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

    Neuronpedia

    INDEX
    Explanations

    mentions of unnamed individuals in news reports

    oai_token-act-pair · gpt-3.5-turbo

    references to unnamed or unidentified individuals or sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    byss
    -0.80
    akings
    -0.78
    ometers
    -0.76
    blems
    -0.75
    achine
    -0.73
    cdn
    -0.72
    ORPG
    -0.71
    arium
    -0.70
    Ont
    -0.70
    lov
    -0.70
    POSITIVE LOGITS
     unnamed
    0.97
     narrator
    0.90
     persons
    0.77
     unidentified
    0.74
     bystand
    0.73
     anonymous
    0.73
    iated
    0.70
     sources
    0.70
     whistleblower
    0.69
     sourcing
    0.68
    Act Density 0.020%

    No Known Activations