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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal numbers and mathematical expressions

    oai_token-act-pair · gpt-3.5-turbo

    numerical values in various formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    steen
    -0.89
    annis
    -0.88
    aws
    -0.73
    geon
    -0.71
    ackle
    -0.70
    stood
    -0.69
    wright
    -0.68
    warts
    -0.68
    awed
    -0.67
     athe
    -0.67
    POSITIVE LOGITS
    00000
    1.05
    0002
    1.00
    0000000
    0.99
    0100
    0.98
     00000000
    0.94
    0000
    0.94
    1001
    0.90
    001
    0.88
    644
    0.86
    0001
    0.85
    Act Density 0.016%

    No Known Activations