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

    Neuronpedia

    INDEX
    Explanations

    the word "what" indicating questions or inquiries about specifics

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

    exactly what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MENAFN
    -0.63
    دانشنامهٔ
    -0.60
    تقاوى
    -0.56
    -------------</
    -0.53
    etcode
    -0.52
    sizeCache
    -0.51
    LookAnd
    -0.51
     Signalez
    -0.50
    Rüyada
    -0.49
    Personendaten
    -0.48
    POSITIVE LOGITS
    Exactly
    0.54
    exactly
    0.47
    EXACT
    0.46
     Exactly
    0.45
    precise
    0.44
     EXACTLY
    0.43
     precisely
    0.42
    Exact
    0.40
    exact
    0.40
    Everyone
    0.39
    Act Density 0.012%

    No Known Activations