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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to societal structures and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    			↵
    -0.22
    OrCreate
    -0.19
    coming
    -0.19
    			↵			↵
    -0.19
                ↵            ↵
    -0.18
    ialis
    -0.18
    asio
    -0.17
    ookies
    -0.17
    UDA
    -0.17
    sv
    -0.17
    POSITIVE LOGITS
    wealth
    0.21
    ifornia
    0.19
    stalk
    0.17
    pillar
    0.17
    =C
    0.15
    icut
    0.15
    à¥Ģन
    0.15
    -cut
    0.15
    agne
    0.15
    ulative
    0.15
    Act Density 2.937%

    No Known Activations