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

    Neuronpedia

    INDEX
    Explanations

    opinion pieces or editorials in newspapers or magazines

    oai_token-act-pair · gpt-3.5-turbo

    references to opinion pieces in media publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     controls
    -0.75
     customs
    -0.72
     embryos
    -0.70
     transporter
    -0.70
     restrooms
    -0.67
     Saiyan
    -0.65
     toilets
    -0.62
    artifacts
    -0.62
     rusty
    -0.61
     genders
    -0.61
    POSITIVE LOGITS
     titled
    1.25
     headlined
    1.03
     entitled
    1.02
     penned
    0.95
     published
    0.93
    itled
    0.92
     reprinted
    0.89
     editor
    0.82
     excerpt
    0.82
     essay
    0.81
    Act Density 0.143%

    No Known Activations