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

    Neuronpedia

    INDEX
    Explanations

    references to trolling or behaviors associated with trolls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĦاÙħ
    -0.17
    emouth
    -0.17
     Lomb
    -0.14
    Unnamed
    -0.14
    dol
    -0.14
     hers
    -0.14
    onth
    -0.14
    LineStyle
    -0.13
    .removeAttribute
    -0.13
    sort
    -0.13
    POSITIVE LOGITS
    adic
    0.15
    auge
    0.15
    atsu
    0.15
    uler
    0.14
    pute
    0.14
    chestra
    0.14
    ativity
    0.14
    ĤŃ
    0.14
    zilla
    0.14
    osphere
    0.14
    Act Density 0.007%

    No Known Activations