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

    Neuronpedia

    INDEX
    Explanations

    words related to physical accidents or injuries

    oai_token-act-pair · gpt-3.5-turbo

    references to incidents or events characterized as accidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zee
    -0.88
    tch
    -0.79
    ebus
    -0.78
    estine
    -0.77
    tsky
    -0.77
    reens
    -0.74
    rylic
    -0.73
    antics
    -0.72
    oyal
    -0.72
    emonic
    -0.72
    POSITIVE LOGITS
     accident
    0.92
     accidents
    0.86
    worthiness
    0.85
     involving
    0.79
     Odyssey
    0.74
     hazard
    0.73
     occ
    0.72
     mish
    0.71
     crashes
    0.70
     crash
    0.69
    Act Density 0.014%

    No Known Activations