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

    Neuronpedia

    INDEX
    Explanations

    references to computer programming concepts, specifically related to runtime operations

    oai_token-act-pair · gpt-3.5-turbo

    the end of the document or indication of completion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    naires
    -0.90
    ging
    -0.86
    iosity
    -0.84
    istan
    -0.82
    essee
    -0.81
    umin
    -0.78
    ifying
    -0.78
    iday
    -0.77
    gments
    -0.76
    itude
    -0.76
    POSITIVE LOGITS
    âĸijâĸij
    0.69
     ILCS
    0.66
    lihood
    0.66
    lean
    0.65
     Leone
    0.65
    VEL
    0.64
    metry
    0.64
     Sierra
    0.62
    LOS
    0.61
    phant
    0.59
    Act Density 0.096%

    No Known Activations