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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "knew" indicating prior knowledge or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azzi
    -0.18
    alley
    -0.18
    ussia
    -0.18
    olina
    -0.17
    ÅĻÃŃ
    -0.16
    oucher
    -0.15
     hang
    -0.15
    uss
    -0.15
    aiser
    -0.15
     hung
    -0.15
    POSITIVE LOGITS
    lify
    0.16
    IRECTION
    0.15
     pornografia
    0.14
     пÑĢеÑģ
    0.13
    ymm
    0.13
    mnop
    0.13
     env
    0.13
    REAM
    0.13
    fov
    0.13
    tables
    0.13
    Act Density 0.008%

    No Known Activations