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

    Neuronpedia

    INDEX
    Explanations

    complex numbers or numerical expressions involving complex numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rador
    -1.07
    hire
    -0.93
    riot
    -0.78
    Sov
    -0.76
    idden
    -0.75
    arkin
    -0.74
    ovie
    -0.73
    raits
    -0.73
    rait
    -0.72
    sels
    -0.69
    POSITIVE LOGITS
     comput
    0.83
     theorem
    0.80
    metry
    0.77
     milliseconds
    0.76
     computation
    0.75
     digits
    0.74
     mathematic
    0.71
     numer
    0.70
     elapsed
    0.69
    define
    0.69
    Act Density 0.049%

    No Known Activations