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

    Neuronpedia

    INDEX
    Explanations

    the presence of questions in the text

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

    literal word Question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.54
    oredCriteria
    -0.44
    mf
    -0.41
     Infórmanos
    -0.40
    mds
    -0.38
    mt
    -0.38
    iki
    -0.38
    <bos>
    -0.38
    mbh
    -0.38
    ft
    -0.37
    POSITIVE LOGITS
    Question
    1.98
     Question
    1.93
    QUESTION
    1.37
     QUESTION
    1.31
    question
    1.22
    uestion
    1.05
     question
    0.99
    GEBURTSDATUM
    0.92
     cuestion
    0.90
     questioning
    0.85
    Act Density 0.007%

    No Known Activations