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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical injuries

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zee
    -0.68
    travel
    -0.68
    chie
    -0.67
    minist
    -0.66
    ramid
    -0.66
    tz
    -0.65
    arten
    -0.64
    arity
    -0.63
    zees
    -0.61
     Prospect
    -0.61
    POSITIVE LOGITS
     inflicted
    1.21
     incurred
    1.05
    hooting
    0.95
     injuries
    0.94
     suffered
    0.91
     sustained
    0.85
    ptoms
    0.81
     wounds
    0.79
    letal
    0.76
     bruises
    0.75
    Act Density 0.033%

    No Known Activations