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

    Neuronpedia

    INDEX
    Explanations

    hyphens in various contexts

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

    all- followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pedersen
    -0.54
    HttpStatusCode
    -0.46
    ersdorf
    -0.45
     Hodgson
    -0.45
     programme
    -0.44
    FileReader
    -0.43
    oudou
    -0.43
    esen
    -0.42
    karten
    -0.42
     scheme
    -0.42
    POSITIVE LOGITS
    All
    0.90
     All
    0.86
    ALL
    0.71
    all
    0.69
     ALL
    0.68
    assertAll
    0.66
    AnchorStyles
    0.66
    setAll
    0.65
     Semua
    0.64
    オール
    0.61
    Act Density 0.005%

    No Known Activations