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

    Neuronpedia

    INDEX
    Explanations

    text related to political events and social issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Ô
    -0.78
    Downloadha
    -0.72
    quickShipAvailable
    -0.72
    emis
    -0.71
     trustworthy
    -0.69
    Ĥİ
    -0.69
     pestic
    -0.68
    rawdownloadcloneembedreportprint
    -0.67
    oslav
    -0.67
     stabilization
    -0.67
    POSITIVE LOGITS
     innocence
    0.82
    otted
    0.78
    oppers
    0.78
    ioned
    0.77
    urch
    0.75
    kes
    0.72
     Detention
    0.71
    opter
    0.69
    uckle
    0.69
    ults
    0.69
    Act Density 1.464%

    No Known Activations