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

    Neuronpedia

    INDEX
    Explanations

    references to "mind-bending" concepts or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wick
    -0.17
    ÃŃnÄĽ
    -0.16
    áš
    -0.15
    vk
    -0.14
    pillar
    -0.14
    gang
    -0.14
    Ú©Ø´
    -0.14
    iben
    -0.14
    bil
    -0.14
    unkt
    -0.14
    POSITIVE LOGITS
    appa
    0.17
    tra
    0.15
    ogg
    0.15
    istra
    0.15
    mind
    0.15
    oggles
    0.15
     Gott
    0.15
    ia
    0.15
    istics
    0.14
    lify
    0.14
    Act Density 0.019%

    No Known Activations