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

    Neuronpedia

    INDEX
    Explanations

    items related to coding syntax and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    featureID
    -0.90
    parsedMessage
    -0.89
    Portail
    -0.88
    tagHelperRunner
    -0.88
     Roskov
    -0.86
    PreferredItem
    -0.83
    mybatisplus
    -0.80
    MigrationBuilder
    -0.79
    tanleria
    -0.76
    createCanvas
    -0.74
    POSITIVE LOGITS
    ↵
    0.52
    ↵↵
    0.52
    Finally
    0.45
    </blockquote>
    0.44
    Again
    0.43
    [toxicity=0]
    0.43
    </code>
    0.42
    $\
    0.41
    \
    0.40
     \\
    0.38
    Act Density 9.430%

    No Known Activations