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

    Neuronpedia

    INDEX
    Explanations

    language suggesting involvement, control, or status in some context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¿ãĥ³
    -0.15
    ilyn
    -0.15
    imar
    -0.15
    avar
    -0.14
    orex
    -0.14
    Slf
    -0.14
    untas
    -0.14
    WND
    -0.14
    inder
    -0.14
    ile
    -0.14
    POSITIVE LOGITS
    ayload
    0.16
    ække
    0.15
    flash
    0.15
    ırak
    0.14
    ientos
    0.14
    brook
    0.14
     Brock
    0.14
    skip
    0.14
    MD
    0.14
    £
    0.14
    Act Density 0.009%

    No Known Activations