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

    Neuronpedia

    INDEX
    Explanations

    references to family members, especially uncles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of familial relationships, specifically related to uncles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mberg
    -0.95
    ãĤ¤ãĥĪ
    -0.69
     largeDownload
    -0.67
    istas
    -0.65
     lapse
    -0.64
    EVA
    -0.63
    punk
    -0.63
    Effect
    -0.62
    NG
    -0.62
    */(
    -0.61
    POSITIVE LOGITS
     uncle
    1.14
    liest
    0.94
    hest
    0.92
     Uncle
    0.88
    hetically
    0.86
     nephew
    0.85
     aunt
    0.83
    heses
    0.82
     niece
    0.80
    ired
    0.79
    Act Density 0.011%

    No Known Activations