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

    Neuronpedia

    INDEX
    Explanations

    the name "Leighton" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    the name "Le" associated with various contexts or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -1.01
    aneers
    -0.99
    ãģĨ
    -0.96
    raints
    -0.93
    ividual
    -0.93
    ãĥ¼ãĥĨ
    -0.92
    etheless
    -0.91
    iaries
    -0.86
    uyomi
    -0.86
    âĶģ
    -0.86
    POSITIVE LOGITS
    isure
    1.21
    lean
    1.16
    ukemia
    1.00
    agues
    0.99
    icester
    0.98
    opard
    0.94
    azy
    0.94
    ven
    0.87
    aching
    0.86
    ather
    0.86
    Act Density 0.016%

    No Known Activations