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

    Neuronpedia

    INDEX
    Explanations

    repeated occurrences of the character 'a' in close proximity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]--;
    -1.03
    )++;
    -0.96
    Portail
    -0.93
    Datuak
    -0.92
     يتيمه
    -0.90
    AutoresizingMask
    -0.89
    Cuánt
    -0.87
    ]++;
    -0.84
    BibitemShut
    -0.84
    ffl
    -0.84
    POSITIVE LOGITS
    a
    3.62
    A
    1.68
    aA
    1.30
    e
    1.20
    ا
    1.13
    aR
    1.12
    а
    1.08
    aa
    1.06
    o
    1.02
    aS
    0.99
    Act Density 0.231%

    No Known Activations