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

    Neuronpedia

    INDEX
    Explanations

    scientific studies discussing limitations and future research directions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.58
    IntoConstraints
    -0.58
    itamente
    -0.58
     LUMP
    -0.56
    UnsafeEnabled
    -0.56
    eneuve
    -0.54
     plötzlich
    -0.54
    kháu
    -0.53
    Havolalar
    -0.53
    کم
    -0.52
    POSITIVE LOGITS
     future
    1.92
    future
    1.66
    Future
    1.55
     Future
    1.53
     further
    1.53
     Further
    1.39
    further
    1.36
     FUTURE
    1.34
    FUTURE
    1.31
    Further
    1.30
    Act Density 1.119%

    No Known Activations