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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to physical injuries

    oai_token-act-pair · gpt-3.5-turbo

    references to injuries or physical damage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sche
    -0.68
    orph
    -0.64
    minist
    -0.63
     Lynd
    -0.61
    ocratic
    -0.61
    occ
    -0.61
    development
    -0.61
     Dayton
    -0.59
    sat
    -0.59
    gent
    -0.58
    POSITIVE LOGITS
     wounds
    1.55
     inflicted
    1.09
     scars
    1.07
     wound
    0.98
     heals
    0.87
    terness
    0.85
     sore
    0.79
     Shards
    0.76
    nesday
    0.75
     redes
    0.75
    Act Density 0.007%

    No Known Activations