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

    Neuronpedia

    INDEX
    Explanations

    ratings and emotional reactions to experiences or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.60
     linkovi
    -0.52
     Pneum
    -0.51
     Batter
    -0.50
     TimeUnit
    -0.50
     Roskov
    -0.49
     DataAccess
    -0.48
     Però
    -0.48
     Hyg
    -0.47
     UITextField
    -0.47
    POSITIVE LOGITS
    笑了笑
    0.54
    LikeLiked
    0.53
    [])
    0.53
    看着他
    0.53
    叹了口气
    0.52
    喊道
    0.51
    glio
    0.50
    笑道
    0.49
     Sorensen
    0.49
    摇摇头
    0.48
    Act Density 0.017%

    No Known Activations