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

    Neuronpedia

    INDEX
    Explanations

    occurrences of personal pronouns, particularly "me" and "us."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogui
    -0.17
    ught
    -0.16
    lant
    -0.16
    HashCode
    -0.15
    olet
    -0.15
    æĮĤ
    -0.14
    ifice
    -0.14
    apur
    -0.14
    iset
    -0.14
    âŁ
    -0.14
    POSITIVE LOGITS
    ROC
    0.15
    ãĤ·ãĥ¼
    0.15
    /us
    0.15
    761
    0.14
     Tiffany
    0.13
    220
    0.13
     Morr
    0.13
     nÃło
    0.13
    752
    0.13
     unsus
    0.13
    Act Density 0.023%

    No Known Activations