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

    Neuronpedia

    INDEX
    Explanations

    occurrences of function definitions and their attributes in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Schul
    -0.15
     Auf
    -0.15
     Carlo
    -0.14
     Imper
    -0.14
    ofire
    -0.14
     Ath
    -0.13
    pole
    -0.13
     Dive
    -0.13
     Prophet
    -0.13
    proof
    -0.13
    POSITIVE LOGITS
    ìłĢ
    0.15
    berger
    0.15
    .gmail
    0.14
    agnostics
    0.14
    asper
    0.14
    eye
    0.13
    xCD
    0.13
    UILTIN
    0.13
    Initializer
    0.13
    inja
    0.13
    Act Density 0.053%

    No Known Activations