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

    Neuronpedia

    INDEX
    Explanations

    care

    np_max-act · gemini-2.0-flash

    terms and language related to healthcare laws and policies.

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

    The neuron specifically responds to occurrences of the phrase “health care” (i.e. the bigram representing the concept of healthcare).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _ix
    -0.08
     Sam
    -0.06
    |int
    -0.06
     gridSize
    -0.06
     shown
    -0.06
    i
    -0.06
     synonym
    -0.06
     Stevens
    -0.06
    26
    -0.06
    ￣￣￣￣￣￣￣￣
    -0.06
    POSITIVE LOGITS
     healthcare
    0.15
     Healthcare
    0.11
    vc
    0.08
    fak
    0.07
    holding
    0.07
    FC
    0.07
    footer
    0.07
    Towards
    0.07
    Alter
    0.07
     페
    0.07
    Act Density 0.008%

    No Known Activations