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

    Neuronpedia

    INDEX
    Explanations

    locations or geographical references

    oai_token-act-pair · gpt-3.5-turbo

    location names, particularly in relation to places in Mexico

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blitz
    -0.78
     Kitty
    -0.70
     Ukip
    -0.70
     Runes
    -0.70
     Wolves
    -0.70
     sled
    -0.69
     Krug
    -0.68
     Clarkson
    -0.68
     grooming
    -0.68
     Hawks
    -0.66
    POSITIVE LOGITS
    ÃŃa
    1.50
    án
    1.47
    ás
    1.45
    ño
    1.44
    ón
    1.42
    ú
    1.42
    ó
    1.37
    acion
    1.36
    encia
    1.35
    ÃŃ
    1.33
    Act Density 0.360%

    No Known Activations