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

    Neuronpedia

    INDEX
    Explanations

    references to hierarchical structures and levels within systems or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asin
    -0.17
    anko
    -0.15
    zin
    -0.15
    idden
    -0.14
    nan
    -0.14
    aign
    -0.14
    -bordered
    -0.14
    anim
    -0.13
    (ERR
    -0.13
    à¥įरव
    -0.13
    POSITIVE LOGITS
     level
    0.34
     levels
    0.33
    -level
    0.31
    级
    0.28
    level
    0.28
    ç´ļ
    0.27
    levels
    0.27
    å±Ĥ
    0.26
     LEVEL
    0.26
    (level
    0.25
    Act Density 0.091%

    No Known Activations