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

    Neuronpedia

    INDEX
    Explanations

    references to identifiers and IDs in code or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itzer
    -0.19
    eries
    -0.17
    ENAME
    -0.16
    onse
    -0.16
    erman
    -0.15
    itz
    -0.15
    alth
    -0.15
    imento
    -0.15
    ese
    -0.14
    itecture
    -0.14
    POSITIVE LOGITS
    entities
    0.27
    ENTITY
    0.23
    aho
    0.19
    emp
    0.18
    leness
    0.18
    _rsa
    0.17
    iom
    0.16
    gent
    0.16
    0.15
    gen
    0.15
    Act Density 0.047%

    No Known Activations