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

    Neuronpedia

    INDEX
    Explanations

    rhetorical questions and expressions that provoke thought or challenge assumptions

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

    why ask questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.47
    Diweddarwch
    -0.47
    GHIJKLM
    -0.45
    RefNanny
    -0.44
     jsPsych
    -0.42
    NUMX
    -0.41
     GIPHY
    -0.41
     насељу
    -0.41
     ब्रेकडाउन
    -0.41
     dataSet
    -0.39
    POSITIVE LOGITS
    Зачем
    0.44
     Зачем
    0.43
     mediocrity
    0.42
     Polak
    0.41
     ventaja
    0.41
    Shouldn
    0.41
    raba
    0.41
     înc
    0.40
    Neden
    0.40
     mengal
    0.40
    Act Density 0.013%

    No Known Activations