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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue and conversational exchanges among characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     irr
    -0.15
     Wi
    -0.15
    pid
    -0.15
     Don
    -0.15
    Ðĭ
    -0.14
     dam
    -0.14
    assin
    -0.14
    edik
    -0.14
     unless
    -0.14
     don
    -0.14
    POSITIVE LOGITS
    êµ°ìļĶ
    0.19
    ãģªãĤĭ
    0.17
     Ingen
    0.15
    orman
    0.15
    inar
    0.15
    wow
    0.14
    ãĥ¬ãĥ³
    0.14
    è³¢
    0.14
    anship
    0.14
    erville
    0.14
    Act Density 0.213%

    No Known Activations