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

    Neuronpedia

    INDEX
    Explanations

    the word "Kin" with varying degrees of relevance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of familial or relational connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enance
    -0.85
     Seym
    -0.82
    shire
    -0.79
    theless
    -0.77
    Ö¼
    -0.74
    enegger
    -0.71
    ONT
    -0.69
    ILLE
    -0.68
    ERE
    -0.66
    ORD
    -0.66
    POSITIVE LOGITS
    folk
    1.30
    etics
    1.29
    etic
    1.16
    etically
    1.14
    Kin
    1.13
    sey
    1.06
    esthetic
    1.04
    ners
    1.02
    zie
    0.98
     kin
    0.96
    Act Density 0.011%

    No Known Activations