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

    Neuronpedia

    INDEX
    Explanations

    phrases related to same-sex relationships or marriages

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    unes
    -0.79
    OIL
    -0.67
     Tune
    -0.67
    steen
    -0.67
    ULE
    -0.67
    hp
    -0.66
    RON
    -0.66
    KEN
    -0.66
    md
    -0.65
    RM
    -0.65
    POSITIVE LOGITS
     couples
    1.08
     marriage
    1.00
    marriage
    0.94
     marriages
    0.91
     relations
    0.87
     parenting
    0.85
     spouses
    0.84
     sex
    0.82
     intercourse
    0.81
     attractions
    0.81
    Act Density 0.034%

    No Known Activations