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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey a sense of surprise or unexpectedness

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

    Comes before "surprising" or "surprisingly"

    np_acts-logits-general · gemini-2.0-flash

    not surprising / unsurprising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rüyada
    -0.44
     computadoras
    -0.43
     supuestamente
    -0.41
     industriel
    -0.40
     tehd
    -0.40
     vallée
    -0.40
     específicamente
    -0.38
     garantías
    -0.38
     garantía
    -0.38
     fotográfico
    -0.38
    POSITIVE LOGITS
    GraphicsUnit
    0.63
     AssemblyTitle
    0.60
     understandably
    0.57
     understandable
    0.55
     unsur
    0.54
     traced
    0.52
    そりゃ
    0.52
     expected
    0.52
    expected
    0.52
    脚注の使い方
    0.52
    Act Density 0.322%

    No Known Activations