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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical models and their critical properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëĬĶì§Ģ
    -0.16
     âĹĦ
    -0.15
    unate
    -0.15
    ãģĵãģĨ
    -0.15
    bern
    -0.14
    íį¼
    -0.14
    kı
    -0.14
    ÑĪки
    -0.13
    ekl
    -0.13
    IOUS
    -0.13
    POSITIVE LOGITS
     meaning
    0.64
     ie
    0.63
    meaning
    0.55
     Meaning
    0.54
     i
    0.52
     ÛĮعÙĨÛĮ
    0.51
     ì¦ī
    0.51
     yani
    0.49
     ÑĤобÑĤо
    0.49
    ie
    0.48
    Act Density 0.457%

    No Known Activations