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

    Neuronpedia

    INDEX
    Explanations

    editorial credits in news articles

    oai_token-act-pair · gpt-3.5-turbo

    text related to authorship and editing credits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gdala
    -0.76
     evid
    -0.74
    viation
    -0.69
     certs
    -0.69
    tera
    -0.69
    gew
    -0.69
    sbm
    -0.68
     scrimmage
    -0.67
     bragging
    -0.67
     guiName
    -0.66
    POSITIVE LOGITS
     Editing
    0.82
    Edited
    0.79
     editing
    0.79
     translator
    0.78
     Rupert
    0.71
     NPR
    0.67
     Jazeera
    0.67
     UNHCR
    0.67
    ARDIS
    0.66
     adapted
    0.65
    Act Density 0.093%

    No Known Activations