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

    Neuronpedia

    INDEX
    Explanations

    statements and concepts related to generalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indr
    -0.17
    maid
    -0.15
    ajas
    -0.15
    еÑĢк
    -0.15
     empt
    -0.15
     Contents
    -0.15
    ym
    -0.15
    머
    -0.14
    ENTA
    -0.14
    748
    -0.14
    POSITIVE LOGITS
    everything
    0.16
    _except
    0.15
    -Ray
    0.15
     Jiang
    0.15
    ayed
    0.15
    ä¸ĢåĪĩ
    0.14
    Everything
    0.14
     Everything
    0.14
    Ùģع
    0.14
     everything
    0.14
    Act Density 0.155%

    No Known Activations