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

    Neuronpedia

    INDEX
    Explanations

    punctuation or pauses in text, particularly commas

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

    comma and conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.35
    c
    -0.29
    SM
    -0.27
     nommée
    -0.26
     via
    -0.26
    A
    -0.26
    C
    -0.26
     denominado
    -0.25
     desired
    -0.24
     '
    -0.23
    POSITIVE LOGITS
    <unused8>
    1.03
    [@BOS@]
    1.03
    <unused43>
    1.03
    <unused74>
    1.03
    <unused52>
    1.03
    <unused42>
    1.02
    <unused47>
    1.02
    <unused41>
    1.02
    <unused14>
    1.02
    <unused16>
    1.02
    Act Density 0.081%

    No Known Activations