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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mental disorders

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various mental disorders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stanbul
    -0.80
    baugh
    -0.71
    mination
    -0.70
     suspic
    -0.70
    riel
    -0.68
    raltar
    -0.68
    Sources
    -0.67
    sheet
    -0.66
     snipp
    -0.65
    fired
    -0.64
    POSITIVE LOGITS
     diagnoses
    1.12
     diagnosis
    1.05
     disorders
    1.03
     symptoms
    0.99
     disorder
    0.99
     Symptoms
    0.98
     spectrum
    0.95
     Disorders
    0.92
     symptom
    0.92
     worsen
    0.91
    Act Density 0.056%

    No Known Activations