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

    Neuronpedia

    INDEX
    Explanations

    countries and geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onom
    -0.75
    olicy
    -0.71
    Redd
    -0.68
    retty
    -0.65
    ecause
    -0.62
    mod
    -0.59
    ãĤ¤
    -0.59
    ãĥĺãĥ©
    -0.59
    *=-
    -0.59
    PN
    -0.58
    POSITIVE LOGITS
     collided
    1.02
     emerges
    0.99
     emerged
    0.95
     surfaced
    0.94
     converge
    0.92
     appeared
    0.92
     conver
    0.88
     arrived
    0.88
     entered
    0.86
     perished
    0.85
    Act Density 0.571%

    No Known Activations