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

    Neuronpedia

    INDEX
    Explanations

    punctuation, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utable
    -0.18
    ordan
    -0.16
    477
    -0.14
    ç§
    -0.14
    utow
    -0.14
    elligent
    -0.14
    uitar
    -0.14
    ilen
    -0.13
    827
    -0.13
    lico
    -0.13
    POSITIVE LOGITS
    ãĥĥãĥĹ
    0.15
    MDB
    0.14
    Painter
    0.14
    .infinity
    0.14
    ADB
    0.14
    ìĦĿ
    0.14
    íĥ
    0.14
    adt
    0.13
    .gdx
    0.13
    AGMA
    0.13
    Act Density 0.016%

    No Known Activations