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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numerical references and data structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endregion
    -0.16
     LAST
    -0.16
    olang
    -0.15
    .Last
    -0.15
    late
    -0.15
     ultimo
    -0.15
     Last
    -0.14
     late
    -0.14
    ixel
    -0.14
    chten
    -0.14
    POSITIVE LOGITS
     first
    0.59
    first
    0.48
    第ä¸Ģ
    0.45
     첫
    0.43
     pierws
    0.43
    .first
    0.40
     eerste
    0.40
     erste
    0.40
    _first
    0.39
     prvnÃŃ
    0.39
    Act Density 0.288%

    No Known Activations