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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating community involvement and social responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.16
    arro
    -0.15
    èĮĤ
    -0.15
    oris
    -0.14
    lesc
    -0.14
    kke
    -0.14
    ihu
    -0.14
    ستاÙĨ
    -0.14
    mark
    -0.14
    enberg
    -0.14
    POSITIVE LOGITS
     gre
    0.15
    ecast
    0.14
     again
    0.14
     Harmony
    0.14
     combining
    0.14
    ocre
    0.14
     Rhe
    0.13
    beit
    0.13
    Looper
    0.13
     morph
    0.13
    Act Density 0.358%

    No Known Activations