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

    Neuronpedia

    INDEX
    Explanations

    the word "original" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    original versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.68
    zzleHttp
    -0.52
    aarrggbb
    -0.49
    égard
    -0.46
     
    -0.45
    참고
    -0.45
    extAlignment
    -0.44
    titleMargin
    -0.43
    ArgsConstructor
    -0.42
     ministries
    -0.42
    POSITIVE LOGITS
     original
    1.15
    Original
    1.04
     ORIGINAL
    1.01
    original
    1.00
     originally
    0.98
     Original
    0.97
     ursprünglichen
    0.93
     originais
    0.92
     Originally
    0.91
     originales
    0.89
    Act Density 0.014%

    No Known Activations