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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to the concept of a singular important element or idea

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "one" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ories
    -0.71
    iolet
    -0.70
    avascript
    -0.70
    ocks
    -0.67
    ICO
    -0.66
    illus
    -0.65
    ypes
    -0.65
    ierrez
    -0.64
    mson
    -0.64
    azard
    -0.63
    POSITIVE LOGITS
     exception
    0.99
     thing
    0.97
     hundred
    0.90
     sided
    0.86
     eyed
    0.83
     remaining
    0.80
     Hundred
    0.78
     drawback
    0.75
     thousand
    0.75
     caveat
    0.72
    Act Density 0.050%

    No Known Activations