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

    Neuronpedia

    INDEX
    Explanations

    terms related to people's backgrounds and professions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or personal backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orsi
    -0.73
    ].
    -0.71
    usercontent
    -0.71
    plet
    -0.69
    Answer
    -0.69
    $.
    -0.68
    idden
    -0.65
    Recommend
    -0.64
    ".
    -0.63
    zik
    -0.63
    POSITIVE LOGITS
     bol
    0.68
     boasting
    0.62
    BuyableInstoreAndOnline
    0.61
     Canter
    0.59
     (),
    0.58
     eccentric
    0.57
     meanwhile
    0.56
    ,,,,,,,,
    0.54
    ®,
    0.54
     faded
    0.53
    Act Density 0.937%

    No Known Activations