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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper names, specifically notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Laos
    -0.69
    á¹
    -0.63
    irlf
    -0.63
     Portug
    -0.61
     Gaia
    -0.59
    oÄŁ
    -0.59
    ostics
    -0.59
    ModLoader
    -0.57
    eenth
    -0.56
    Tea
    -0.55
    POSITIVE LOGITS
    taker
    0.68
    owitz
    0.65
    elson
    0.65
    arden
    0.64
    antage
    0.63
    ermott
    0.62
    lamm
    0.62
    gat
    0.62
    xual
    0.62
    dden
    0.61
    Act Density 0.114%

    No Known Activations