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

    Neuronpedia

    INDEX
    Explanations

    interrogative words and phrases related to questioning or clarification

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

    relative clauses / which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.71
    setVerticalGroup
    -0.61
     للمعارف
    -0.60
    ########.
    -0.59
    Geplaatst
    -0.58
    +#+
    -0.56
     jScrollPane
    -0.56
    onViewCreated
    -0.53
     Perſ
    -0.53
    icola
    -0.52
    POSITIVE LOGITS
     vilket
    0.65
     hvilket
    0.57
     which
    0.56
    Which
    0.50
     Which
    0.49
     což
    0.49
    which
    0.48
    ซึ่ง
    0.48
     οποίο
    0.48
     WHICH
    0.47
    Act Density 0.013%

    No Known Activations