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

    Neuronpedia

    INDEX
    Explanations

    words related to societal issues and societal change

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    PLIED
    -0.76
    CRIPTION
    -0.73
    notations
    -0.72
     anonymously
    -0.68
    uristic
    -0.67
     Vide
    -0.66
     Outdoor
    -0.65
    cript
    -0.65
    ifles
    -0.65
    ributes
    -0.64
    POSITIVE LOGITS
     slump
    1.16
     turmoil
    1.06
     infancy
    1.00
     precarious
    1.00
     meltdown
    0.98
     decline
    0.97
     brink
    0.94
     upheaval
    0.94
     flux
    0.93
    inventoryQuantity
    0.93
    Act Density 0.629%

    No Known Activations