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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and social commentary

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    gypt
    -1.09
    illin
    -1.05
    bian
    -1.05
    eki
    -1.05
    Adv
    -0.94
     cultivating
    -0.92
     bonded
    -0.92
    OTOS
    -0.88
    031
    -0.87
     periphery
    -0.87
    POSITIVE LOGITS
    't
    1.90
    nings
    1.45
    stall
    1.22
    itive
    1.19
    now
    1.17
    geon
    1.11
    etsk
    1.08
    ners
    1.08
    rar
    1.08
    cest
    1.04
    Act Density 0.504%

    No Known Activations