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

    Neuronpedia

    INDEX
    Explanations

    references to new policies, administrations, or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udu
    -0.15
    uren
    -0.14
    kal
    -0.14
    unfinished
    -0.14
    ytut
    -0.14
    áty
    -0.14
    gles
    -0.14
    itize
    -0.14
    onso
    -0.14
    adıģı
    -0.14
    POSITIVE LOGITS
    swire
    0.18
    iche
    0.17
    -found
    0.15
    roz
    0.15
    _latency
    0.14
    adir
    0.14
    uce
    0.14
    .sponge
    0.14
    icho
    0.14
    erve
    0.14
    Act Density 0.059%

    No Known Activations