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

    Neuronpedia

    INDEX
    Explanations

    the activation values associated with mathematical equations combined with elements such as numbers, symbols, and variables

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.96
    aver
    -0.83
    73
    -0.83
    FY
    -0.82
    74
    -0.82
    53
    -0.78
    54
    -0.77
    76
    -0.77
    429
    -0.77
    52
    -0.77
    POSITIVE LOGITS
     {
    0.83
     1000
    0.80
     Submit
    0.79
     10000
    0.78
     01
    0.77
     =================
    0.77
     2100
    0.77
     0
    0.75
     Categories
    0.74
     $
    0.74
    Act Density 0.021%

    No Known Activations