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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to the United States

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McCartney
    -0.67
     Ernst
    -0.63
     vain
    -0.63
    rette
    -0.63
    zzle
    -0.63
     bells
    -0.62
     Rasm
    -0.62
     hazard
    -0.61
    bably
    -0.61
    lets
    -0.61
    POSITIVE LOGITS
    GS
    1.26
    ADA
    1.25
    AAF
    1.24
    MC
    1.16
    $
    1.15
    FK
    1.13
    NI
    1.10
    OC
    1.00
    UAL
    0.99
    ACA
    0.98
    Act Density 0.063%

    No Known Activations