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

    Neuronpedia

    INDEX
    Explanations

    references to dystopian themes in literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.19
     Shields
    -0.17
    steen
    -0.15
     Malk
    -0.14
    ysz
    -0.14
    kenin
    -0.14
    engo
    -0.14
    itchen
    -0.14
     slik
    -0.13
    ridge
    -0.13
    POSITIVE LOGITS
     Rhodes
    0.16
    격
    0.15
    lld
    0.15
     声
    0.15
    iot
    0.14
     Force
    0.14
    iously
    0.14
    ocale
    0.14
     Pon
    0.14
    Force
    0.14
    Act Density 0.016%

    No Known Activations