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

    Neuronpedia

    INDEX
    Explanations

    numeric values or indicators of significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rád
    -0.15
    glich
    -0.15
    urette
    -0.15
    ertz
    -0.15
     srv
    -0.15
    uru
    -0.15
    ijk
    -0.15
    iв
    -0.14
    amenti
    -0.14
    bard
    -0.14
    POSITIVE LOGITS
    ayan
    0.15
    td
    0.15
    inu
    0.15
    createClass
    0.15
    thouse
    0.14
    à¸IJาà¸Ļ
    0.14
    atham
    0.14
    èĻ
    0.14
    /he
    0.14
    ó
    0.14
    Act Density 0.002%

    No Known Activations