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

    Neuronpedia

    INDEX
    Explanations

    comparisons or contrasts within the text

    oai_token-act-pair · gpt-3.5-turbo

    key concepts related to social mechanisms and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancial
    -0.84
    escription
    -0.83
    mercial
    -0.81
    itably
    -0.81
    retty
    -0.81
    ;;;;;;;;;;;;
    -0.80
    uilt
    -0.77
    ocument
    -0.75
     Mehran
    -0.75
    oided
    -0.75
    POSITIVE LOGITS
    CLASSIFIED
    0.98
    WAYS
    0.84
    NetMessage
    0.81
     toile
    0.76
     behavi
    0.75
    namese
    0.69
     agitation
    0.68
     suscept
    0.67
     largeDownload
    0.67
     reperc
    0.66
    Act Density 6.906%

    No Known Activations