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

    Neuronpedia

    INDEX
    Explanations

    indicators of conditional statements and return values in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cke
    -0.19
     èĭ
    -0.15
     scho
    -0.15
    ala
    -0.14
    lauf
    -0.14
     Vak
    -0.14
    abled
    -0.14
    assa
    -0.14
    ui
    -0.14
    laughter
    -0.13
    POSITIVE LOGITS
    anje
    0.16
    OPSIS
    0.15
    ATEGORIES
    0.15
     мÑĸÑģÑĤ
    0.15
    ãĥ¼ãĥ³
    0.15
    aign
    0.15
    /jav
    0.14
    PEND
    0.14
    ospace
    0.14
    λεÏħ
    0.13
    Act Density 0.059%

    No Known Activations