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

    Neuronpedia

    INDEX
    Explanations

    references to "star" and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ester
    -0.17
    elho
    -0.17
    eah
    -0.17
    ÛĮا
    -0.17
    ieder
    -0.17
    esel
    -0.17
    emente
    -0.16
    esch
    -0.15
    ymous
    -0.15
    tan
    -0.15
    POSITIVE LOGITS
    ved
    0.40
    ry
    0.39
    burst
    0.39
    light
    0.36
    kest
    0.35
    bucks
    0.35
    fish
    0.34
    vation
    0.33
    lit
    0.33
    let
    0.33
    Act Density 0.025%

    No Known Activations