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

    Neuronpedia

    INDEX
    Explanations

    specific entities or terms related to roles, actions, and compliance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ariat
    -0.15
    895
    -0.15
    659
    -0.15
    mark
    -0.15
    329
    -0.15
    umbn
    -0.14
    realm
    -0.14
    awn
    -0.14
    961
    -0.14
     petroleum
    -0.13
    POSITIVE LOGITS
    _initialize
    0.17
    tık
    0.15
    лÑĥб
    0.14
    ÙĨس
    0.14
     bÄĻd
    0.14
    apon
    0.14
    ¥
    0.14
    teki
    0.14
    主任
    0.14
     Rub
    0.13
    Act Density 0.032%

    No Known Activations