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

    Neuronpedia

    INDEX
    Explanations

    instances where the phrase "I would say" is used

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinion or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Witches
    -0.65
    eatured
    -0.65
     Printing
    -0.62
     Seah
    -0.61
    adobe
    -0.60
     Built
    -0.60
    =~=~
    -0.60
    velength
    -0.60
     Painter
    -0.59
     Written
    -0.59
    POSITIVE LOGITS
     goodbye
    0.89
    xus
    0.74
     anecd
    0.66
     unequivocally
    0.64
    ings
    0.63
     definitively
    0.62
    bolt
    0.62
    INGS
    0.61
    aco
    0.59
    lihood
    0.59
    Act Density 0.042%

    No Known Activations