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

    Neuronpedia

    INDEX
    Explanations

    references to spouses and marital relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Uru
    -0.73
     CMM
    -0.73
     Yeh
    -0.70
    .='
    -0.70
    Poc
    -0.69
     demur
    -0.68
     Judea
    -0.67
     Appear
    -0.66
     Calla
    -0.66
    وذ
    -0.65
    POSITIVE LOGITS
     wife
    1.50
     wives
    1.38
     WIFE
    1.36
     husband
    1.28
     Wife
    1.28
     Husband
    1.23
    Wife
    1.23
     spouse
    1.22
    husband
    1.21
    wife
    1.20
    Act Density 0.036%

    No Known Activations