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

    Neuronpedia

    INDEX
    Explanations

    symbols or characters that represent non-traditional or special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Levin
    -0.15
     cult
    -0.14
    Âģ
    -0.14
     âĢ¯
    -0.14
    ãĤ¿ãĥ¼
    -0.14
     imagined
    -0.14
    .btnClose
    -0.14
    à¹IJ
    -0.14
     obs
    -0.13
     fort
    -0.13
    POSITIVE LOGITS
    µ
    0.18
     ±
    0.17
     mu
    0.16
    ä
    0.15
    ±
    0.15
    é
    0.15
    _,,
    0.15
    »
    0.14
    _mu
    0.14
    iec
    0.14
    Act Density 0.005%

    No Known Activations