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

    Neuronpedia

    INDEX
    Explanations

    quotations and reported speech

    oai_token-act-pair · gpt-3.5-turbo

    strong emotional or evaluative statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arthed
    -0.47
     Fey
    -0.45
    aired
    -0.44
     "...
    -0.43
    ãĤ´ãĥ³
    -0.43
    byss
    -0.42
    surprisingly
    -0.42
    +.
    -0.42
    utterstock
    -0.41
     Weeks
    -0.41
    POSITIVE LOGITS
     âĢ¦"
    0.95
    %"
    0.93
     [
    0.90
    .")
    0.89
     ..."
    0.88
    ,"
    0.87
    ),"
    0.85
    ,'"
    0.83
    )"
    0.81
    )."
    0.79
    Act Density 1.933%

    No Known Activations