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

    Neuronpedia

    INDEX
    Explanations

    expressions of curiosity and self-reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cân
    -0.08
    éĤ
    -0.07
    esser
    -0.07
    ëĭĪìķĦ
    -0.07
    æµ´
    -0.07
    جÙĬÙĦ
    -0.07
    ypse
    -0.07
    огÑĥ
    -0.07
     dinosaurs
    -0.07
    ì§ĢëıĦ
    -0.07
    POSITIVE LOGITS
     military
    0.07
    ocker
    0.07
     societies
    0.06
     religious
    0.06
     often
    0.06
    ondo
    0.06
     RectTransform
    0.06
     Soci
    0.06
     prod
    0.06
    dere
    0.06
    Act Density 0.066%

    No Known Activations