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

    Neuronpedia

    INDEX
    Explanations

    phrases related to imprisonment or restraint

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UGE
    -0.17
    à¹īà¸ĩ
    -0.15
    =$((
    -0.15
    lak
    -0.15
    ä¸ĸ
    -0.14
     миÑĢов
    -0.14
    çŁ¢
    -0.14
     ÑģÑĤаÑĤи
    -0.14
    ermen
    -0.14
    .EventQueue
    -0.14
    POSITIVE LOGITS
    illac
    0.16
    ARIANT
    0.15
     Chew
    0.15
    ADE
    0.15
     immobil
    0.14
    antee
    0.14
    inte
    0.14
     ideal
    0.14
    apon
    0.13
    apple
    0.13
    Act Density 0.082%

    No Known Activations