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

    Neuronpedia

    INDEX
    Explanations

    legal and political terms

    oai_token-act-pair · gpt-3.5-turbo

    references to legal and political restrictions or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "#
    -0.62
     recy
    -0.59
     Reload
    -0.57
     crochet
    -0.55
     Collider
    -0.54
     booze
    -0.54
     refill
    -0.53
     scoop
    -0.52
     slang
    -0.52
     Aer
    -0.52
    POSITIVE LOGITS
     ..."
    1.14
    .,"
    0.92
    ,'"
    0.91
     âĢ¦"
    0.89
    [/
    0.89
    .",
    0.88
    ?",
    0.85
     [...]
    0.83
    ',"
    0.82
    ,''
    0.82
    Act Density 1.213%

    No Known Activations