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

    Neuronpedia

    INDEX
    Explanations

    references to rapid changes or increases in various contexts

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

    rapidLY followed by change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exitRule
    -0.58
     مرئيه
    -0.54
     esternos
    -0.51
    Източници
    -0.46
    rungsseite
    -0.44
     Wink
    -0.44
     Drink
    -0.43
    Speak
    -0.43
    $_['
    -0.42
    Igual
    -0.41
    POSITIVE LOGITS
     rapidly
    1.87
     swiftly
    0.85
     rapidamente
    0.83
     rápidamente
    0.81
    rapid
    0.76
     gradually
    0.75
     rapidement
    0.73
     steadily
    0.72
     slowly
    0.72
     vigorously
    0.71
    Act Density 0.006%

    No Known Activations