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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    MJ
    -0.77
     Allied
    -0.64
     Jonas
    -0.62
    )].
    -0.61
    ertodd
    -0.59
    ãĤŃ
    -0.58
    ni
    -0.58
    Ń·
    -0.58
    HAM
    -0.57
    Js
    -0.57
    POSITIVE LOGITS
     Poc
    0.79
    negie
    0.75
    ramid
    0.69
    licks
    0.67
    ritical
    0.65
    nings
    0.65
     Belle
    0.64
     hijab
    0.64
     Tuls
    0.64
    abus
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.