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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "le" and its forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    duit
    -0.16
    osi
    -0.15
     Demp
    -0.15
    acket
    -0.15
    pery
    -0.15
    anke
    -0.14
     Diss
    -0.14
    emale
    -0.14
    allback
    -0.14
    apesh
    -0.14
    POSITIVE LOGITS
    istung
    0.22
    hr
    0.22
    ist
    0.21
    bens
    0.20
    icht
    0.20
    hra
    0.19
    hn
    0.19
    erra
    0.19
    ute
    0.18
    hrs
    0.18
    Act Density 0.007%

    No Known Activations