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

    Neuronpedia

    INDEX
    Explanations

    function definitions and their relationship to expected outcomes in policy validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odore
    -0.22
    uly
    -0.15
    aria
    -0.15
    iline
    -0.15
    nt
    -0.14
    sko
    -0.14
    ish
    -0.14
    acos
    -0.14
    akan
    -0.14
    alog
    -0.14
    POSITIVE LOGITS
     {↵
    0.21
    eriod
    0.17
     {//
    0.17
    erin
    0.16
     {↵↵
    0.16
    {//
    0.15
    547
    0.15
    677
    0.15
    947
    0.14
    ìĦľ
    0.14
    Act Density 0.023%

    No Known Activations