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

    Neuronpedia

    INDEX
    Explanations

    references to crashes or incidents related to cars and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Indus
    -0.62
    üli
    -0.53
    jstor
    -0.49
     Warehouse
    -0.48
    rhe
    -0.47
     scissors
    -0.47
    DropColumn
    -0.47
     DIST
    -0.47
    verses
    -0.45
     بلکه
    -0.45
    POSITIVE LOGITS
     Crash
    0.86
     crash
    0.86
    crash
    0.80
    Crash
    0.80
    +#+
    0.79
    Sucesor
    0.76
     فريبيس
    0.70
    횟
    0.70
    ButtonModule
    0.69
     disambiguazione
    0.67
    Act Density 0.040%

    No Known Activations