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

    Neuronpedia

    INDEX
    Explanations

    references to negative health conditions or behavioral traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ill health, ill effects, ill will

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    convite
    -0.65
    ſelf
    -0.62
     Commencez
    -0.60
    vereignty
    -0.59
    fsen
    -0.59
     Autorizaciones
    -0.58
     anhänger
    -0.58
    bibfield
    -0.58
    quatch
    -0.58
     mẽ
    -0.57
    POSITIVE LOGITS
     ill
    1.65
     Ill
    1.16
    Ill
    1.05
     ILL
    0.88
     sick
    0.83
    ill
    0.81
     unwell
    0.78
     illness
    0.73
     Sick
    0.68
    sick
    0.66
    Act Density 0.009%

    No Known Activations