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

    Neuronpedia

    INDEX
    Explanations

    details and descriptions related to a wide variety of topics, including reasons, sources, locations, and diseases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to complexity and multiple contributing elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enne
    -0.72
    anny
    -0.70
    arde
    -0.63
     411
    -0.61
    atown
    -0.61
    DERR
    -0.61
     Fury
    -0.59
     Redemption
    -0.59
    eka
    -0.57
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.57
    POSITIVE LOGITS
     including
    1.47
     ranging
    1.19
     simultaneously
    1.18
     imaginable
    1.15
     besides
    1.13
     Including
    1.04
    including
    1.04
     includ
    0.95
     vying
    0.95
     concurrently
    0.92
    Act Density 0.409%

    No Known Activations