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

    Neuronpedia

    INDEX
    Explanations

    phrases related to recommendations or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    patterns of punctuation and conjunction use in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļéĨĴ
    -0.70
    minster
    -0.68
    AME
    -0.65
    osite
    -0.64
    ioned
    -0.63
    urga
    -0.62
    ELD
    -0.62
    ¬¼
    -0.61
    ophon
    -0.60
    eln
    -0.60
    POSITIVE LOGITS
     congratulations
    1.27
     chances
    1.26
     please
    1.20
     congr
    1.14
     beware
    1.12
    please
    1.08
     you
    1.02
     PLEASE
    0.99
    you
    0.98
     consider
    0.96
    Act Density 0.126%

    No Known Activations