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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal terms and regulations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unemploy
    -0.71
     looms
    -0.66
    76561
    -0.64
     combatants
    -0.63
    reon
    -0.62
     spoil
    -0.61
    :/
    -0.61
     entertained
    -0.59
     nailed
    -0.58
     distur
    -0.58
    POSITIVE LOGITS
     addition
    1.41
     spite
    1.36
    cluding
    1.29
    jured
    1.29
    juries
    1.29
    ventory
    1.29
    herent
    1.28
     contrast
    1.27
    flation
    1.25
     lieu
    1.25
    Act Density 1.088%

    No Known Activations