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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the absence of something or negative assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iets
    -0.17
    ãĤ´ãĥª
    -0.16
     itself
    -0.16
    ectors
    -0.16
    elman
    -0.15
    дÑĢеÑģ
    -0.15
    otypes
    -0.15
    igi
    -0.14
    yles
    -0.14
    284
    -0.14
    POSITIVE LOGITS
     two
    0.16
    Compile
    0.15
     three
    0.14
     Katz
    0.14
     rules
    0.14
     few
    0.14
    責
    0.14
    iyan
    0.13
     Laws
    0.13
     Rules
    0.13
    Act Density 0.377%

    No Known Activations