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

    Neuronpedia

    INDEX
    Explanations

    information related to academic qualifications and scholarly publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilogy
    -0.07
     ÎĬ
    -0.07
    aws
    -0.07
    alach
    -0.06
    akov
    -0.06
    ilde
    -0.06
    लब
    -0.06
    ples
    -0.06
     engineering
    -0.06
    ytt
    -0.06
    POSITIVE LOGITS
     argument
    0.07
     book
    0.07
     mon
    0.07
     research
    0.07
     arguing
    0.07
     project
    0.07
     Mellon
    0.07
    cul
    0.07
     sint
    0.06
     argue
    0.06
    Act Density 0.017%

    No Known Activations