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

    Neuronpedia

    INDEX
    Explanations

    references to couples

    oai_token-act-pair · gpt-3.5-turbo

    references to couples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.78
    schild
    -0.74
    é¾
    -0.71
     Directorate
    -0.66
    ibaba
    -0.61
    OUGH
    -0.61
    umbn
    -0.58
    emouth
    -0.58
    ifact
    -0.57
    ichick
    -0.57
    POSITIVE LOGITS
    hood
    0.94
     wed
    0.91
    maid
    0.88
    ndra
    0.87
     married
    0.87
    tons
    0.85
    plates
    0.83
    riages
    0.82
     divorced
    0.81
     divor
    0.80
    Act Density 0.027%

    No Known Activations