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

    Neuronpedia

    INDEX
    Explanations

    references to figures and formatting commands related to document structuring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alus
    -0.18
    ataires
    -0.16
    quential
    -0.15
    anka
    -0.15
    oli
    -0.15
    rok
    -0.15
    heed
    -0.14
    gz
    -0.14
    iciary
    -0.14
    aptor
    -0.14
    POSITIVE LOGITS
    evin
    0.18
    line
    0.18
    451
    0.16
    áž
    0.16
    ing
    0.15
    842
    0.15
     conce
    0.15
     Rag
    0.14
    float
    0.14
    lined
    0.14
    Act Density 0.012%

    No Known Activations