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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "or"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dera
    -0.15
    vertise
    -0.15
    edn
    -0.15
    omaly
    -0.14
    enty
    -0.14
    _GP
    -0.14
    klä
    -0.14
    dar
    -0.14
    Const
    -0.13
    esco
    -0.13
    POSITIVE LOGITS
     so
    0.39
     more
    0.28
     maybe
    0.23
     fewer
    0.22
    maybe
    0.20
    so
    0.20
     less
    0.20
    å¦ĤæѤ
    0.20
     lebih
    0.19
    æĽ´å¤ļ
    0.19
    Act Density 0.020%

    No Known Activations