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

    Neuronpedia

    INDEX
    Explanations

    references to specific terrorist organizations and leaders

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Laur
    -0.68
    livious
    -0.66
     Poles
    -0.65
     Wilde
    -0.65
     Warp
    -0.64
     EVE
    -0.64
     crochet
    -0.64
     erection
    -0.62
     Victoria
    -0.61
     Polar
    -0.60
    POSITIVE LOGITS
    azeera
    1.27
    aeda
    1.11
    aghd
    1.00
    abi
    0.98
    qqa
    0.98
    awi
    0.96
    adr
    0.95
    adi
    0.90
    aq
    0.90
    aida
    0.89
    Act Density 0.079%

    No Known Activations