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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of authority or control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aires
    -0.16
    ลาย
    -0.14
    rez
    -0.14
    ERING
    -0.14
    rooms
    -0.14
    å¹ķ
    -0.14
    ForMember
    -0.14
    JKLMNOP
    -0.14
     æŃ
    -0.13
    abant
    -0.13
    POSITIVE LOGITS
    emann
    0.18
    .deepcopy
    0.17
    /cop
    0.17
    eland
    0.17
    .BorderFactory
    0.17
    Sys
    0.16
    ilot
    0.15
    finger
    0.15
    yleft
    0.15
    ys
    0.15
    Act Density 0.019%

    No Known Activations