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

    Neuronpedia

    INDEX
    Explanations

    references to academic or formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    os
    -0.71
     Hus
    -0.70
    ()")
    -0.70
    los
    -0.67
     }}"></
    -0.67
    yan
    -0.66
    ;"></
    -0.65
    */)
    -0.64
    a
    -0.62
    '')
    -0.61
    POSITIVE LOGITS
     $|
    1.53
     |
    1.46
    ]|
    1.44
    .|
    1.41
    +|
    1.38
    |
    1.37
    -|
    1.32
    '|
    1.30
    "|
    1.28
     '|
    1.27
    Act Density 0.080%

    No Known Activations