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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "are" in relation to descriptions of organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ederland
    -0.17
    erguson
    -0.15
     Roland
    -0.15
    emean
    -0.14
     unreal
    -0.14
     port
    -0.14
    ep
    -0.14
     gast
    -0.14
    endor
    -0.13
    ystone
    -0.13
    POSITIVE LOGITS
    anches
    0.14
    odo
    0.14
    hort
    0.14
     Nay
    0.14
    íıī
    0.14
    atts
    0.14
    ë³
    0.14
    hlen
    0.14
    ãĥ¼ãĥª
    0.14
    resco
    0.13
    Act Density 0.000%

    No Known Activations