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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and syntax elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edar
    -0.15
    addtogroup
    -0.14
    amo
    -0.14
    arel
    -0.14
    itzer
    -0.14
     ntohs
    -0.14
    ót
    -0.14
     cone
    -0.14
    azen
    -0.14
    es
    -0.13
    POSITIVE LOGITS
    rello
    0.16
    ige
    0.15
    ãĤ¤ãĤº
    0.15
    ispers
    0.14
    mez
    0.14
    æ¦ľ
    0.14
     ì²
    0.14
    obar
    0.14
    duck
    0.14
     outs
    0.13
    Act Density 0.008%

    No Known Activations