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

    Neuronpedia

    INDEX
    Explanations

    punctuations and sentence endings, indicating a focus on sentence structure or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     […]
    -0.79
    ↵
    -0.69
    ...
    -0.66
    id
    -0.62
    ↵↵↵
    -0.59
     ...
    -0.56
    ↵↵
    -0.56
    </blockquote>
    -0.56
    ind
    -0.55
    </em>
    -0.54
    POSITIVE LOGITS
    Again
    1.18
     Again
    1.11
    InputBorder
    1.09
    again
    1.06
    AndEndTag
    1.04
    ValueStyle
    0.99
     again
    0.95
     تضيفلها
    0.93
     pinulongan
    0.92
    setViewportView
    0.90
    Act Density 0.006%

    No Known Activations