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

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical and political events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.34
    PMailer
    -0.62
    quias
    -0.61
     Chwiliwch
    -0.60
    RegressionTest
    -0.59
     beginnetje
    -0.58
    mphony
    -0.57
     esboço
    -0.57
    TagMode
    -0.56
     AllMovie
    -0.56
    POSITIVE LOGITS
     unspeak
    1.40
     shenan
    1.38
     reluct
    1.36
     apprehen
    1.35
     disagre
    1.34
     pamph
    1.31
     impra
    1.31
     sophistic
    1.29
     ineffec
    1.25
     uninten
    1.25
    Act Density 2.554%

    No Known Activations