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

    Neuronpedia

    INDEX
    Explanations

    sentences containing information about criminal sentences, convictions, and legal proceedings

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.98
    horn
    -0.95
    echo
    -0.86
    connected
    -0.84
    hesion
    -0.84
    rified
    -0.83
    eways
    -0.82
    notations
    -0.80
    CTV
    -0.79
    hed
    -0.79
    POSITIVE LOGITS
     conserve
    1.01
    ãĥīãĥ©
    0.96
    asty
    0.94
     inflict
    0.93
    asted
    0.93
     considerable
    0.93
     varying
    0.93
     indefinite
    0.89
     fulfill
    0.89
     astronomical
    0.89
    Act Density 1.076%

    No Known Activations