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

    Neuronpedia

    INDEX
    Explanations

    words related to marital status, specifically identifying individuals who are married

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "married."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urg
    -0.78
    abwe
    -0.78
     Flavoring
    -0.77
    ostic
    -0.74
    ebin
    -0.70
    affer
    -0.69
    efer
    -0.69
    acco
    -0.68
    umbn
    -0.67
    osta
    -0.66
    POSITIVE LOGITS
    nesday
    1.01
     couples
    0.84
    ton
    0.78
     married
    0.76
    tons
    0.76
    equality
    0.75
     marry
    0.75
     equality
    0.74
    thood
    0.73
    women
    0.73
    Act Density 0.025%

    No Known Activations