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

    Neuronpedia

    INDEX
    Explanations

    function words that indicate connections or relationships in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullan
    -0.19
     Sole
    -0.15
    ith
    -0.15
     éĸ
    -0.15
     apr
    -0.14
     sole
    -0.14
     Strip
    -0.14
     رÙħ
    -0.14
     Ley
    -0.14
    ail
    -0.14
    POSITIVE LOGITS
    otte
    0.17
    _IE
    0.16
    ystate
    0.16
    /Grid
    0.15
    ÑħодиÑĤÑĮ
    0.15
    INES
    0.15
    éru
    0.15
    ines
    0.15
    ServerError
    0.14
     Speech
    0.14
    Act Density 0.002%

    No Known Activations