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

    Neuronpedia

    INDEX
    Explanations

    isolated sequences of uppercase letters separated by non-letter characters

    oai_token-act-pair · gpt-3.5-turbo

    repetition of certain punctuation or formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     incent
    -0.66
    hement
    -0.65
    obbies
    -0.62
    terday
    -0.62
     destro
    -0.61
     subpoena
    -0.59
     disadvant
    -0.59
    ardless
    -0.58
    ury
    -0.58
     diving
    -0.58
    POSITIVE LOGITS
    ccording
    0.93
    ³³³³³³³³³³³³³³³³
    0.93
    ³³³³
    0.93
    ³³³
    0.90
    ³³³³³³³³
    0.88
    Posted
    0.85
    Associated
    0.84
     largeDownload
    0.82
    Trivia
    0.81
    Copyright
    0.81
    Act Density 0.071%

    No Known Activations