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

    Neuronpedia

    INDEX
    Explanations

    occurrences of rhetorical questions and interruptions in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ksen
    -0.17
    isse
    -0.15
    845
    -0.14
     Bis
    -0.14
     holy
    -0.14
     Trouble
    -0.14
    elin
    -0.14
    ç¼
    -0.13
    583
    -0.13
    815
    -0.13
    POSITIVE LOGITS
     Erotische
    0.16
    precated
    0.15
    premium
    0.15
    apos
    0.15
    eway
    0.14
    irts
    0.14
    usta
    0.14
    âĢIJâĢIJ
    0.14
    ÑħодиÑĤÑĮ
    0.14
    oger
    0.14
    Act Density 0.002%

    No Known Activations