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

    Neuronpedia

    INDEX
    Explanations

    accidental events or incidents

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "accident" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zee
    -0.87
    reens
    -0.81
    tsky
    -0.79
    tch
    -0.76
    bern
    -0.75
    ebus
    -0.75
    berman
    -0.74
    estine
    -0.73
    pees
    -0.73
    rylic
    -0.72
    POSITIVE LOGITS
     accident
    0.97
     accidents
    0.81
    worthiness
    0.79
     occ
    0.78
     involving
    0.78
     mish
    0.75
     Odyssey
    0.74
     wreck
    0.73
     hazard
    0.72
     occurring
    0.70
    Act Density 0.016%

    No Known Activations