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

    Neuronpedia

    INDEX
    Explanations

    references to important identifiers and keys in a data context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ationToken
    -0.18
    ucci
    -0.17
    èķī
    -0.15
    ±
    -0.15
    alley
    -0.15
    al
    -0.15
    aklı
    -0.15
    phere
    -0.14
    apus
    -0.14
    arians
    -0.14
    POSITIVE LOGITS
    note
    0.23
    notes
    0.22
    hole
    0.21
    edi
    0.20
    eb
    0.20
    holder
    0.18
    nes
    0.18
    chains
    0.17
    ways
    0.17
    logger
    0.16
    Act Density 0.059%

    No Known Activations