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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations or regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ard
    -0.17
     Swiss
    -0.16
     Egyptian
    -0.16
    ÑģÑĤÑĢÑĥ
    -0.15
     snakes
    -0.15
     Guerr
    -0.14
     Cher
    -0.14
     snake
    -0.14
    Egypt
    -0.14
    ÑĢап
    -0.14
    POSITIVE LOGITS
     Alaska
    0.36
     Arctic
    0.32
     Nome
    0.25
     sled
    0.25
     Yuk
    0.24
     Labrador
    0.22
     Siber
    0.21
     Lena
    0.20
    undra
    0.20
     Anch
    0.19
    Act Density 0.144%

    No Known Activations