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

    Neuronpedia

    INDEX
    Explanations

    instances of the French article "l'" and related contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.17
    a
    -0.17
    ’s
    -0.16
    åľ°æĸ¹
    -0.16
    auss
    -0.16
    /OR
    -0.15
    shaw
    -0.15
    anna
    -0.15
    ’t
    -0.14
    zik
    -0.14
    POSITIVE LOGITS
     "
    0.16
    /'
    0.14
    -'
    0.14
    agen
    0.14
    _undo
    0.14
    -"
    0.14
    ullivan
    0.14
    ezier
    0.14
    gerald
    0.14
    ence
    0.13
    Act Density 0.027%

    No Known Activations