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

    Neuronpedia

    INDEX
    Explanations

    contractions where the words "not" and/or "do not" follow a pronoun or auxiliary verb

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions of denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amer
    -0.72
    Site
    -0.70
    ancer
    -0.68
    éĥ
    -0.67
    Intern
    -0.65
    bard
    -0.63
    itiz
    -0.63
    Reviewer
    -0.63
    inav
    -0.63
    interstitial
    -0.63
    POSITIVE LOGITS
     necessarily
    1.26
     bother
    1.11
    icably
    1.06
     exactly
    1.00
    icable
    0.97
    epad
    0.91
     bothering
    0.90
     gonna
    0.89
     quite
    0.88
    urtles
    0.88
    Act Density 0.088%

    No Known Activations