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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data collection and privacy concerns

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bos
    -0.82
     Buddh
    -0.71
     Blizz
    -0.69
     Buddhism
    -0.67
     Bron
    -0.65
    Hart
    -0.63
     Doors
    -0.63
     Tasman
    -0.62
     Ri
    -0.62
     Heroes
    -0.61
    POSITIVE LOGITS
    rogens
    1.00
    pload
    0.94
     manipulate
    0.87
     consume
    0.85
     discard
    0.84
    rehend
    0.83
    hold
    0.83
     distribute
    0.83
     dissemin
    0.83
     consumes
    0.82
    Act Density 0.099%

    No Known Activations