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

    Neuronpedia

    INDEX
    Explanations

    terms related to rules or limitations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to governmental or legal restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rious
    -0.75
    psc
    -0.67
    past
    -0.67
    earth
    -0.65
    enic
    -0.64
    icus
    -0.62
    TPP
    -0.62
     Generations
    -0.62
    Asia
    -0.61
    ousing
    -0.61
    POSITIVE LOGITS
     imposed
    1.15
     restricting
    1.08
     restrictions
    1.01
     prohibited
    0.97
     restricts
    0.94
     prohibiting
    0.91
     restriction
    0.87
     inhib
    0.84
     regimes
    0.83
     restricted
    0.82
    Act Density 0.038%

    No Known Activations