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

    Neuronpedia

    INDEX
    Explanations

    mentions of relationships, particularly between spouses or partners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berger
    -0.16
     masturb
    -0.16
     ancestor
    -0.15
    rella
    -0.15
    amedi
    -0.15
     puberty
    -0.15
     Boys
    -0.15
    ancestor
    -0.15
    ruk
    -0.14
     ancestral
    -0.14
    POSITIVE LOGITS
     wife
    0.93
     husband
    0.80
     Wife
    0.79
    wife
    0.77
     wives
    0.75
    -wife
    0.73
     spouse
    0.73
     Husband
    0.68
     spouses
    0.67
    妻
    0.66
    Act Density 0.548%

    No Known Activations