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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrast or exceptions in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.49
     CreateTagHelper
    -0.47
     addirittura
    -0.46
     spesielt
    -0.46
    不止
    -0.46
    Билгалдахарш
    -0.45
     falsche
    -0.44
    깐
    -0.43
    indd
    -0.43
     hurtig
    -0.42
    POSITIVE LOGITS
    MLLoader
    0.86
    Otherwise
    0.76
     Otherwise
    0.75
    audiovisuel
    0.70
     AssemblyCulture
    0.68
     otherwise
    0.67
    otherwise
    0.67
     Trouver
    0.65
    UnknownFields
    0.64
    invokeLater
    0.64
    Act Density 0.299%

    No Known Activations