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

    Neuronpedia

    INDEX
    Explanations

    titles of movies or sequels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĤ°ãĥ«
    -0.07
    ↵
    -0.06
     McDon
    -0.06
    691
    -0.05
    éc
    -0.05
    usal
    -0.05
     passage
    -0.05
    -
    -0.05
    angered
    -0.05
    532
    -0.05
    POSITIVE LOGITS
    ãĥ³ãĤº
    0.09
    ãĤ´ãĥª
    0.09
    .Elements
    0.08
    оÑıн
    0.08
     metic
    0.07
    ếp
    0.07
    ãģĭãĤı
    0.07
    atoria
    0.07
    ãĥ¬ãĤ¹
    0.07
    ÅĻád
    0.07
    Act Density 0.012%

    No Known Activations