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

    Neuronpedia

    INDEX
    Explanations

    the word "actually" across various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "actually" used to emphasize statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icipated
    -0.69
    cit
    -0.66
    stakes
    -0.66
     canopy
    -0.63
     Crusader
    -0.61
    bye
    -0.61
    akh
    -0.61
    ifully
    -0.60
     lungs
    -0.60
    detail
    -0.58
    POSITIVE LOGITS
     quite
    0.88
    netflix
    0.81
    ional
    0.77
     managed
    0.69
    ãĥĩãĤ£
    0.68
     kinda
    0.67
    æĺ
    0.66
    Ñĭ
    0.65
     REALLY
    0.65
     externalToEVAOnly
    0.64
    Act Density 0.037%

    No Known Activations