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

    Neuronpedia

    INDEX
    Explanations

    references to offices and their locations

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

    offices and their locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cuándo
    -0.53
    dinosaur
    -0.49
     German
    -0.48
     stubborn
    -0.47
     spiritual
    -0.47
     Gian
    -0.46
    diabetes
    -0.46
    Gian
    -0.46
    neutron
    -0.45
    Desired
    -0.45
    POSITIVE LOGITS
     offices
    1.80
     Offices
    1.79
     OFFICES
    1.51
    offices
    1.48
     office
    1.38
    office
    1.30
    Office
    1.25
     Office
    1.24
     OFFICE
    1.23
     oficinas
    1.18
    Act Density 0.010%

    No Known Activations