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

    Neuronpedia

    INDEX
    Explanations

    repetitive conjunctions and connectors in legal language

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

    and followed by enumeration or continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     even
    -0.56
    甚至
    -0.52
     swat
    -0.48
     Even
    -0.48
    Even
    -0.47
     EVEN
    -0.47
     addirittura
    -0.46
    even
    -0.45
    甚至是
    -0.44
     nawet
    -0.43
    POSITIVE LOGITS
     shall
    0.64
    shall
    0.53
    such
    0.52
     such
    0.51
    AddWithValue
    0.49
     associated
    0.49
     solchen
    0.48
     demás
    0.47
     any
    0.47
     SHALL
    0.47
    Act Density 0.139%

    No Known Activations