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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating settings or contexts in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢоÑĤ
    -0.15
    anime
    -0.15
     Hud
    -0.15
    adle
    -0.14
    olumn
    -0.14
    Connell
    -0.13
     kalan
    -0.13
    اÙĨÙĪ
    -0.13
     Couch
    -0.13
    ctrine
    -0.13
    POSITIVE LOGITS
     too
    0.16
    }_${
    0.15
    ference
    0.15
    771
    0.15
     loos
    0.14
    ervative
    0.14
     chung
    0.14
    ented
    0.14
    콩
    0.13
    tu
    0.13
    Act Density 0.038%

    No Known Activations