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

    Neuronpedia

    INDEX
    Explanations

    speculation and consequences

    np_max-act · gemini-2.0-flash

    discussions about feelings of inadequacy and impostor syndrome in academic or professional settings.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is primarily detecting conditional or speculative auxiliary verbs (e.g., “would”) in a sentence.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Candidates
    -0.07
    /videos
    -0.07
    ип
    -0.06
     Avust
    -0.06
    proj
    -0.06
     boilers
    -0.06
     Desmond
    -0.06
     ÜNİVERSİTESİ
    -0.06
     GOODMAN
    -0.06
    Carlos
    -0.06
    POSITIVE LOGITS
    件
    0.07
    	 
↵
    0.07
    (gray
    0.06
    _para
    0.06
     fib
    0.06
     [],
↵
    0.06
    SERVICE
    0.06
     SUR
    0.06
    oenix
    0.06
     fingerprints
    0.06
    Act Density 0.088%

    No Known Activations