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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    MpServer
    -0.68
    girlfriend
    -0.67
     starving
    -0.66
    prison
    -0.66
    obyl
    -0.64
     js
    -0.63
    ðŁĺ
    -0.63
    ruciating
    -0.62
     immersion
    -0.62
     bow
    -0.62
    POSITIVE LOGITS
    icio
    0.80
    enegger
    0.72
     Franch
    0.72
     Advis
    0.70
     Fiorina
    0.69
    TX
    0.69
     Leone
    0.68
    asters
    0.67
    lio
    0.67
    oleon
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.