes
    -0.67
    cffff
    -0.67
    POSITIVE LOGITS
    Center
    0.78
    atur
    0.73
    Cent
    0.70
    artisan
    0.70
    WAR
    0.68
    Fake
    0.66
    Proof
    0.66
    icion
    0.64
    Mill
    0.64
    ature
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.