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

    Neuronpedia

    INDEX
    Explanations

    marker tokens indicating the beginning of a segment or new context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.70
     
    -0.63
    ↵
    -0.57
     the
    -0.57
    </h3>
    -0.50
    </h1>
    -0.47
     -
    -0.46
     a
    -0.45
     ...
    -0.45
    ...
    -0.44
    POSITIVE LOGITS
     Efq
    1.14
     ་་
    1.11
     ―――――
    1.11
    PerformLayout
    1.10
    parsedMessage
    1.08
     AspNetCore
    1.07
     فريبيس
    1.07
     oprot
    1.03
     المعيارى
    1.03
    +#+#
    1.03
    Act Density 0.081%

    No Known Activations