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

    Neuronpedia

    INDEX
    Explanations

    incrementing or modifying operations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bias
    -0.15
    æĸĻ
    -0.15
     Mae
    -0.14
    /Runtime
    -0.14
    Æ°
    -0.14
    ssel
    -0.14
    474
    -0.14
    sel
    -0.13
    antage
    -0.13
    rocess
    -0.13
    POSITIVE LOGITS
    orage
    0.15
    å¹¹
    0.15
    lix
    0.14
     Wien
    0.14
    ace
    0.14
    uja
    0.14
    ajo
    0.14
    emen
    0.14
    inus
    0.14
     steps
    0.14
    Act Density 0.020%

    No Known Activations