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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to a specific fictional character or family

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Stark and related names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WAYS
    -0.79
    PER
    -0.75
    ulhu
    -0.74
    BLE
    -0.72
    uters
    -0.71
    EPA
    -0.68
    CRE
    -0.68
    ãĥ¼ãĥ³
    -0.68
    Ú
    -0.67
    WHERE
    -0.66
    POSITIVE LOGITS
     Stark
    1.29
     Banner
    1.00
    iller
    0.80
    olicy
    0.80
    auld
    0.78
     Lann
    0.78
    weather
    0.75
    iffs
    0.74
    lund
    0.72
    orman
    0.72
    Act Density 0.026%

    No Known Activations