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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or doubt

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

    Alternatives or negations

    np_acts-logits-general · gemini-2.0-flash

    whether or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }}">
    -0.55
    ViewImports
    -0.53
     pokry
    -0.47
    TargetApi
    -0.47
    lebo
    -0.46
     ImportError
    -0.45
    titu
    -0.44
    MLLoader
    -0.43
     Turi
    -0.43
    </caption>
    -0.42
    POSITIVE LOGITS
     not
    2.54
    not
    2.03
    Not
    1.83
     Not
    1.81
    NOT
    1.59
     NOT
    1.57
     نه
    1.46
     nicht
    1.32
     bukan
    1.30
     niet
    1.21
    Act Density 0.185%

    No Known Activations