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

    Neuronpedia

    INDEX
    Explanations

    words related to specific physical characteristics or attributes

    oai_token-act-pair · gpt-3.5-turbo

    descriptors of various characters and their attributes in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.68
     solitary
    -0.56
    TPPStreamerBot
    -0.55
     )]
    -0.54
     sidx
    -0.52
     Insight
    -0.50
     faulty
    -0.50
     mathemat
    -0.49
    é¾į
    -0.49
    hematically
    -0.47
    POSITIVE LOGITS
     sandwic
    0.67
    aments
    0.63
    ahime
    0.62
    stros
    0.62
     awaits
    0.60
    smanship
    0.57
    vironments
    0.55
     attRot
    0.54
     spew
    0.54
     featuring
    0.53
    Act Density 0.791%

    No Known Activations