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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awa
    -0.17
    lem
    -0.14
     py
    -0.14
    lag
    -0.14
    ent
    -0.14
    ention
    -0.14
    odo
    -0.14
     sym
    -0.14
    JI
    -0.14
    consts
    -0.14
    POSITIVE LOGITS
    zdy
    0.17
    âĦĸâĦĸ
    0.16
    aliz
    0.15
    jeme
    0.15
    zych
    0.15
     kulak
    0.15
    zioni
    0.15
    Ð®ÐĽ
    0.14
    anon
    0.14
    edia
    0.14
    Act Density 0.091%

    No Known Activations