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

    Neuronpedia

    INDEX
    Explanations

    mathematical structures and formal definitions related to categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çļĦæĺ¯
    -0.14
    -</
    -0.14
    oret
    -0.14
    añ
    -0.13
    inho
    -0.13
    #=
    -0.13
     Falls
    -0.13
    ÙĪرÙĨ
    -0.13
    anners
    -0.13
    otta
    -0.13
    POSITIVE LOGITS
     ->
    0.41
     âĨĴ
    0.38
     -->
    0.31
    ->
    0.30
    âĨĴ
    0.28
     =>
    0.27
     \
    0.25
     ->↵
    0.25
    ]->
    0.24
    -->
    0.23
    Act Density 0.071%

    No Known Activations