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

    Neuronpedia

    INDEX
    Explanations

    references to legal agreements or treaties

    oai_token-act-pair · gpt-3.5-turbo

    references to treaties or legal agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alach
    -0.86
    edition
    -0.75
    shown
    -0.74
    ©¶æ
    -0.73
    stocks
    -0.70
    gur
    -0.68
    vae
    -0.68
    corn
    -0.67
    athy
    -0.67
    serving
    -0.67
    POSITIVE LOGITS
     Treaty
    1.01
     treaty
    1.00
     treaties
    0.90
    breaker
    0.82
    breakers
    0.81
     Implementation
    0.79
     Framework
    0.78
     ratified
    0.77
    ually
    0.76
    eers
    0.76
    Act Density 0.015%

    No Known Activations