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

    Neuronpedia

    INDEX
    Explanations

    airport codes and government-related terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    BIP
    -1.13
    lly
    -1.05
    bt
    -1.05
    lda
    -1.04
    ppe
    -1.03
    bek
    -0.99
    STEM
    -0.97
    PDATE
    -0.96
    Äĩ
    -0.96
    PRESS
    -0.95
    POSITIVE LOGITS
    artisan
    1.33
    itect
    1.27
    arine
    1.25
    orage
    1.23
    eur
    1.18
    ieri
    1.15
    oir
    1.14
    heses
    1.10
    aires
    1.09
    al
    1.08
    Act Density 1.468%

    No Known Activations