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

    Neuronpedia

    INDEX
    Explanations

    specific symbols or fragments in programming and technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    velt
    -0.19
    feld
    -0.19
    fabs
    -0.16
    fila
    -0.16
    frau
    -0.16
    folk
    -0.16
    felt
    -0.16
    fil
    -0.15
    fur
    -0.15
    facts
    -0.15
    POSITIVE LOGITS
    ront
    0.40
    eature
    0.38
    eatures
    0.37
    rame
    0.36
    ield
    0.36
    orce
    0.36
    irst
    0.36
    eed
    0.35
    rames
    0.35
    amily
    0.34
    Act Density 0.088%

    No Known Activations