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

    Neuronpedia

    INDEX
    Explanations

    references to individuals in directorial positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    croft
    -0.17
    angel
    -0.15
    yan
    -0.15
    å©·
    -0.15
    acey
    -0.15
    ALCHEMY
    -0.15
    ÙĦÛĮسÛĮ
    -0.14
    .tif
    -0.14
    optic
    -0.14
     sujet
    -0.14
    POSITIVE LOGITS
     operations
    0.17
    letcher
    0.16
    ¹
    0.15
    liner
    0.15
    èĹı
    0.14
    andles
    0.14
     Bur
    0.14
    757
    0.14
     attention
    0.13
    lining
    0.13
    Act Density 0.028%

    No Known Activations