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

    Neuronpedia

    INDEX
    Explanations

    references to fame and public figures in historical and cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     newcomer
    -0.15
    491
    -0.15
     independents
    -0.15
    ipo
    -0.14
    ')."
    -0.14
    Listeners
    -0.14
    ystems
    -0.13
    ugo
    -0.13
    arsers
    -0.13
    .IsNull
    -0.13
    POSITIVE LOGITS
     celebrities
    0.44
     celebrity
    0.39
     cele
    0.37
     stars
    0.34
     famous
    0.34
     personalities
    0.28
     Famous
    0.28
    stars
    0.25
     icons
    0.25
     Cele
    0.25
    Act Density 0.295%

    No Known Activations