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

    Neuronpedia

    INDEX
    Explanations

    references to the use of tasers in police incidents

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    orio
    -0.74
    erest
    -0.67
    ersen
    -0.61
    catentry
    -0.58
    ers
    -0.56
     Granger
    -0.56
    estine
    -0.56
     Patriarch
    -0.56
    orno
    -0.55
    endor
    -0.54
    POSITIVE LOGITS
    bang
    0.56
    pling
    0.56
    IUM
    0.56
    xes
    0.55
     choke
    0.54
    zer
    0.54
    idon
    0.54
    gency
    0.54
    ilities
    0.53
    rette
    0.53
    Act Density 9.461%

    No Known Activations