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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "symbol" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aus
    -0.19
    avors
    -0.18
    .AutoScaleMode
    -0.16
    ิà¸ŀ
    -0.16
    ening
    -0.15
    iba
    -0.15
    STA
    -0.15
    liness
    -0.14
    yb
    -0.14
    /lo
    -0.14
    POSITIVE LOGITS
    ically
    0.26
    osate
    0.19
    /sign
    0.18
    izes
    0.18
    lico
    0.17
    izing
    0.17
    ical
    0.17
    ize
    0.17
    owie
    0.16
    ized
    0.16
    Act Density 0.014%

    No Known Activations