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

    Neuronpedia

    INDEX
    Explanations

    specific symbols or formatting elements, often related to categorization or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Arca
    -0.73
    cob
    -0.68
     nawr
    -0.68
    nesc
    -0.67
    ob
    -0.67
    */)
    -0.66
    ()")
    -0.65
    ensement
    -0.65
     arca
    -0.65
    Arca
    -0.64
    POSITIVE LOGITS
     |
    1.60
     $|
    1.45
    +|
    1.31
    ]|
    1.28
    .|
    1.27
    ("|
    1.27
    |
    1.27
    "|
    1.26
     $|\
    1.26
    }|
    1.25
    Act Density 0.089%

    No Known Activations