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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal or official agreements

    oai_token-act-pair · gpt-3.5-turbo

    mentions of treaties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stocks
    -0.81
    alach
    -0.81
    gur
    -0.77
    regon
    -0.75
    utenberg
    -0.73
    shown
    -0.71
    vae
    -0.71
    ©¶æ
    -0.69
    edition
    -0.69
    baugh
    -0.68
    POSITIVE LOGITS
     treaty
    1.22
     Treaty
    1.18
     treaties
    1.03
    eers
    0.80
    ually
    0.80
     ratification
    0.79
    ãĥ¼ãĥĨãĤ£
    0.78
     droid
    0.77
     negotiations
    0.75
    breaker
    0.74
    Act Density 0.012%

    No Known Activations