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

    Neuronpedia

    INDEX
    Explanations

    references to confusion and chaos in various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑģилÑĮ
    -0.15
     strides
    -0.15
    _SZ
    -0.14
    emd
    -0.14
    ording
    -0.14
     Violence
    -0.14
     trouble
    -0.14
     nto
    -0.14
     示
    -0.13
     ë§Ŀ
    -0.13
    POSITIVE LOGITS
     guessing
    0.23
     tug
    0.22
     race
    0.21
     sé
    0.20
     mad
    0.20
     game
    0.19
     dance
    0.19
     merry
    0.18
     mini
    0.18
     Kab
    0.18
    Act Density 0.332%

    No Known Activations