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

    Neuronpedia

    INDEX
    Explanations

    phrases related to important concepts and principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     own
    -0.19
    ucz
    -0.17
    SEL
    -0.17
    atcher
    -0.16
     ourselves
    -0.16
    esti
    -0.15
    TestingModule
    -0.15
    self
    -0.15
     Own
    -0.14
    æĥ
    -0.14
    POSITIVE LOGITS
     seus
    0.20
     seu
    0.18
     suo
    0.16
     suas
    0.16
     reins
    0.15
     his
    0.15
    isko
    0.15
     Sne
    0.14
     sua
    0.14
    aternity
    0.14
    Act Density 0.325%

    No Known Activations