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

    Neuronpedia

    INDEX
    Explanations

    instances of procedural language related to planning or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ara
    -0.17
     notion
    -0.16
    ussy
    -0.15
     Sawyer
    -0.15
     Oswald
    -0.15
    angi
    -0.14
    aque
    -0.14
     Tart
    -0.14
    avy
    -0.14
    uss
    -0.14
    POSITIVE LOGITS
    divid
    0.14
    iyim
    0.14
    ÅĻaz
    0.14
    ÙĮ
    0.14
    usercontent
    0.13
    ĨĴ
    0.13
    éļĨ
    0.13
     addButton
    0.13
     pri
    0.13
    anceled
    0.13
    Act Density 0.122%

    No Known Activations