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

    Neuronpedia

    INDEX
    Explanations

    political and philosophical discussions or arguments

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    opian
    -0.77
     destro
    -0.74
     pse
    -0.70
    owicz
    -0.69
     schooling
    -0.69
    iatrics
    -0.67
     abandon
    -0.66
    apons
    -0.65
     overth
    -0.65
     exting
    -0.64
    POSITIVE LOGITS
    WASHINGTON
    1.07
    SHARE
    1.05
    Overview
    1.02
    Abstract
    1.01
    Product
    1.01
    Contents
    1.01
    CLE
    0.97
    HOU
    0.96
    Details
    0.96
    About
    0.96
    Act Density 0.111%

    No Known Activations