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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different types of couples, such as unmarried, married, and diverse couples

    oai_token-act-pair · gpt-3.5-turbo

    references to couples, particularly in the context of marriage and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.94
    ukong
    -0.79
     Flavoring
    -0.78
    OLOG
    -0.74
    ibaba
    -0.70
    osure
    -0.68
     Removal
    -0.64
     Horizon
    -0.63
     Runner
    -0.62
    OUGH
    -0.61
    POSITIVE LOGITS
     couples
    1.09
    riages
    0.84
    ples
    0.84
    folk
    0.82
    tones
    0.78
    icles
    0.76
    hood
    0.74
     dads
    0.73
    maid
    0.73
    ecided
    0.72
    Act Density 0.012%

    No Known Activations