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

    Neuronpedia

    INDEX
    Explanations

    references to countries and governmental bodies, particularly the U.S

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the U.S. government and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.86
     bending
    -0.70
    bet
    -0.69
    oba
    -0.64
     horizont
    -0.62
     bunny
    -0.62
     aber
    -0.62
     mosqu
    -0.60
    bda
    -0.59
    ahime
    -0.59
    POSITIVE LOGITS
    S
    1.30
    Va
    0.93
    Y
    0.91
    K
    0.86
    ¥
    0.86
    N
    0.84
    KS
    0.84
    Ds
    0.83
    ª
    0.83
    American
    0.80
    Act Density 0.049%

    No Known Activations