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

    Neuronpedia

    INDEX
    Explanations

    official references or contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "official" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.84
    esville
    -0.81
    ĸļ
    -0.79
    ertodd
    -0.77
    lust
    -0.77
    rums
    -0.76
    nesota
    -0.75
    ocene
    -0.71
    bane
    -0.71
    =-=-
    -0.68
    POSITIVE LOGITS
    dom
    1.02
     sanctioned
    0.92
     scorer
    0.85
    ities
    0.80
     confirmation
    0.79
     sanction
    0.77
    ised
    0.76
     spokes
    0.76
     announcement
    0.75
     documentation
    0.74
    Act Density 0.057%

    No Known Activations