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

    Neuronpedia

    INDEX
    Explanations

    locations and events related to news stories or legal cases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    MODE
    -0.69
     cruc
    -0.64
    RL
    -0.62
    $$
    -0.60
    ennes
    -0.58
     choke
    -0.57
    amus
    -0.56
    lements
    -0.56
    QB
    -0.56
    Includes
    -0.55
    POSITIVE LOGITS
    slaught
    1.29
     behalf
    1.23
    coming
    1.16
     occasion
    1.09
    look
    1.06
    etime
    1.03
    eness
    0.97
    sight
    0.95
     July
    0.93
    shore
    0.92
    Act Density 0.061%

    No Known Activations