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

    Neuronpedia

    INDEX
    Explanations

    concepts related to social issues and systemic phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     such
    -0.17
    theless
    -0.17
    such
    -0.17
    raci
    -0.16
    è¿Ļæł·çļĦ
    -0.15
    /respond
    -0.14
     ÑĨÑĮомÑĥ
    -0.14
     ê·¸ëłĩ
    -0.14
    ÑĢÑĥ
    -0.14
    ength
    -0.14
    POSITIVE LOGITS
     alone
    0.29
    alone
    0.25
     Alone
    0.18
     particular
    0.16
    Ľ°
    0.15
    icular
    0.15
    -ci
    0.15
    /th
    0.15
    -alone
    0.15
     plus
    0.15
    Act Density 0.541%

    No Known Activations