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

    Neuronpedia

    INDEX
    Explanations

    coding-related error messages

    oai_token-act-pair · gpt-3.5-turbo

    programming terminology related to function and variable usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢİ
    -0.85
    SPONSORED
    -0.75
     âĢİ
    -0.71
    Fight
    -0.70
     Sabb
    -0.69
    bill
    -0.68
     prosecutions
    -0.68
     Bett
    -0.68
    HCR
    -0.68
    Tenn
    -0.68
    POSITIVE LOGITS
     recursive
    1.06
     configure
    1.04
     lookup
    1.04
     duplicate
    1.02
     specified
    1.02
     user
    1.00
     computed
    0.99
     parameter
    0.99
     initialization
    0.99
     compute
    0.99
    Act Density 1.157%

    No Known Activations