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

    Neuronpedia

    INDEX
    Explanations

    occurrences of punctuation marks, especially periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    `.` followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.49
     aceptas
    -0.44
     intercamb
    -0.42
    GEBURTS
    -0.42
     myſelf
    -0.41
     revanche
    -0.41
    tagext
    -0.40
     evacuation
    -0.40
    nexpected
    -0.40
     TextInputType
    -0.39
    POSITIVE LOGITS
     .
    1.00
     `.
    0.90
     [.
    0.83
    (".
    0.82
    ('.
    0.82
     (.
    0.80
    =.
    0.74
    ">.
    0.74
    =".
    0.73
     ".
    0.73
    Act Density 0.076%

    No Known Activations