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

    Neuronpedia

    INDEX
    Explanations

    references to stunts and stunt performance in film

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

    stunts challenges adventure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    formik
    -0.50
     kasarigan
    -0.45
    tonsoft
    -0.43
    WriteBarrier
    -0.43
    contentLoaded
    -0.42
    ografija
    -0.42
     TextAlign
    -0.41
    bitField
    -0.40
     tricot
    -0.40
    InputTagHelper
    -0.39
    POSITIVE LOGITS
     stunts
    0.59
     acrobat
    0.57
     acrob
    0.55
     stunt
    0.50
     adventurous
    0.49
     hazards
    0.49
     @"/
    0.47
     Hazards
    0.47
     adren
    0.46
     SAFETY
    0.45
    Act Density 0.051%

    No Known Activations