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

    Neuronpedia

    INDEX
    Explanations

    phrases related to procedural actions and instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.83
    InjectAttribute
    -0.68
    NameInMap
    -0.64
    aarrggbb
    -0.61
    Hauptartikel
    -0.50
     Detect
    -0.49
    PhysRev
    -0.49
     surla
    -0.48
     "..\..\
    -0.47
    بوابة
    -0.47
    POSITIVE LOGITS
     melakukannya
    1.93
     hacerlo
    1.77
     doing
    1.63
     farlo
    1.63
    Doing
    1.50
     Doing
    1.47
    这样做
    1.40
    doing
    1.25
     accomplish
    1.21
     done
    1.18
    Act Density 0.588%

    No Known Activations