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

    Neuronpedia

    INDEX
    Explanations

    words related to names or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aliz
    -0.15
    cia
    -0.15
    į°
    -0.15
    i
    -0.15
    gor
    -0.14
    à¥Ģà¤Łà¤°
    -0.14
    ouser
    -0.14
    appen
    -0.14
    QA
    -0.14
    ican
    -0.13
    POSITIVE LOGITS
    othy
    0.20
    icina
    0.17
    poster
    0.17
    yasal
    0.16
    ãģķãĤī
    0.15
    aginator
    0.15
    ë²Į
    0.15
    ÑĥÑīеÑģÑĤв
    0.15
    pressions
    0.15
    posta
    0.14
    Act Density 0.048%

    No Known Activations