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

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical events and global political affairs, especially related to countries and leaders

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    naissance
    -1.05
    vernment
    -1.03
     mileage
    -1.02
    Reviewer
    -0.96
    ativity
    -0.94
    ously
    -0.93
    ISON
    -0.90
     slic
    -0.89
     laundry
    -0.89
    nces
    -0.88
    POSITIVE LOGITS
    weet
    1.71
    arnaev
    1.69
    hirt
    1.48
    onic
    1.45
    omething
    1.38
    avorite
    1.34
    arah
    1.33
    ugar
    1.31
    ierra
    1.30
    omp
    1.28
    Act Density 1.303%

    No Known Activations