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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.76
    Personendaten
    -0.66
    windowFixed
    -0.63
     تضيفلها
    -0.62
    AsUp
    -0.57
    -0.55
     bezeichneter
    -0.54
    ftagPool
    -0.52
     defaultstate
    -0.52
    󠁣
    -0.52
    POSITIVE LOGITS
    ennen
    0.32
     Boletín
    0.30
    WebpackPlugin
    0.30
     /#
    0.29
    umbus
    0.29
    Pyx
    0.29
     estekak
    0.28
    ​​​
    0.28
    kologi
    0.28
    (&:
    0.28
    Act Density 0.174%

    No Known Activations