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

    Neuronpedia

    INDEX
    Explanations

    the occurrences of certain German words, particularly based on their context and grammatical usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cheid
    -0.19
    essel
    -0.17
    dorf
    -0.16
    tems
    -0.16
    +xml
    -0.15
    .ManyToMany
    -0.15
    anders
    -0.15
    bble
    -0.15
     Mellon
    -0.14
     Hun
    -0.14
    POSITIVE LOGITS
    erk
    0.27
    pass
    0.22
    fang
    0.21
    ony
    0.19
    ker
    0.18
    sat
    0.17
    bot
    0.17
    sett
    0.17
    hang
    0.17
     Bord
    0.17
    Act Density 0.008%

    No Known Activations