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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geopolitical events and political decisions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    usterity
    -0.69
     partial
    -0.63
     +/-
    -0.63
     Slayer
    -0.62
     {:
    -0.62
     psy
    -0.61
     CJ
    -0.61
     ±
    -0.60
     Fallen
    -0.60
     Robin
    -0.58
    POSITIVE LOGITS
    abouts
    1.95
    upon
    1.33
    fore
    0.90
     guiActiveUn
    0.88
    with
    0.85
    ublic
    0.82
    comings
    0.80
    under
    0.78
    tics
    0.77
    Else
    0.77
    Act Density 1.035%

    No Known Activations