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

    Neuronpedia

    INDEX
    Explanations

    provocative or controversial statements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     circulating
    -0.75
     flooded
    -0.72
     diversion
    -0.71
     auxiliary
    -0.68
     prescribed
    -0.67
     Haj
    -0.66
     Maxwell
    -0.65
     volunt
    -0.65
     floating
    -0.65
     hovering
    -0.65
    POSITIVE LOGITS
    Br
    3.75
    br
    1.73
    BR
    1.64
     Br
    1.62
     Brus
    1.54
    Fr
    1.25
    Bel
    1.25
    Brand
    1.25
    Buff
    1.20
    Bron
    1.19
    Act Density 0.010%

    No Known Activations