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

    Neuronpedia

    INDEX
    Explanations

    references to literary works and character interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñİдж
    -0.15
     OK
    -0.14
    "Yeah
    -0.14
     Sesso
    -0.14
    opup
    -0.14
     chiefs
    -0.14
     kli
    -0.14
    ÑģÑĥÑĤ
    -0.13
     cpt
    -0.13
    alom
    -0.13
    POSITIVE LOGITS
     Society
    0.20
     matchmaking
    0.19
     scandal
    0.19
     gazet
    0.19
     Lady
    0.18
     Parliament
    0.17
     gover
    0.17
    çĪµ
    0.17
    pton
    0.17
     ladies
    0.17
    Act Density 0.117%

    No Known Activations