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

    Neuronpedia

    INDEX
    Explanations

    mentions of emigration, immigration, and related terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    lihood
    -0.67
    DragonMagazine
    -0.55
     Elves
    -0.54
     Kavanaugh
    -0.52
     Physics
    -0.52
     Lane
    -0.52
     Scientific
    -0.52
    IGH
    -0.52
     Desire
    -0.51
     Strauss
    -0.51
    POSITIVE LOGITS
    igration
    0.88
    igrated
    0.86
    inently
    0.85
    igrants
    0.83
    bers
    0.83
    ailable
    0.81
    igrant
    0.80
    pher
    0.80
    ulators
    0.80
    ittance
    0.80
    Act Density 5.457%

    No Known Activations