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

    Neuronpedia

    INDEX
    Explanations

    words related to certainty or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    the word "obviously" and its significance in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ictions
    -0.72
    lake
    -0.72
    board
    -0.69
    hi
    -0.68
    tein
    -0.67
    bury
    -0.66
    ingers
    -0.65
    nan
    -0.65
    lite
    -0.65
    lets
    -0.64
    POSITIVE LOGITS
     proble
    0.80
    icably
    0.79
     obviously
    0.77
     identifiable
    0.72
     defic
    0.69
    SPA
    0.67
    س
    0.66
     incomp
    0.65
    ãĥ´ãĤ¡
    0.65
     appre
    0.65
    Act Density 0.008%

    No Known Activations