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

    Neuronpedia

    INDEX
    Explanations

    references to high quantities or levels, often in relation to performance metrics or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quiv
    -0.16
    oard
    -0.15
    monds
    -0.14
    cular
    -0.14
    gems
    -0.14
    ipa
    -0.14
    ège
    -0.14
    quet
    -0.14
    odon
    -0.14
    _IL
    -0.14
    POSITIVE LOGITS
    (er
    0.20
    /high
    0.17
     enough
    0.17
     indeed
    0.17
    /fast
    0.16
    781
    0.16
     Priest
    0.14
    aje
    0.14
    ummer
    0.14
    ieder
    0.14
    Act Density 0.364%

    No Known Activations