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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "crash" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ✨:
    -0.81
     surla
    -0.79
    TagHelper
    -0.70
     Colman
    -0.66
     Barb
    -0.65
    AutoresizingMask
    -0.63
    KeySpec
    -0.62
     EconPapers
    -0.60
    เภ
    -0.60
    findpost
    -0.60
    POSITIVE LOGITS
     crash
    2.22
     crashes
    1.97
     Crash
    1.92
     crashed
    1.91
    crash
    1.90
    Crash
    1.78
     crashing
    1.70
     Cras
    1.48
    cras
    1.31
     cras
    1.23
    Act Density 0.068%

    No Known Activations