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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "De" or its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olang
    -0.17
     Erk
    -0.16
    Ø®ÙĪاÙĨ
    -0.16
    loon
    -0.15
    arend
    -0.15
    mi
    -0.15
    ovie
    -0.15
    OrElse
    -0.14
    ebo
    -0.14
    ÙĤÙĩ
    -0.14
    POSITIVE LOGITS
    uts
    0.44
    utsch
    0.33
    utschen
    0.30
    utsche
    0.29
    utch
    0.25
    usch
    0.23
    chant
    0.22
    zent
    0.21
    chants
    0.20
    pon
    0.20
    Act Density 0.005%

    No Known Activations