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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names associated with individuals or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BAD
    -0.17
    uc
    -0.14
     tub
    -0.14
     odp
    -0.14
    ä¼ı
    -0.14
    -BEGIN
    -0.14
    æ°ĹãģĮ
    -0.13
    ikipedia
    -0.13
    Aws
    -0.13
    zo
    -0.13
    POSITIVE LOGITS
     Ab
    0.22
     ab
    0.21
    querque
    0.19
    -ab
    0.18
    ance
    0.18
    afia
    0.17
    enant
    0.17
     AB
    0.17
    .Ab
    0.16
    Ab
    0.16
    Act Density 0.037%

    No Known Activations