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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific weight classes and titles in the context of combat sports

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    quist
    -0.85
     Helpful
    -0.79
    ibel
    -0.78
     Gutenberg
    -0.77
     FEMA
    -0.73
    atche
    -0.72
     Beh
    -0.71
    ickr
    -0.69
    ophysical
    -0.68
     Bezos
    -0.68
    POSITIVE LOGITS
    weights
    1.04
     contender
    1.02
    weight
    1.01
     boxing
    1.00
     wrestlers
    0.96
     championship
    0.96
     boxer
    0.93
     champion
    0.93
     division
    0.92
     champ
    0.91
    Act Density 0.036%

    No Known Activations