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

    Neuronpedia

    INDEX
    Explanations

    geographical locations and place names

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     يتيمه
    -1.11
     themſelves
    -0.90
     himſelf
    -0.89
     Sando
    -0.78
     Monfieur
    -0.78
     Abbe
    -0.77
     Erwin
    -0.77
     Betracht
    -0.77
     myſelf
    -0.77
     itſelf
    -0.77
    POSITIVE LOGITS
     Baltimore
    1.07
    Baltimore
    1.05
     Maryland
    0.97
    Maryland
    0.96
     Ravens
    0.88
    TIMORE
    0.80
     Orioles
    0.77
     Annapolis
    0.60
    Legături
    0.58
    "])){
    0.57
    Act Density 0.236%

    No Known Activations