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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "an" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cheid
    -0.18
    essel
    -0.18
    appen
    -0.16
     Mellon
    -0.14
    éļľ
    -0.14
    enced
    -0.14
     {*
    -0.14
    Ñħови
    -0.14
    anders
    -0.14
    n
    -0.14
    POSITIVE LOGITS
    erk
    0.25
    fang
    0.22
    pass
    0.21
    ony
    0.21
    onym
    0.19
    ze
    0.18
    sat
    0.17
    hang
    0.17
    son
    0.17
    oni
    0.17
    Act Density 0.007%

    No Known Activations