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

    Neuronpedia

    INDEX
    Explanations

    negative quantifiers and expressions related to evidence or claims

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

    that come after "no"

    np_acts-logits-general · gemini-2.0-flash

    no followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     who
    -0.48
    <bos>
    -0.43
     المعيارى
    -0.41
     ucap
    -0.40
     őket
    -0.40
    さで
    -0.39
     που
    -0.39
     hvor
    -0.38
    了他
    -0.38
    ที่จะ
    -0.35
    POSITIVE LOGITS
     مشين
    0.99
    цездатний
    0.97
     AssemblyTitle
    0.93
     happens
    0.91
    ChildScrollView
    0.88
     تانيه
    0.88
     Efq
    0.87
    帖最后由
    0.87
    MENAFN
    0.85
     Beſ
    0.85
    Act Density 0.470%

    No Known Activations