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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    surprisingly
    -0.45
    ãĤ´ãĥ³
    -0.39
    byss
    -0.36
    aired
    -0.36
    agonists
    -0.35
    translation
    -0.35
    arnaev
    -0.35
    anwhile
    -0.34
    rawled
    -0.34
    utterstock
    -0.34
    POSITIVE LOGITS
     ..."
    1.06
     âĢ¦"
    1.02
    .")
    0.89
    %"
    0.88
    ,'"
    0.87
    ,"
    0.86
    ),"
    0.85
    )."
    0.84
    )"
    0.82
     [
    0.82
    Act Density 17.971%

    No Known Activations