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

    Neuronpedia

    INDEX
    Explanations

    topics, proposals, and concepts for discussion and consideration

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Mamm
    -0.67
    administ
    -0.63
    ads
    -0.60
    \/\/
    -0.58
    san
    -0.57
    ords
    -0.57
    owl
    -0.57
    emale
    -0.56
    Ba
    -0.55
     occupancy
    -0.54
    POSITIVE LOGITS
     ideas
    0.72
     Ideas
    0.72
    ensical
    0.65
     underlying
    0.64
     underpin
    0.61
    ĸļ
    0.61
     embodied
    0.59
    matter
    0.58
    ually
    0.58
     borrowed
    0.58
    Act Density 14.472%

    No Known Activations