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

    Neuronpedia

    INDEX
    Explanations

    phrases related to marriage and relationships, particularly focusing on the role and treatment of wives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.75
     GOODMAN
    -0.73
    oola
    -0.73
    UFF
    -0.71
    itars
    -0.69
    IFIED
    -0.69
     constitu
    -0.69
     athlet
    -0.68
    Rush
    -0.66
     Spicer
    -0.66
    POSITIVE LOGITS
    hood
    1.01
    wife
    0.95
    maid
    0.83
    doctor
    0.80
    bands
    0.78
    liest
    0.78
    heses
    0.78
    yer
    0.77
    nesday
    0.77
    folk
    0.77
    Act Density 0.060%

    No Known Activations