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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and thankfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eca
    -0.15
     ëĤ
    -0.15
    ÏģÏį
    -0.15
    796
    -0.15
     ê´Ģíķľ
    -0.15
    é¼ĵ
    -0.14
    StartPosition
    -0.14
    orce
    -0.14
    ал
    -0.14
    stoff
    -0.14
    POSITIVE LOGITS
    fulness
    0.21
    ness
    0.21
    nes
    0.20
    sgiving
    0.20
    ful
    0.19
    lest
    0.18
    ilty
    0.17
    izer
    0.16
    fully
    0.16
    ulet
    0.16
    Act Density 0.024%

    No Known Activations