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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.99
     Monfieur
    -0.79
    extAlignment
    -0.79
     Beſ
    -0.74
     Diſ
    -0.72
     ſeveral
    -0.70
     greateſt
    -0.70
     ſche
    -0.69
     Anſ
    -0.68
     Efq
    -0.68
    POSITIVE LOGITS
     Expert
    0.60
    Expert
    0.56
     expert
    0.56
     services
    0.56
     expertise
    0.54
     Services
    0.54
     consulting
    0.53
     Consulting
    0.52
    services
    0.51
     consultancy
    0.51
    Act Density 0.219%

    No Known Activations