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

    Neuronpedia

    INDEX
    Explanations

    expressions of satisfaction or dissatisfaction

    oai_token-act-pair · gpt-3.5-turbo

    expressions of satisfaction and dissatisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gey
    -0.99
    onds
    -0.74
    ozo
    -0.71
    rils
    -0.70
    famous
    -0.68
    udder
    -0.66
    URA
    -0.66
    inger
    -0.65
    Legendary
    -0.65
    ï¸ı
    -0.65
    POSITIVE LOGITS
     outcome
    1.31
     direction
    1.14
     results
    1.10
     handling
    1.07
     performance
    1.05
     lack
    1.03
     outcomes
    1.02
     attitude
    1.01
     behaviour
    1.01
     manner
    1.00
    Act Density 0.281%

    No Known Activations