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

    Neuronpedia

    INDEX
    Explanations

    elements of dialogue and discussion that convey uncertainty or disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omination
    -0.14
    ofday
    -0.13
    ICENSE
    -0.12
    ucci
    -0.12
    ilen
    -0.12
    <quote
    -0.12
    iž
    -0.12
    ÛĮز
    -0.12
    opc
    -0.12
    uggy
    -0.12
    POSITIVE LOGITS
    quia
    0.15
    ds
    0.14
    kaar
    0.13
    ssel
    0.13
     Sabb
    0.13
    vrier
    0.13
     ï
    0.13
    arti
    0.13
    peat
    0.13
     [âĢ¦
    0.13
    Act Density 2.495%

    No Known Activations