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

    Neuronpedia

    INDEX
    Explanations

    references to celestial bodies and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to deities and significant cultural symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xus
    -0.84
    orthy
    -0.82
    OME
    -0.76
    ascript
    -0.74
    cffff
    -0.74
    oS
    -0.72
    devices
    -0.71
    igi
    -0.70
    adow
    -0.70
    icken
    -0.70
    POSITIVE LOGITS
     Amos
    0.82
     Hannah
    0.81
     Artemis
    0.81
     William
    0.80
     Rudolph
    0.79
     Theodore
    0.78
     Martha
    0.76
     Herod
    0.75
     itself
    0.72
     Garry
    0.72
    Act Density 0.325%

    No Known Activations