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

    Neuronpedia

    INDEX
    Explanations

    words related to organizations or groups

    oai_token-act-pair · gpt-3.5-turbo

    symbols or specific characters that may represent licensing or quality standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ction
    -0.66
     seiz
    -0.65
     Glacier
    -0.64
     Slug
    -0.64
    AAF
    -0.60
     Passage
    -0.58
    agall
    -0.58
    icks
    -0.58
     shelf
    -0.57
     Gael
    -0.57
    POSITIVE LOGITS
    cause
    0.91
    then
    0.87
    shall
    0.86
    nown
    0.84
    which
    0.83
    said
    0.80
    _>
    0.80
    according
    0.79
    including
    0.78
    sed
    0.77
    Act Density 0.267%

    No Known Activations