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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal terms and procedures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    monary
    -0.71
    ologically
    -0.70
    govtrack
    -0.70
     IMAGES
    -0.70
     dearly
    -0.69
    minecraft
    -0.63
    rontal
    -0.62
     sqor
    -0.62
    mong
    -0.61
    iversal
    -0.60
    POSITIVE LOGITS
    steen
    0.84
    ij士
    0.83
    otte
    0.75
    WHERE
    0.74
     Musk
    0.70
    cent
    0.70
    ador
    0.69
    ITH
    0.69
    quez
    0.69
    agne
    0.67
    Act Density 17.561%

    No Known Activations