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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash

    The neuron activates on the phrase “I think that,” i.e. expressions of personal opinion.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Yen
    -0.07
    ,No
    -0.07
    ��
    -0.06
     Encore
    -0.06
     Meer
    -0.06
     useMemo
    -0.06
     underwear
    -0.06
    avigate
    -0.06
     creek
    -0.06
    .ov
    -0.06
    POSITIVE LOGITS
     that
    0.10
    that
    0.08
     That
    0.08
     THAT
    0.07
    That
    0.07
    -that
    0.06
     Pirate
    0.06
    Those
    0.06
    кап
    0.06
    cho
    0.06
    Act Density 0.073%

    No Known Activations