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

    Neuronpedia

    INDEX
    Explanations

    sentences that indicate conclusions or summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATRIX
    -0.18
    ihan
    -0.14
    wend
    -0.14
    žÃŃ
    -0.14
    etto
    -0.14
    .updateDynamic
    -0.14
    наÑĩе
    -0.14
     cán
    -0.14
    atrix
    -0.14
    han
    -0.14
    POSITIVE LOGITS
     among
    0.46
     example
    0.41
     examples
    0.41
     Among
    0.40
     amongst
    0.39
    among
    0.37
     Examples
    0.37
    Among
    0.35
     напÑĢимеÑĢ
    0.35
    ä¾ĭå¦Ĥ
    0.33
    Act Density 0.377%

    No Known Activations