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

    Neuronpedia

    INDEX
    Explanations

    descriptions of unusual or exaggerated situations or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    humorous or exaggerated descriptions and reviews, particularly those related to unique experiences or performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTO
    -0.76
    isSpecialOrderable
    -0.74
    actionDate
    -0.74
    untled
    -0.71
    ivating
    -0.69
     Tayyip
    -0.68
    anwhile
    -0.66
    umed
    -0.66
    pecting
    -0.64
    ivas
    -0.64
    POSITIVE LOGITS
     predicament
    0.80
     existence
    0.80
     selves
    0.80
     tale
    0.76
     manners
    0.75
     stance
    0.74
     excuse
    0.73
     conco
    0.73
     relationship
    0.73
     basis
    0.72
    Act Density 0.925%

    No Known Activations