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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "ein" (meaning "a" or "one" in German)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dess
    -0.17
    ille
    -0.17
    ks
    -0.16
    a
    -0.15
    jev
    -0.15
    kov
    -0.15
    uby
    -0.14
    gal
    -0.14
    sy
    -0.14
    sq
    -0.14
    POSITIVE LOGITS
    zel
    0.27
    wo
    0.23
    igen
    0.23
    heit
    0.23
    zelf
    0.22
    heiten
    0.22
    iges
    0.21
    heits
    0.20
    ige
    0.20
    zig
    0.19
    Act Density 0.007%

    No Known Activations