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

    Neuronpedia

    INDEX
    Explanations

    negations or expressions of denial

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

    contractions ending in n't

    np_acts-logits-general · gemini-2.5-flash-lite

    It detects negation fragments—roots of negative contractions like aren, wasn, haven, isn, don, didn, hasn (the "n't" parts).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.44
     незавершена
    -0.41
     insuffisamment
    -0.41
    País
    -0.36
    Сылтамалар
    -0.36
     ویکی‌پدی
    -0.36
    webElementXpaths
    -0.34
    锈钢
    -0.34
    MemoryWarning
    -0.33
    haer
    -0.33
    POSITIVE LOGITS
    AndEndTag
    0.59
     ब्रेकडाउन
    0.57
    })`
    0.55
     שוליים
    0.52
    出版年
    0.52
    principalTable
    0.52
     surla
    0.51
    HtmlAttribute
    0.49
    ostante
    0.47
     kasarigan
    0.46
    Act Density 0.872%

    No Known Activations