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

    Neuronpedia

    INDEX
    Explanations

    dates and specific public figures closely tied to news events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    $$
    -0.69
    ynt
    -0.68
    uum
    -0.64
    arat
    -0.63
    anan
    -0.63
    arth
    -0.61
    BIP
    -0.58
    ults
    -0.58
    oler
    -0.58
    Feed
    -0.57
    POSITIVE LOGITS
     behalf
    1.51
     Thursday
    1.12
    shore
    1.09
     Wednesday
    1.09
     Friday
    1.05
    etime
    1.05
    erous
    1.05
     September
    1.04
     Monday
    1.04
    etheless
    1.04
    Act Density 0.193%

    No Known Activations