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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and organizations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Rebels
    -0.75
    etheless
    -0.68
    EStream
    -0.65
    espie
    -0.65
     Blizz
    -0.64
     extraction
    -0.60
     convey
    -0.60
     captcha
    -0.60
     Eternity
    -0.60
     Gemini
    -0.60
    POSITIVE LOGITS
    CA
    1.19
    CS
    1.13
    SE
    1.12
    VA
    1.10
    SP
    1.09
    SC
    1.09
    NA
    1.08
    SA
    1.08
    aim
    1.06
    GS
    1.06
    Act Density 14.320%

    No Known Activations