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

    Neuronpedia

    INDEX
    Explanations

    references to high-profile individuals and their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Meng
    -0.19
     Hus
    -0.15
     Donne
    -0.15
     Wheeler
    -0.15
    388
    -0.15
     Bach
    -0.15
    ird
    -0.14
    IRD
    -0.14
    858
    -0.14
    hack
    -0.14
    POSITIVE LOGITS
     Harry
    0.54
    Harry
    0.50
     Potter
    0.48
    Pot
    0.38
     Rowling
    0.38
     wizard
    0.37
     Pot
    0.37
     Hogwarts
    0.36
     Dumbledore
    0.35
     pot
    0.35
    Act Density 0.021%

    No Known Activations