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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    partial
    -0.79
    option
    -0.73
    ãĥĩãĤ£
    -0.70
    suff
    -0.65
    ilitation
    -0.63
     futures
    -0.63
    unity
    -0.63
     CD
    -0.61
     disabled
    -0.60
     deletion
    -0.59
    POSITIVE LOGITS
    izabeth
    0.71
    enstein
    0.70
    lesi
    0.69
     Rossi
    0.68
    ĨĴ
    0.66
    vez
    0.66
     Zot
    0.66
    jab
    0.65
    ertodd
    0.64
    vich
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.