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

    Neuronpedia

    INDEX
    Explanations

    numbers and sports team names

    oai_token-act-pair · gpt-3.5-turbo

    numbers and their related statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     loudspe
    -0.68
     entreprene
    -0.67
     interpreter
    -0.67
     newsp
    -0.66
     whistle
    -0.66
     roundup
    -0.65
     vide
    -0.65
     eagerly
    -0.63
     facilit
    -0.63
     drawn
    -0.62
    POSITIVE LOGITS
    Total
    0.75
     TOTAL
    0.72
     Avg
    0.70
    "}
    0.68
    OTAL
    0.68
     Ratio
    0.68
    Ast
    0.68
     respectively
    0.67
     Difference
    0.67
     Tot
    0.66
    Act Density 0.098%

    No Known Activations