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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and terms related to functions and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Richardson
    -0.17
     Freed
    -0.15
     Fors
    -0.14
    centroid
    -0.14
     Fully
    -0.14
    aldo
    -0.14
    ÙħÛĮÙĨ
    -0.13
    رÙĬس
    -0.13
     shr
    -0.13
     Robinson
    -0.13
    POSITIVE LOGITS
     function
    0.37
     functions
    0.32
    function
    0.31
    åĩ½æķ°
    0.30
     Function
    0.30
     Functions
    0.30
     ÑĦÑĥнкÑĨи
    0.29
    .function
    0.28
    functions
    0.28
     fonction
    0.27
    Act Density 0.397%

    No Known Activations