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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "Well,"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "well" as a discourse marker

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    İĭ
    -0.70
    FN
    -0.67
    mage
    -0.63
    untarily
    -0.62
    =~=~
    -0.60
     neighb
    -0.60
    coni
    -0.60
    emo
    -0.60
    sk
    -0.59
    atile
    -0.59
    POSITIVE LOGITS
     yeah
    1.05
     uh
    0.94
     guess
    0.92
     maybe
    0.90
     fortunately
    0.87
     congr
    0.87
     luckily
    0.87
     congratulations
    0.84
     yes
    0.84
     sorry
    0.83
    Act Density 0.047%

    No Known Activations