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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their associated formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opp
    -0.15
    ¼
    -0.15
     vas
    -0.15
    athan
    -0.15
    aida
    -0.14
    ddf
    -0.14
    Tube
    -0.14
    aya
    -0.14
     Threat
    -0.14
     plug
    -0.14
    POSITIVE LOGITS
    (æ°´
    0.16
    iales
    0.15
    emas
    0.15
    createCommand
    0.15
    _POLL
    0.15
    AQ
    0.14
    оло
    0.14
     rodin
    0.14
    ÑĪиб
    0.14
    emap
    0.13
    Act Density 0.075%

    No Known Activations