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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of universities, colleges, and institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to academic institutions and their names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Uriel
    -0.85
     Sho
    -0.79
     OW
    -0.76
     Hog
    -0.76
     Toast
    -0.75
    utz
    -0.73
     Yo
    -0.73
     Upton
    -0.72
     Otto
    -0.72
     Oprah
    -0.71
    POSITIVE LOGITS
    CC
    1.55
    CCC
    1.47
    C
    1.34
    c
    1.31
    cc
    1.30
    CP
    1.26
    CF
    1.25
    CS
    1.24
    Cs
    1.23
    cs
    1.22
    Act Density 1.049%

    No Known Activations