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

    Neuronpedia

    INDEX
    Explanations

    references to large-scale projects and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elden
    -0.16
    ůr
    -0.16
    ani
    -0.15
    èn
    -0.15
    iddles
    -0.14
    iddy
    -0.14
    éné
    -0.14
    CLUDING
    -0.13
     Lazy
    -0.13
    prend
    -0.13
    POSITIVE LOGITS
     planned
    0.37
     intended
    0.27
     Planned
    0.26
     would
    0.25
    åİŁæľ¬
    0.24
     originally
    0.23
     Would
    0.23
     ready
    0.22
     plans
    0.21
     had
    0.21
    Act Density 0.218%

    No Known Activations