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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "use" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amt
    -0.16
    amate
    -0.15
    etto
    -0.15
    abar
    -0.15
    ipop
    -0.14
    ier
    -0.13
    ovu
    -0.13
    478
    -0.13
    /u
    -0.13
    ãĤ«ãĥ¼
    -0.13
    POSITIVE LOGITS
    fully
    0.17
    geh
    0.15
    ulner
    0.14
    éĢĶ
    0.14
     divide
    0.14
    394
    0.14
    åĪĨ
    0.14
    544
    0.14
    ombok
    0.13
    è¯Ĭ
    0.13
    Act Density 0.033%

    No Known Activations