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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    jri
    -0.80
    ghai
    -0.78
    ailability
    -0.75
    illion
    -0.71
     tremend
    -0.70
    itaire
    -0.68
    nered
    -0.68
    obyl
    -0.68
    egal
    -0.66
    ornings
    -0.66
    POSITIVE LOGITS
    VIDEO
    0.77
     è£ıè
    0.68
    YP
    0.67
     Zap
    0.66
     KEY
    0.66
     Director
    0.63
     Terminator
    0.63
     Magnetic
    0.62
    BACK
    0.62
    READ
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.