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

    Neuronpedia

    INDEX
    Explanations

    phrases that mention family relationships

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wife" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    othal
    -0.80
    etary
    -0.75
    enture
    -0.73
    ramids
    -0.73
    orst
    -0.73
    ramid
    -0.72
    ":"/
    -0.72
    Translation
    -0.69
    ocal
    -0.69
    ibaba
    -0.69
    POSITIVE LOGITS
     Karen
    1.02
     Sue
    1.00
     Tammy
    1.00
     Valerie
    0.99
     Nancy
    0.95
     Kathy
    0.94
     Beau
    0.91
     Pam
    0.91
     Sara
    0.91
     Denise
    0.91
    Act Density 0.095%

    No Known Activations