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

    Neuronpedia

    INDEX
    Explanations

    expressions of thoughts, beliefs, and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    δά
    -0.16
    wik
    -0.15
    ropolis
    -0.14
    oples
    -0.14
     же
    -0.14
    iyas
    -0.14
    æĤª
    -0.13
    ìĿ´ëĿ¼ëĬĶ
    -0.13
     Alive
    -0.13
    ä¸ľè¥¿
    -0.13
    POSITIVE LOGITS
     would
    0.21
     should
    0.20
     is
    0.19
     might
    0.17
     could
    0.17
     will
    0.17
     are
    0.17
     SHOULD
    0.16
     must
    0.16
     ought
    0.15
    Act Density 0.072%

    No Known Activations