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

    Neuronpedia

    INDEX
    Explanations

    expressions of certainty or affirmation

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

    Adverbs indicating certainty

    np_acts-logits-general · gemini-2.0-flash

    certainly, definitely, clearly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     actually
    -1.10
    actually
    -1.04
     Actually
    -0.95
    Actually
    -0.95
     apparently
    -0.94
     basically
    -0.88
     ACTUALLY
    -0.86
    Basically
    -0.85
     Basically
    -0.85
    意外と
    -0.83
    POSITIVE LOGITS
    Архівовано
    0.69
    EditorBrowsable
    0.67
     MessageBoxIcon
    0.66
    ConstraintMaker
    0.62
    unkt
    0.61
    saraba
    0.61
    writeFieldEnd
    0.60
    aarrggbb
    0.60
    しも
    0.59
     فريبيس
    0.59
    Act Density 0.226%

    No Known Activations