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

    Neuronpedia

    INDEX
    Explanations

    references to physical injuries and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to injuries and wounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essions
    -0.75
    oggle
    -0.73
    Ü
    -0.71
    urch
    -0.69
    rador
    -0.69
    oS
    -0.68
    ramid
    -0.67
    ordan
    -0.67
    iazep
    -0.66
    ondon
    -0.65
    POSITIVE LOGITS
     wounds
    1.34
     inflicted
    1.28
     scars
    0.99
     wound
    0.86
     wounded
    0.83
     wounding
    0.82
     suffered
    0.81
     healed
    0.81
     pierced
    0.79
     incurred
    0.78
    Act Density 0.020%

    No Known Activations