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

    Neuronpedia

    INDEX
    Explanations

    programming or code-related syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.91
     للاسماء
    -0.86
     kasarigan
    -0.85
    HasForeignKey
    -0.81
    دانشنامهٔ
    -0.80
     '\\;'
    -0.80
    Становништво
    -0.74
     calendriers
    -0.74
     <=",
    -0.73
    verwijspagina
    -0.71
    POSITIVE LOGITS
    \{\\
    0.75
    0.63
    [toxicity=0]
    0.53
    </em>
    0.53
     *

    0.52
    IMPORTED
    0.51
    \_
    0.51
    </thead>
    0.50
    enumi
    0.50
    Parcelable
    0.48
    Act Density 0.817%
    No Known Activations