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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to headquarters (HQ)

    oai_token-act-pair · gpt-3.5-turbo

    references to headquarters or notable locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -0.85
    fin
    -0.79
    Pac
    -0.77
    agues
    -0.77
    flies
    -0.70
    Austral
    -0.68
    ×ij
    -0.67
     ages
    -0.67
    ozo
    -0.66
    é¾į
    -0.66
    POSITIVE LOGITS
     HQ
    1.13
    yrinth
    1.05
     Headquarters
    0.81
    eteria
    0.81
    HQ
    0.80
    ynthesis
    0.78
    paio
    0.78
     lapt
    0.78
     workspace
    0.76
     sergeant
    0.75
    Act Density 0.006%

    No Known Activations