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
    vig
    -0.15
    enha
    -0.15
    engan
    -0.14
    à¹īà¸ĩ
    -0.14
    aho
    -0.14
    engl
    -0.14
    ìłij
    -0.14
     اختÛĮار
    -0.13
     cub
    -0.13
    omnia
    -0.13
    POSITIVE LOGITS
    sgiving
    0.20
    fulness
    0.17
    ilty
    0.16
    nowled
    0.15
    ness
    0.15
    å°¼äºļ
    0.15
    loggedin
    0.14
    ird
    0.14
    istique
    0.14
    ãĥĻãĥ«
    0.14
    Act Density 0.027%

    No Known Activations