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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or negation

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

    Contractions with "not" or "'s"

    np_acts-logits-general · gemini-2.0-flash

    dont think, and thats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.76
    PageContext
    -0.69
    帖最后由
    -0.69
    disposing
    -0.67
    memoized
    -0.67
    //</
    -0.66
     (‘
    -0.65
    (‘
    -0.63
    XmlAccessType
    -0.63
    LabelTagHelper
    -0.63
    POSITIVE LOGITS
    Heres
    0.81
     يتيمه
    0.78
    '
    0.74
    ´
    0.73
    Thats
    0.73
     Theres
    0.73
    Theres
    0.71
     doesnt
    0.70
    `
    0.69
     Thats
    0.69
    Act Density 0.087%

    No Known Activations