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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Toolkit
    -0.14
    âĨĵ
    -0.14
    çĹ
    -0.14
    933
    -0.14
    urge
    -0.14
    جÙĨ
    -0.14
    ador
    -0.13
    hone
    -0.13
     Lump
    -0.13
     carbon
    -0.13
    POSITIVE LOGITS
     Orc
    0.24
     Department
    0.23
    Department
    0.21
     Departments
    0.20
     department
    0.19
     corresponding
    0.19
     Division
    0.18
     correspondence
    0.17
     )↵↵↵↵↵↵↵↵
    0.17
    Division
    0.17
    Act Density 0.054%

    No Known Activations