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

    Neuronpedia

    INDEX
    Explanations

    web URLs and parameters

    oai_token-act-pair · gpt-3.5-turbo

    technical elements associated with data structuring and embedding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dangerous
    -0.69
     Immunity
    -0.63
     Moonlight
    -0.63
    tarian
    -0.61
     Oxy
    -0.60
     Jericho
    -0.58
     Libertarian
    -0.58
    issance
    -0.57
    regor
    -0.57
     Armageddon
    -0.56
    POSITIVE LOGITS
    &
    0.88
    utm
    0.88
    =
    0.85
    daq
    0.82
    =/
    0.75
    work
    0.71
    cd
    0.71
    _.
    0.70
    _
    0.70
    dp
    0.70
    Act Density 0.094%

    No Known Activations