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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icious
    -0.16
    ´
    -0.16
    mente
    -0.15
    utos
    -0.15
    WD
    -0.14
    module
    -0.13
    ced
    -0.13
    heck
    -0.13
    sed
    -0.13
    pa
    -0.13
    POSITIVE LOGITS
    omorphic
    0.17
    aft
    0.16
    tah
    0.15
    WindowState
    0.15
    ÙħارÛĮ
    0.14
    isnan
    0.14
    æĪ²
    0.14
    abyrinth
    0.14
    eview
    0.13
    arger
    0.13
    Act Density 0.371%

    No Known Activations