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

    Neuronpedia

    INDEX
    Explanations

    mentions of criminal activities or controversial events in news articles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wander
    -0.66
     Horizons
    -0.66
     Leilan
    -0.66
     Paran
    -0.65
     Prol
    -0.62
     Seller
    -0.61
     Vert
    -0.59
     Remix
    -0.59
     Tsukuyomi
    -0.59
     Annotations
    -0.58
    POSITIVE LOGITS
    rates
    0.69
     looph
    0.64
     categ
    0.60
    âĢİ
    0.59
     adolesc
    0.57
    ĵĺ
    0.57
    efficients
    0.57
    acting
    0.56
    Õ
    0.55
     urged
    0.55
    Act Density 0.085%

    No Known Activations