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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical injuries and wounds

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of injuries and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adian
    -0.65
    natureconservancy
    -0.63
     snipp
    -0.60
    uminati
    -0.59
    compan
    -0.59
    gres
    -0.58
    eworld
    -0.58
    anyl
    -0.58
     START
    -0.57
    vana
    -0.56
    POSITIVE LOGITS
     inflicted
    1.26
     sustained
    1.18
     suffered
    1.10
     incurred
    1.02
     caused
    0.90
     consistent
    0.89
     inhal
    0.86
     wounds
    0.83
    hooting
    0.82
     attributed
    0.81
    Act Density 0.080%

    No Known Activations