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

    Neuronpedia

    INDEX
    Explanations

    terms related to policies and action plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iant
    -0.15
    illac
    -0.15
    otta
    -0.14
    x
    -0.14
    ic
    -0.14
    ury
    -0.14
    agi
    -0.14
    zilla
    -0.13
    empt
    -0.13
    by
    -0.13
    POSITIVE LOGITS
    ëŁ
    0.14
    rary
    0.14
    FileVersion
    0.14
    NCY
    0.14
    SPAN
    0.14
     Kaynak
    0.14
    íĴĪ
    0.13
     trú
    0.13
    .scalablytyped
    0.13
    CCCC
    0.13
    Act Density 2.240%

    No Known Activations