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

    Neuronpedia

    INDEX
    Explanations

    phrases related to universities and research institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to universities and research institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     swear
    -0.79
    FX
    -0.78
    UV
    -0.76
    FG
    -0.75
     prayers
    -0.70
    ITCH
    -0.68
    fx
    -0.68
    DH
    -0.67
     FG
    -0.66
     stricken
    -0.65
    POSITIVE LOGITS
     Carnegie
    4.30
    negie
    2.73
     Brookings
    2.11
     Rockefeller
    1.46
     Mellon
    1.34
    kefeller
    1.34
     RAND
    1.30
     Cornell
    1.22
     Vanderbilt
    1.17
     Cato
    1.09
    Act Density 0.023%

    No Known Activations