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

    Neuronpedia

    INDEX
    Explanations

    phrases related to locations and specific geographical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xdb
    -0.35
     Sochi
    -0.35
    PhysRev
    -0.31
    Coordonnées
    -0.31
     Chaldean
    -0.30
     Iraqi
    -0.30
     Somali
    -0.30
     peruano
    -0.30
     bewer
    -0.28
     aanges
    -0.28
    POSITIVE LOGITS
     Taiwan
    1.86
     Taiwanese
    1.74
    Taiwan
    1.67
     Taipei
    1.61
     taiwan
    1.46
     Formosa
    1.23
    台湾
    1.13
     台湾
    1.02
     Tsai
    0.98
    Tai
    0.97
    Act Density 0.117%

    No Known Activations