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

    Neuronpedia

    INDEX
    Explanations

    people's names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those named Curtis and Vand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ances
    -0.82
    orthy
    -0.75
    arent
    -0.70
    aced
    -0.68
    ously
    -0.66
    lies
    -0.66
    iot
    -0.66
    ods
    -0.65
    HF
    -0.64
    ded
    -0.64
    POSITIVE LOGITS
    prus
    0.82
    selage
    0.70
    eer
    0.70
    ©¶æ¥µ
    0.69
    plin
    0.67
    ãĥ¼ãĥĨãĤ£
    0.67
    ²¾
    0.66
    ãĥģ
    0.66
    allas
    0.66
    anguage
    0.65
    Act Density 0.074%

    No Known Activations