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

    Neuronpedia

    INDEX
    Explanations

    code snippets related to mathematical computations and operations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    numeric literals, especially integers and floating-point numbers in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jiahuipeng
    New Auto-Interp
    Negative Logits
     NRA
    -0.64
     coron
    -0.64
     veto
    -0.63
     lieu
    -0.63
     Belle
    -0.61
     Loving
    -0.61
    hens
    -0.60
    hement
    -0.59
     portfolios
    -0.59
     demonstr
    -0.58
    POSITIVE LOGITS
    0000
    1.40
    000000
    1.34
    0000000
    1.29
    0000000000000000
    1.27
    00000
    1.22
    00000000
    1.21
    9999
    1.13
    FFFF
    1.04
    px
    1.04
    999
    0.99
    Act Density 0.132%

    No Known Activations