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

    Neuronpedia

    INDEX
    Explanations

    university names

    oai_token-act-pair · gpt-3.5-turbo

    alphanumeric identifiers and academic institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.85
    èª
    -0.75
    é¾įåĸļ士
    -0.69
    ĻĤ
    -0.68
    NRS
    -0.68
    ãĥı
    -0.65
    èĪ
    -0.64
    Reviewer
    -0.62
    Reviewed
    -0.62
    Catalog
    -0.61
    POSITIVE LOGITS
     Rockefeller
    0.74
    hyde
    0.73
    rimination
    0.68
    phia
    0.66
    Ö¼
    0.66
     Pil
    0.65
    utsche
    0.63
    geon
    0.63
    inction
    0.63
     Claw
    0.63
    Act Density 0.720%

    No Known Activations