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

    Neuronpedia

    INDEX
    Explanations

    words related to medical conditions and healthcare facilities

    oai_token-act-pair · gpt-3.5-turbo

    references to coma or related medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    self
    -0.71
    Penn
    -0.68
    ģ
    -0.66
    DN
    -0.63
    rug
    -0.62
    Ģ
    -0.61
    Unique
    -0.61
    Princ
    -0.61
    advertisement
    -0.61
    ĥ
    -0.60
    POSITIVE LOGITS
     coma
    1.43
    wcs
    0.88
    ormal
    0.80
     decomp
    0.78
    itial
    0.77
     withd
    0.76
    irtual
    0.75
    beat
    0.74
     ridden
    0.73
    ivery
    0.72
    Act Density 0.006%

    No Known Activations