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

    Neuronpedia

    INDEX
    Explanations

    references to various categories or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     évêque
    -0.73
     Geophysics
    -0.72
     adjourn
    -0.71
     tremors
    -0.67
     grossesse
    -0.67
     hypotension
    -0.66
     mencu
    -0.66
     estabiliz
    -0.65
     femur
    -0.65
     amortization
    -0.64
    POSITIVE LOGITS
     types
    1.05
     type
    1.02
     getType
    0.95
     Type
    0.92
     kind
    0.90
     kinds
    0.89
     TYPE
    0.85
     Types
    0.83
     tipo
    0.82
     tipos
    0.79
    Act Density 0.204%

    No Known Activations