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

    Neuronpedia

    INDEX
    Explanations

    the word "swear"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "swear" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carnegie
    -0.70
     Progress
    -0.67
    hel
    -0.65
    Ħ
    -0.65
     Reading
    -0.64
     Stage
    -0.63
     Container
    -0.61
    ommod
    -0.61
     Cont
    -0.61
     Mobility
    -0.60
    POSITIVE LOGITS
     swear
    4.24
     swore
    2.40
     swearing
    2.32
     sworn
    1.64
     oath
    1.63
     vow
    1.37
     cursing
    1.23
     cringe
    1.16
     Oath
    1.08
     promise
    1.06
    Act Density 0.010%

    No Known Activations