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

    Neuronpedia

    INDEX
    Explanations

    words expressing certainty or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    the word "definitely" and its variations, indicating strong affirmation or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roups
    -0.85
    ently
    -0.84
    sembly
    -0.84
     Mour
    -0.77
    soever
    -0.70
    acity
    -0.69
    aciously
    -0.69
    Reviewer
    -0.68
    entary
    -0.67
    ELD
    -0.67
    POSITIVE LOGITS
     recommend
    0.71
     qualifies
    0.69
     Vader
    0.68
     gonna
    0.67
     NS
    0.66
     wanna
    0.65
     underest
    0.65
     impacted
    0.62
     correlated
    0.62
     underrated
    0.62
    Act Density 0.035%

    No Known Activations