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

    Neuronpedia

    INDEX
    Explanations

    questions soliciting opinions

    oai_token-act-pair · gpt-3.5-turbo

    inquiries that seek opinions or thoughts from the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Adin
    -0.73
     Immunity
    -0.64
    gm
    -0.61
    vity
    -0.61
    mone
    -0.60
    zik
    -0.59
     allerg
    -0.59
    fw
    -0.57
     consultants
    -0.56
     diarrhea
    -0.56
    POSITIVE LOGITS
     about
    0.80
    76561
    0.73
     inspires
    0.71
    PLA
    0.68
     ABOUT
    0.67
    aptic
    0.66
    onymous
    0.66
    ij士
    0.65
     weighs
    0.65
     motiv
    0.65
    Act Density 0.042%

    No Known Activations