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

    Neuronpedia

    INDEX
    Explanations

    text that refers to something being specialized or unique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -1.02
     Houſe
    -0.87
     Cæsar
    -0.81
     Monfieur
    -0.81
     Majefty
    -0.80
     houſe
    -0.80
     Chriftian
    -0.79
     <<<<<<<<<<<<<<
    -0.78
     photolibrary
    -0.76
     mourut
    -0.76
    POSITIVE LOGITS
     special
    1.39
    special
    1.13
     specialized
    1.07
     Special
    1.03
     speciale
    1.00
     speciali
    1.00
    Special
    0.99
     specially
    0.94
     विशेष
    0.93
     specialised
    0.92
    Act Density 0.034%

    No Known Activations