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

    Neuronpedia

    INDEX
    Explanations

    terms related to politics and current events, especially concerning media coverage and public opinion

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rar
    -0.70
    NESS
    -0.69
    soDeliveryDate
    -0.68
    ONSORED
    -0.68
    anan
    -0.65
    wine
    -0.65
    Cola
    -0.64
    mask
    -0.63
    729
    -0.62
    far
    -0.62
    POSITIVE LOGITS
     behalf
    1.00
    etime
    0.94
    erous
    0.91
    eday
    0.90
     autop
    0.85
     arrival
    0.82
     purpose
    0.82
     cue
    0.82
     occasion
    0.81
     fumes
    0.81
    Act Density 0.170%

    No Known Activations