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

    Neuronpedia

    INDEX
    Explanations

    references to films and their related works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¬ãĤ¹
    -0.15
    vla
    -0.15
    wnd
    -0.15
    alfa
    -0.14
    reta
    -0.14
    opal
    -0.14
    baru
    -0.14
    ùy
    -0.13
    thon
    -0.13
    _EDITOR
    -0.13
    POSITIVE LOGITS
    åIJĮ
    0.44
     same
    0.44
    same
    0.40
    Same
    0.35
     Same
    0.33
     gleich
    0.32
     similarly
    0.31
     SAME
    0.30
     aynı
    0.29
     mismo
    0.29
    Act Density 0.122%

    No Known Activations