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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to widows

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals who have lost a spouse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atre
    -0.74
     constitu
    -0.72
    orescent
    -0.71
    ebook
    -0.67
     Lansing
    -0.64
    iggurat
    -0.63
    Recipe
    -0.62
    orically
    -0.61
    anian
    -0.61
    eele
    -0.60
    POSITIVE LOGITS
     widow
    1.44
     wid
    1.00
    hood
    0.97
     Widow
    0.94
    nesday
    0.91
    iciary
    0.89
    doms
    0.82
     adolesc
    0.79
    maker
    0.78
    rocket
    0.78
    Act Density 0.006%

    No Known Activations