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

    Neuronpedia

    INDEX
    Explanations

    references to time intervals and durations

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

    time taken or required

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.43
    writeFieldEnd
    -0.39
     виправивши
    -0.38
     NSObject
    -0.38
     opérés
    -0.38
     فريبيس
    -0.38
     Савезне
    -0.37
    styleable
    -0.37
    TokenNameEQUAL
    -0.37
     antemano
    -0.37
    POSITIVE LOGITS
     quick
    0.63
    quick
    0.60
     quicker
    0.59
     Fastest
    0.59
     quickest
    0.59
     Speed
    0.58
     Quick
    0.57
    Quick
    0.57
    Takes
    0.56
     speed
    0.56
    Act Density 0.196%

    No Known Activations