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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific keywords related to health care and medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pecially
    -0.77
     unknownFields
    -0.71
    withstanding
    -0.70
    ditionally
    -0.69
    vailable
    -0.69
    ordinaire
    -0.69
    unately
    -0.64
    cluded
    -0.64
    marginHorizontal
    -0.63
    pears
    -0.63
    POSITIVE LOGITS
    +#+#
    1.01
     Efq
    0.85
     resourceCulture
    0.83
    IntoConstraints
    0.82
     HasFactory
    0.79
     houſe
    0.78
     تضيفلها
    0.76
     ſche
    0.75
     myſelf
    0.75
     Monfieur
    0.74
    Act Density 0.375%

    No Known Activations