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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences indicating the gradual development or progression of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to events and processes that develop over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uana
    -0.73
    unte
    -0.73
    exc
    -0.72
    alty
    -0.71
    iked
    -0.68
    ogun
    -0.67
    audi
    -0.67
     Quit
    -0.66
    uncle
    -0.65
    ofer
    -0.65
    POSITIVE LOGITS
     unfold
    1.25
     unfolding
    1.12
     unfolded
    1.06
     unfolds
    1.04
    hower
    0.78
    borough
    0.73
     tremend
    0.72
    ĸļ
    0.71
     unravel
    0.71
     anew
    0.70
    Act Density 0.034%

    No Known Activations