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

    Neuronpedia

    INDEX
    Explanations

    parentheses used in the text

    oai_token-act-pair · gpt-3.5-turbo

    opening parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tears
    -0.94
     starters
    -0.70
     Bees
    -0.69
     highlights
    -0.68
     oranges
    -0.68
     counselors
    -0.65
     windows
    -0.64
     bows
    -0.64
     tamp
    -0.63
     Secrets
    -0.63
    POSITIVE LOGITS
    albeit
    1.58
    non
    1.35
    sic
    1.34
    yet
    1.31
    possibly
    1.10
    rather
    1.07
    but
    1.05
    literally
    1.03
    anti
    1.03
    sometimes
    1.02
    Act Density 0.075%

    No Known Activations