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

    Neuronpedia

    INDEX
    Explanations

    references to citizenship and citizenship-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.86
    MigrationBuilder
    -0.81
    ברס
    -0.77
     molasses
    -0.69
     Canal
    -0.69
     Magdalene
    -0.68
     Ando
    -0.67
    dafx
    -0.66
     Spinoza
    -0.66
     Elmo
    -0.65
    POSITIVE LOGITS
     Citizen
    1.35
     citizen
    1.35
    Citizen
    1.20
     Citizens
    1.19
     citizens
    1.17
    Citizens
    1.14
    citizen
    1.11
    citizens
    1.04
    IZEN
    0.97
     CIT
    0.96
    Act Density 0.060%

    No Known Activations