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

    Neuronpedia

    INDEX
    Explanations

    references to characters, performances, or notable elements from films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .asp
    -0.17
     глÑĥ
    -0.15
    Basket
    -0.14
    lak
    -0.14
     Abed
    -0.14
    :NO
    -0.14
    offsetof
    -0.14
    urr
    -0.13
    679
    -0.13
     harga
    -0.13
    POSITIVE LOGITS
     Rupert
    0.18
     Histor
    0.17
    histor
    0.16
     historical
    0.16
     historically
    0.15
    æ´²
    0.15
     Magick
    0.15
     swords
    0.15
     Freddie
    0.15
    Histor
    0.15
    Act Density 0.220%

    No Known Activations