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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns in the text

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

    relative pronoun followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    majánló
    -0.76
     Verſ
    -0.69
    NameInMap
    -0.69
    ロウィン
    -0.69
    Personendaten
    -0.66
     $_(
    -0.65
    <unused74>
    -0.65
    <unused79>
    -0.65
    <unused52>
    -0.65
    <unused17>
    -0.65
    POSITIVE LOGITS
     which
    0.60
    which
    0.56
     whose
    0.45
     with
    0.45
     and
    0.43
     aufzu
    0.43
    whose
    0.43
     jonka
    0.40
    is
    0.39
     vilket
    0.39
    Act Density 0.077%

    No Known Activations