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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "you" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dna
    -0.17
    725
    -0.15
    ãĤ¿ãĥ«
    -0.15
    ottage
    -0.15
    ãģŁãĤĬ
    -0.15
    ughters
    -0.15
    730
    -0.14
    ninger
    -0.14
    ÑĢоÑĩ
    -0.14
     Manor
    -0.14
    POSITIVE LOGITS
     Mori
    0.17
    axter
    0.17
     Gund
    0.16
    ̣
    0.16
    vertise
    0.16
    /******/
    0.15
    Äı
    0.15
     ži
    0.15
    sd
    0.15
    oss
    0.15
    Act Density 0.040%

    No Known Activations