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

    Neuronpedia

    INDEX
    Explanations

    information related to current events and government actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     expire
    -0.80
     nuts
    -0.75
     macros
    -0.74
     retard
    -0.71
     entitle
    -0.67
     overlap
    -0.67
     plants
    -0.66
     recip
    -0.66
     orche
    -0.65
     ris
    -0.64
    POSITIVE LOGITS
    Reuters
    1.19
    Thom
    1.16
    CNN
    1.09
    AFP
    1.08
    via
    1.07
    CBS
    1.06
    emphasis
    1.05
    PET
    1.05
    pictured
    1.05
    ...)
    1.03
    Act Density 3.393%

    No Known Activations