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

    Neuronpedia

    INDEX
    Explanations

    information related to accidents or disasters, specifically focusing on details of crashes

    oai_token-act-pair · gpt-3.5-turbo

    references to vehicle crashes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achu
    -0.69
    icrobial
    -0.68
    Ĭ±
    -0.65
    ...]
    -0.63
    iries
    -0.62
    THER
    -0.61
    arov
    -0.61
    yi
    -0.61
    rolog
    -0.60
    erity
    -0.59
    POSITIVE LOGITS
    worthiness
    0.95
     crash
    0.94
     crashes
    0.94
    ulent
    0.88
    Crash
    0.84
    ulence
    0.81
     wreck
    0.81
     Dive
    0.77
     Crash
    0.73
    olean
    0.73
    Act Density 0.012%

    No Known Activations