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

    Neuronpedia

    INDEX
    Explanations

    proper names and titles

    oai_token-act-pair · gpt-3.5-turbo

    names or identifiers related to individuals, particularly in a professional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.75
     ASIC
    -0.66
     Goose
    -0.64
     Swordsman
    -0.64
     Cheong
    -0.62
    ufact
    -0.59
     Hallow
    -0.58
     Ms
    -0.58
     Fitzgerald
    -0.58
    atform
    -0.58
    POSITIVE LOGITS
    pta
    0.87
    士
    0.81
    acus
    0.77
    omal
    0.75
    pport
    0.75
    iaz
    0.75
    allah
    0.74
    imaru
    0.71
    etsk
    0.71
    letal
    0.71
    Act Density 0.400%

    No Known Activations