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

    Neuronpedia

    INDEX
    Explanations

    phrases and questions related to official requests and inquiries involving authority figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iddle
    -0.16
     Raum
    -0.15
    emarks
    -0.15
     Nej
    -0.14
    utos
    -0.14
    ONO
    -0.14
    67
    -0.14
     Scar
    -0.13
    rar
    -0.13
    914
    -0.13
    POSITIVE LOGITS
    plorer
    0.18
    byt
    0.15
    Drv
    0.14
    Ïģον
    0.14
    /manage
    0.14
     Quad
    0.14
    Owned
    0.14
    aggi
    0.14
    /Typography
    0.14
    лÑĸÑĤ
    0.14
    Act Density 0.001%

    No Known Activations