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

    Neuronpedia

    INDEX
    Explanations

    questions or phrases regarding types or categories of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tong
    -0.16
    覧
    -0.15
    frared
    -0.15
    HX
    -0.15
    ernen
    -0.14
    ductor
    -0.14
     Pod
    -0.14
    trer
    -0.14
    ¬¬
    -0.14
    oug
    -0.13
    POSITIVE LOGITS
    arella
    0.16
    uhn
    0.15
     Exped
    0.15
     Vác
    0.14
    ÑĶв
    0.14
    zia
    0.14
    _unpack
    0.14
    abyrinth
    0.14
    isko
    0.14
    cloth
    0.14
    Act Density 0.024%

    No Known Activations