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

    Neuronpedia

    INDEX
    Explanations

    names of news organizations and journalists

    oai_token-act-pair · gpt-3.5-turbo

    mentions of organizations and entities involved in news reporting or media contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shant
    -0.61
     sucker
    -0.60
     awoken
    -0.59
    eric
    -0.57
    dies
    -0.57
     Stall
    -0.57
    animate
    -0.56
    range
    -0.56
     Valve
    -0.56
    itars
    -0.56
    POSITIVE LOGITS
     Magazine
    1.17
     Editorial
    1.16
     editorial
    1.11
    Magazine
    1.10
     magazine
    1.09
     editors
    1.00
     News
    0.99
     contributor
    0.99
     readers
    0.98
     Editors
    0.98
    Act Density 0.250%

    No Known Activations