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

    Neuronpedia

    INDEX
    Explanations

    words related to invention and intellectual property

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ANTE
    -0.17
    lla
    -0.16
    hind
    -0.15
    adolu
    -0.15
     tÃŃn
    -0.15
    زب
    -0.14
    ÙĦات
    -0.14
    BITS
    -0.14
    iful
    -0.14
    ÏģοÏį
    -0.14
    POSITIVE LOGITS
    ary
    0.78
    aries
    0.64
    ARY
    0.57
    ory
    0.51
    arily
    0.45
    ario
    0.43
    ories
    0.42
    atory
    0.40
    uary
    0.39
    arios
    0.38
    Act Density 0.066%

    No Known Activations