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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or lack of clarity

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

    special characters and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſever
    -0.49
     myſelf
    -0.48
     themſelves
    -0.47
     tranſ
    -0.46
     Inſ
    -0.46
    +#+#
    -0.45
     ſta
    -0.45
     diſt
    -0.44
     ſtate
    -0.44
     leſs
    -0.44
    POSITIVE LOGITS
    ครับ
    1.49
    ค่ะ
    1.26
     ครับ
    1.15
    นะครับ
    0.90
    คะ
    0.85
     ạ
    0.70
    นะคะ
    0.59
    paramMap
    0.59
    CloseOperation
    0.55
     للمعارف
    0.55
    Act Density 0.003%

    No Known Activations