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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     AAA
    -0.66
     Victorian
    -0.66
     hover
    -0.63
    âĶĢâĶĢ
    -0.62
     litter
    -0.62
     proto
    -0.62
     fragmented
    -0.62
     Highlander
    -0.61
     Cerberus
    -0.61
     Aboriginal
    -0.60
    POSITIVE LOGITS
    inski
    1.12
    insky
    1.10
    auer
    1.08
    ucci
    1.06
    ahl
    1.05
    enson
    1.05
    assi
    1.05
    zel
    1.04
    iani
    1.03
    ettel
    1.02
    Act Density 0.341%

    No Known Activations