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

    Neuronpedia

    INDEX
    Explanations

    references to regulatory and administrative processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stage
    -0.14
    важ
    -0.14
    REATED
    -0.14
    ickers
    -0.14
    iew
    -0.14
    ŀ
    -0.14
     vis
    -0.14
    iet
    -0.13
    aby
    -0.13
    .hand
    -0.13
    POSITIVE LOGITS
    akan
    0.15
    stery
    0.15
    оÑĢе
    0.15
    .scalablytyped
    0.15
    WindowState
    0.14
    velt
    0.14
    ighbor
    0.14
    _heads
    0.14
    åİ
    0.14
     Rena
    0.14
    Act Density 0.016%

    No Known Activations