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

    Neuronpedia

    INDEX
    Explanations

    differences or disparities between multiple elements

    oai_token-act-pair · gpt-3.5-turbo

    references to social issues and disparities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Laun
    -0.70
    ãĥ³ãĤ¸
    -0.66
    hands
    -0.62
    printed
    -0.61
    thumbnails
    -0.60
     scra
    -0.58
    noticed
    -0.57
    Fin
    -0.56
    arthed
    -0.56
    was
    -0.56
    POSITIVE LOGITS
     arise
    1.72
     occur
    1.55
     involve
    1.49
     abound
    1.42
     imply
    1.40
     preclude
    1.40
     coincide
    1.39
     vary
    1.39
     exist
    1.39
     relate
    1.38
    Act Density 0.364%

    No Known Activations