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

    Neuronpedia

    INDEX
    Explanations

    references to faces in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tz
    -0.17
    urm
    -0.16
    isha
    -0.16
    ered
    -0.15
     Arm
    -0.15
     Emit
    -0.15
    arsi
    -0.14
    огод
    -0.14
     Anglo
    -0.14
    ubits
    -0.14
    POSITIVE LOGITS
    adge
    0.18
    lian
    0.15
    mpar
    0.14
    /ion
    0.14
    -headed
    0.14
    .variant
    0.14
    zik
    0.13
    è³¢
    0.13
    鬼
    0.13
    adan
    0.13
    Act Density 0.004%

    No Known Activations