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

    Neuronpedia

    INDEX
    Explanations

    instances of the character "Ze" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sek
    -0.18
    çĭIJ
    -0.18
    eon
    -0.17
    liers
    -0.17
    é¬
    -0.15
    lier
    -0.15
    ázev
    -0.15
    ATCH
    -0.14
    acc
    -0.14
    se
    -0.14
    POSITIVE LOGITS
    ppelin
    0.31
    alous
    0.24
    itchens
    0.17
    bron
    0.17
    aland
    0.17
    oldt
    0.17
    elon
    0.17
    alley
    0.16
     Ze
    0.16
    igte
    0.15
    Act Density 0.012%

    No Known Activations