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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and regulatory discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    átka
    -0.16
    ÐŀÐĴ
    -0.16
    ayah
    -0.15
     Xiao
    -0.15
    911
    -0.14
    uky
    -0.14
    aille
    -0.14
    -basket
    -0.14
    TestFixture
    -0.14
     Regents
    -0.14
    POSITIVE LOGITS
     Union
    0.23
    Union
    0.19
     Prime
    0.19
     union
    0.19
    İ
    0.18
     sources
    0.18
     till
    0.17
     apart
    0.17
     Chief
    0.17
    Prime
    0.16
    Act Density 0.117%

    No Known Activations