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

    Neuronpedia

    INDEX
    Explanations

    specific unicode characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    --
    -0.18
    ['
    -0.18
    ‘
    -0.18
    .--
    -0.17
     '
    -0.16
    -->↵
    -0.16
    `
    -0.16
     ‘
    -0.16
    !--
    -0.16
    ---
    -0.16
    POSITIVE LOGITS
     ÂŃ
    0.61
    ÂŃ
    0.43
    ÂŃt
    0.39
    ÂŃs
    0.38
    âĢħ
    0.36
    ÂŃn
    0.35
    ÂŃing
    0.34
    ÂŃi
    0.32
    ÂŃtion
    0.31
    č
    0.31
    Act Density 0.001%

    No Known Activations