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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to location and geographical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Digest
    -0.17
     Digest
    -0.17
     though
    -0.15
     digest
    -0.15
     parks
    -0.15
    arat
    -0.15
    arkan
    -0.15
    digest
    -0.14
    forum
    -0.14
     Cathedral
    -0.14
    POSITIVE LOGITS
     village
    0.70
     villages
    0.58
     Village
    0.58
    æĿij
    0.56
     villagers
    0.47
     ham
    0.46
     settlement
    0.41
    illage
    0.40
     settlements
    0.39
     vill
    0.39
    Act Density 0.170%

    No Known Activations