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

    Neuronpedia

    INDEX
    Explanations

    mentions of locations where people live

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "live in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    casters
    -0.84
    catentry
    -0.78
    killed
    -0.78
    offer
    -0.77
    IJ
    -0.75
    ¿½
    -0.73
     culprit
    -0.70
    STAR
    -0.69
     undone
    -0.67
    acter
    -0.65
    POSITIVE LOGITS
     accordance
    1.13
    ordinate
    1.02
    animate
    0.93
     lieu
    0.89
     vitro
    0.88
     spite
    0.87
     Denmark
    0.85
     France
    0.85
     vain
    0.83
     exile
    0.80
    Act Density 0.141%

    No Known Activations