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

    Neuronpedia

    INDEX
    Explanations

    terms related to empires and imperial structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     gat
    -0.72
    LEncoder
    -0.72
    :]:
    -0.71
     Philist
    -0.70
     Dmit
    -0.66
    bolistas
    -0.66
     Thom
    -0.66
    Wit
    -0.65
     Laus
    -0.63
    <!--[
    -0.63
    POSITIVE LOGITS
    Empire
    1.16
     Empire
    1.14
     EMPIRE
    1.13
     empire
    1.04
     empires
    1.02
     Empires
    0.99
     Imperio
    0.94
     emperors
    0.93
    empire
    0.89
    empereur
    0.88
    Act Density 0.007%

    No Known Activations