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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scandals and controversial events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    hetics
    -0.69
    cki
    -0.66
    requisite
    -0.66
    eele
    -0.64
    */(
    -0.64
    lasses
    -0.62
     Swords
    -0.62
    ramer
    -0.61
    icrobial
    -0.61
    ignty
    -0.60
    POSITIVE LOGITS
     involving
    1.08
    ous
    1.03
     scandals
    1.01
     plag
    0.99
    ously
    0.99
     revolving
    0.95
     scandal
    0.94
    icity
    0.91
     engulf
    0.90
     erupted
    0.89
    Act Density 0.048%

    No Known Activations