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

    Neuronpedia

    INDEX
    Explanations

    The neuron selectively activates on interrogative question words (e.g. “What”) at the start of a user’s question.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     الش
    -0.06
    PLATFORM
    -0.06
    -no
    -0.06
    los
    -0.06
    �
    -0.06
    -system
    -0.06
    heads
    -0.06
     Thumb
    -0.06
     polo
    -0.06
     문화
    -0.06
    POSITIVE LOGITS
     سكان
    0.07
     "",↵
    0.07
     injuring
    0.06
     Taken
    0.06
    čka
    0.06
    (sec
    0.06
    _div
    0.06
    '/>↵
    0.06
    (visitor
    0.06
     smrt
    0.06
    Act Density 0.046%

    No Known Activations