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

    Neuronpedia

    INDEX
    Explanations

    instances of emphasis or qualifiers in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pee
    -0.14
    iere
    -0.14
    illance
    -0.14
    DED
    -0.13
    awy
    -0.13
    ASIC
    -0.13
    odal
    -0.13
     Wir
    -0.13
    igue
    -0.13
    ertools
    -0.13
    POSITIVE LOGITS
     being
    0.17
     along
    0.17
     through
    0.16
     trick
    0.16
     having
    0.15
     in
    0.15
    arrison
    0.15
     reverse
    0.15
     had
    0.15
     flush
    0.15
    Act Density 0.105%

    No Known Activations