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

    Neuronpedia

    INDEX
    Explanations

    references to formal meetings and hearings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utt
    -0.15
    aku
    -0.15
    vek
    -0.14
    rams
    -0.14
    poses
    -0.14
    avs
    -0.14
    fone
    -0.13
    å½¼
    -0.13
     Pin
    -0.13
    batis
    -0.13
    POSITIVE LOGITS
    -toggler
    0.18
    977
    0.17
    zell
    0.16
    uards
    0.14
    unan
    0.14
    Âłmiles
    0.13
    ارب
    0.13
    iba
    0.13
    åı
    0.13
    tridges
    0.13
    Act Density 0.074%

    No Known Activations