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

    Neuronpedia

    INDEX
    Explanations

    phrases related to immigration and movement between different locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" referring to movement or transition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forcing
    -0.66
    ially
    -0.66
    Directory
    -0.65
    ŃĶ
    -0.65
    ãĤ°
    -0.65
    locking
    -0.64
    icularly
    -0.64
    tun
    -0.64
    acious
    -0.63
    menu
    -0.61
    POSITIVE LOGITS
     England
    1.12
     America
    1.11
     reside
    1.09
     join
    1.09
     Australia
    1.06
     Spain
    1.05
     Canada
    1.03
     Denmark
    1.03
     Sweden
    1.02
     Italy
    1.01
    Act Density 0.135%

    No Known Activations