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

    Neuronpedia

    INDEX
    Explanations

    references to individuals in a narrative context, particularly focusing on their characteristics and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pta
    -0.17
    uela
    -0.17
    Female
    -0.15
     Female
    -0.15
    pets
    -0.14
    íĨ¤
    -0.14
    sik
    -0.14
    loor
    -0.13
     Prostit
    -0.13
    à¸ı
    -0.13
    POSITIVE LOGITS
     guy
    0.71
     man
    0.64
     dude
    0.49
     fellow
    0.47
     person
    0.47
     guys
    0.45
     chap
    0.44
     blo
    0.41
     gentleman
    0.39
     Guy
    0.38
    Act Density 0.319%

    No Known Activations