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

    Neuronpedia

    INDEX
    Explanations

    references to time periods, sequences, or structured steps in processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leans
    -0.15
    第
    -0.15
    ovit
    -0.15
    ogui
    -0.14
    abad
    -0.14
    abal
    -0.14
     Eighth
    -0.14
    ื
    -0.14
    ViewById
    -0.14
    åĥ
    -0.13
    POSITIVE LOGITS
     three
    0.21
     zero
    0.19
     four
    0.19
    (s
    0.19
     #
    0.19
     two
    0.18
     drei
    0.17
     five
    0.17
     seven
    0.17
     six
    0.17
    Act Density 0.193%

    No Known Activations