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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack of significant change or importance

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the phrase "not much"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yne
    -0.75
    kus
    -0.73
    idon
    -0.73
    İĭ
    -0.73
    YES
    -0.70
    iseum
    -0.67
    izoph
    -0.67
    avering
    -0.66
    èĢ
    -0.66
    ortium
    -0.66
    POSITIVE LOGITS
     anymore
    1.10
     consolation
    0.87
     else
    0.84
     avail
    0.78
     fuss
    0.76
     bothered
    0.74
     nor
    0.73
     whatsoever
    0.73
     dime
    0.70
     noticeable
    0.69
    Act Density 0.057%

    No Known Activations