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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    naments
    -0.19
    ãģ¾ãģ¾
    -0.15
    à¹īà¸ĩ
    -0.14
    aneous
    -0.14
    ango
    -0.14
    anlı
    -0.14
    ander
    -0.14
    sav
    -0.14
    antro
    -0.14
    VERRIDE
    -0.14
    POSITIVE LOGITS
    nowled
    0.20
    ingly
    0.19
    sgiving
    0.17
    soever
    0.16
    yntax
    0.15
    fulness
    0.15
    fully
    0.15
    roup
    0.14
    round
    0.14
    allery
    0.14
    Act Density 0.033%

    No Known Activations