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

    Neuronpedia

    INDEX
    Explanations

    names of researchers and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    856
    -0.15
    duc
    -0.15
    urge
    -0.14
    933
    -0.13
    dy
    -0.13
     ReSharper
    -0.13
    oyer
    -0.13
    atte
    -0.13
    Toolkit
    -0.13
    ฯ
    -0.13
    POSITIVE LOGITS
     Orc
    0.24
     Department
    0.22
    Department
    0.20
     corresponding
    0.20
     Departments
    0.19
     )↵↵↵↵↵↵↵↵
    0.18
     Correspond
    0.17
     correspondence
    0.17
     department
    0.17
     Division
    0.16
    Act Density 0.051%

    No Known Activations