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

    Neuronpedia

    INDEX
    Explanations

    phrases related to marriage legality and equality, especially regarding same-sex couples

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    OLOG
    -0.82
    acco
    -0.82
     Chocobo
    -0.72
    atche
    -0.71
    anwhile
    -0.70
    OLOGY
    -0.68
    burgh
    -0.68
     Lyons
    -0.68
    ourning
    -0.67
     Flavoring
    -0.67
    POSITIVE LOGITS
     equality
    1.17
     Equality
    0.97
    equality
    0.92
    riages
    0.88
    making
    0.86
    owship
    0.85
    bands
    0.83
     marriage
    0.79
    able
    0.78
     marry
    0.78
    Act Density 8.910%

    No Known Activations