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

    Neuronpedia

    INDEX
    Explanations

    references to specific numerical or coded values and their connections to recognizable terms or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¬ãĥĥãĥĪ
    -0.17
     Pier
    -0.15
    erb
    -0.15
     PREF
    -0.14
     primitive
    -0.14
    енÑĮ
    -0.14
    ãn
    -0.14
    ged
    -0.13
    anzi
    -0.13
     Prevention
    -0.13
    POSITIVE LOGITS
    éĺµ
    0.15
     Nab
    0.15
    iku
    0.15
    ола
    0.15
    iral
    0.15
    onal
    0.14
    ixa
    0.14
    loor
    0.14
    ادÙĩ
    0.14
    -inline
    0.14
    Act Density 0.023%

    No Known Activations