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

    Neuronpedia

    INDEX
    Explanations

    legal-related terms and phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.72
    eful
    -0.70
    hoff
    -0.69
    atomic
    -0.68
    ilon
    -0.68
     Runner
    -0.67
    efully
    -0.66
     livest
    -0.66
    oday
    -0.65
     Tate
    -0.65
    POSITIVE LOGITS
    ising
    0.93
    istically
    0.92
     recourse
    0.91
     precedent
    0.89
     enforcement
    0.88
     proceedings
    0.87
    ised
    0.85
     liability
    0.84
    suit
    0.82
    suits
    0.81
    Act Density 0.036%

    No Known Activations