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

    Neuronpedia

    INDEX
    Explanations

    references to educational or informational books and guides

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oller
    -0.15
    porno
    -0.15
    bsub
    -0.15
    pillar
    -0.14
     Joi
    -0.14
     shock
    -0.14
     pom
    -0.14
    à¸ģำ
    -0.14
    phins
    -0.14
    misc
    -0.14
    POSITIVE LOGITS
    -series
    0.15
     series
    0.15
     tin
    0.14
     edition
    0.14
     pitched
    0.14
    fait
    0.14
    uang
    0.14
    format
    0.14
     editions
    0.14
     Laud
    0.14
    Act Density 0.028%

    No Known Activations