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

    Neuronpedia

    INDEX
    Explanations

    words related to health and healthcare topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dickerson
    -0.86
     Kitten
    -0.85
     Showroom
    -0.83
    zygous
    -0.81
     Olímp
    -0.78
     Ideology
    -0.77
    dividend
    -0.77
     Bubbles
    -0.77
     Crusaders
    -0.77
     Tuo
    -0.77
    POSITIVE LOGITS
     health
    1.52
     Health
    1.49
    Health
    1.38
    health
    1.31
    HEALTH
    1.15
     Heath
    1.10
     HEALTH
    1.03
    Heath
    0.95
     helse
    0.93
     salud
    0.91
    Act Density 0.066%

    No Known Activations