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

    Neuronpedia

    INDEX
    Explanations

    names related to media and ownership in news reporting

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    warm
    -0.82
    RNA
    -0.81
    artifacts
    -0.81
    ppo
    -0.80
    cession
    -0.78
    adena
    -0.76
    externalActionCode
    -0.76
    activated
    -0.76
    atos
    -0.75
    merga
    -0.75
    POSITIVE LOGITS
     Murdoch
    1.37
     tabloid
    1.00
     mog
    0.91
     Tycoon
    0.86
     tabl
    0.81
     Newsp
    0.79
     newspapers
    0.79
     columnist
    0.78
     Mail
    0.75
    lisher
    0.75
    Act Density 0.033%

    No Known Activations