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

    Neuronpedia

    INDEX
    Explanations

    specific syntax or structures related to figure captions and references in documents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ulongan
    -0.79
    EndGlobalSection
    -0.79
    contentLoaded
    -0.79
    oneofs
    -0.77
    FieldNumber
    -0.77
    ApplicationTests
    -0.76
     NSCoder
    -0.74
    elry
    -0.73
    borderSide
    -0.71
     bots
    -0.69
    POSITIVE LOGITS
    <eos>
    0.62
    ↵↵↵
    0.57
     ever
    0.57
    function
    0.54
    ↵↵↵↵↵
    0.53
    ↵↵↵↵↵↵
    0.52
     (
    0.52
    代
    0.50
    </blockquote>
    0.50
     代
    0.49
    Act Density 0.001%

    No Known Activations