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

    Neuronpedia

    INDEX
    Explanations

    references to postdoctoral positions or fellowships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dwarf
    -0.18
    кеÑĤ
    -0.15
    èĢ
    -0.15
    ãĥ³ãĥĸ
    -0.15
    reed
    -0.15
     Maiden
    -0.15
     Duncan
    -0.15
     dem
    -0.14
    ÃĿ
    -0.14
    abez
    -0.14
    POSITIVE LOGITS
    doctor
    0.40
    odo
    0.32
    -do
    0.31
     doctor
    0.28
    Doctor
    0.27
    docs
    0.27
    doc
    0.26
     Doctor
    0.25
     doctoral
    0.24
    Doc
    0.23
    Act Density 0.006%

    No Known Activations