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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or lack of knowledge

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

    preceding or following "know" or "knew."

    np_acts-logits-general · gemini-2.0-flash

    expressing uncertainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.79
    SequentialGroup
    -0.78
    DoubleQuotes
    -0.73
    хьтан
    -0.71
     &___
    -0.71
     nahilalakip
    -0.70
     ویکی‌پدیای
    -0.70
    ])));
    -0.67
    IsContent
    -0.67
     PARSER
    -0.65
    POSITIVE LOGITS
     knows
    1.14
     dunno
    1.05
     unknown
    1.02
     know
    1.00
    knows
    0.94
     idk
    0.92
     неизвест
    0.89
    unknown
    0.88
     Unknown
    0.82
    know
    0.80
    Act Density 0.149%

    No Known Activations