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

    Neuronpedia

    INDEX
    Explanations

    terms related to locations and political figures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    gaard
    -0.91
    ============
    -0.87
    ========
    -0.86
     clothed
    -0.85
     Alleg
    -0.82
     Totem
    -0.81
     Fernand
    -0.80
    tto
    -0.77
    natureconservancy
    -0.75
     Siber
    -0.75
    POSITIVE LOGITS
    icago
    1.50
    anical
    1.40
    amber
    1.30
    craft
    1.28
    ambers
    1.22
    ington
    1.18
    arma
    1.09
    ican
    1.06
    inese
    1.06
    istry
    1.06
    Act Density 0.628%

    No Known Activations