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

    Neuronpedia

    INDEX
    Explanations

    phrases related to perceptions and social narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èlement
    -0.68
    OOTDTY
    -0.66
     devrez
    -0.62
     NSObject
    -0.61
    Revenir
    -0.60
     pter
    -0.60
    ברס
    -0.60
    ніципа
    -0.59
    czuk
    -0.59
    IRST
    -0.59
    POSITIVE LOGITS
     perception
    1.01
     perceptions
    0.99
     impression
    0.92
     Perceptions
    0.85
     Perception
    0.80
    Perception
    0.75
    印象
    0.75
    perception
    0.74
     impressions
    0.73
     stereotypes
    0.73
    Act Density 0.242%

    No Known Activations