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

    Neuronpedia

    INDEX
    Explanations

    negations or phrases that express dissent or disagreement

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

    whether... or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.52
    ➟
    -0.50
    ➯
    -0.49
    ativna
    -0.47
     AssemblyCompany
    -0.46
    quelize
    -0.42
     Cinque
    -0.42
    Rhestr
    -0.40
    GEBURTS
    -0.40
    bitField
    -0.39
    POSITIVE LOGITS
     anyway
    0.59
    anyway
    0.57
    Anyways
    0.56
     anyways
    0.55
     anyhow
    0.55
    imanapun
    0.51
     Anyways
    0.47
    Välislingid
    0.47
    Anyhow
    0.46
     Anyway
    0.46
    Act Density 0.006%

    No Known Activations