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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     veto
    -0.71
     devast
    -0.65
    DoS
    -0.63
     debunk
    -0.63
    ultz
    -0.62
    evil
    -0.62
     divest
    -0.60
    bps
    -0.59
    iasco
    -0.59
     Nos
    -0.58
    POSITIVE LOGITS
     Ambro
    0.72
    ãĤ¦ãĤ¹
    0.66
    TED
    0.65
     [|
    0.65
    tro
    0.65
     æľ
    0.63
     reperto
    0.63
    ée
    0.62
    ãĤ´
    0.62
    thood
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.