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

    Neuronpedia

    INDEX
    Explanations

    links to further information or related articles

    oai_token-act-pair · gpt-3.5-turbo

    empty tokens or separators in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.67
    oster
    -0.64
     accordingly
    -0.61
    idden
    -0.61
     respectively
    -0.61
     coloured
    -0.59
     presumably
    -0.58
     adjustment
    -0.58
     nerve
    -0.57
     reservation
    -0.57
    POSITIVE LOGITS
    <|endoftext|>
    0.96
    :
    0.93
    :'
    0.92
    !:
    0.89
    agascar
    0.87
     SHARES
    0.85
    :-
    0.80
    htaking
    0.79
     VIDEOS
    0.79
     âĨĴ
    0.78
    Act Density 0.088%

    No Known Activations