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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and periods indicating completion or continuation of thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ero
    -0.15
    erra
    -0.14
    shake
    -0.14
    (Of
    -0.14
     merits
    -0.14
     mission
    -0.14
     Malk
    -0.13
    chl
    -0.13
    ä¹Ļ
    -0.13
    .getAs
    -0.13
    POSITIVE LOGITS
    .abstract
    0.17
    uder
    0.17
    abus
    0.17
    853
    0.15
    929
    0.15
    alach
    0.15
     Wire
    0.15
    wire
    0.15
    UNCT
    0.14
    оза
    0.14
    Act Density 0.002%

    No Known Activations