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

    Neuronpedia

    INDEX
    Explanations

    concepts related to mathematical or programming variables and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /preferences
    -0.19
    /portfolio
    -0.18
     Bare
    -0.14
    &P
    -0.14
    ourg
    -0.14
    +W
    -0.14
    /slider
    -0.14
     (&
    -0.14
    /goto
    -0.13
     vara
    -0.13
    POSITIVE LOGITS
    /
    0.50
     /
    0.38
    \/
    0.31
    ï¼ı
    0.31
    _/
    0.29
    /{
    0.28
    ,/
    0.28
    /↵
    0.28
    /\
    0.27
    /&
    0.26
    Act Density 0.506%

    No Known Activations