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

    Neuronpedia

    INDEX
    Explanations

    names, specifically "Rupert"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Rupert Murdoch and related figures in the context of media or news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assian
    -0.83
    ngth
    -0.75
    activated
    -0.71
     Helsinki
    -0.70
    ccording
    -0.68
    atchewan
    -0.68
    agher
    -0.67
    omething
    -0.67
    href
    -0.66
    pmwiki
    -0.66
    POSITIVE LOGITS
     Murdoch
    1.34
     Rupert
    1.20
    iev
    0.84
    Net
    0.78
    Ru
    0.78
    rey
    0.76
    shire
    0.74
     Hoo
    0.73
    ython
    0.73
     Giles
    0.72
    Act Density 0.008%

    No Known Activations