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

    Neuronpedia

    INDEX
    Explanations

    numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and expressions related to programming or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierrez
    -0.82
    anooga
    -0.78
     ultras
    -0.76
    undai
    -0.72
    accompan
    -0.71
     spons
    -0.69
    abwe
    -0.69
     Beir
    -0.68
     hemor
    -0.68
    raviolet
    -0.67
    POSITIVE LOGITS
    0000
    1.13
    000000
    1.11
    00
    1.08
    00000
    1.06
    xx
    1.02
    67
    1.00
    45
    0.98
    00000000
    0.97
    9999
    0.97
    456
    0.97
    Act Density 0.175%

    No Known Activations