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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "shorten" and its derivatives

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

    shorten time or duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     newInstance
    -0.47
    jface
    -0.47
    playerId
    -0.45
    staticmethod
    -0.44
     Tages
    -0.44
     detectors
    -0.43
     testCase
    -0.43
     medium
    -0.42
    intValue
    -0.41
     positive
    -0.41
    POSITIVE LOGITS
     shortening
    1.34
     shortened
    1.30
     shorten
    1.27
    缩
    0.93
    縮
    0.91
     сокра
    0.90
     narrowing
    0.79
     narrowed
    0.78
    reduction
    0.65
     abbreviated
    0.65
    Act Density 0.009%

    No Known Activations