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

    Neuronpedia

    INDEX
    Explanations

    geographical locations and administrative divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ainfi
    -1.20
     nôtre
    -1.02
     auroit
    -1.01
     enfans
    -1.01
     étoient
    -1.01
     auffi
    -1.01
     Houſe
    -1.00
     houſe
    -1.00
     avoient
    -0.99
     fédé
    -0.98
    POSITIVE LOGITS
     French
    1.13
     France
    1.13
     Paris
    0.97
    France
    0.96
    French
    0.93
     french
    0.91
    法国
    0.84
    Paris
    0.82
    PARIS
    0.81
    FRANCE
    0.77
    Act Density 0.347%

    No Known Activations