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

    Neuronpedia

    INDEX
    Explanations

    references to community infrastructure and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     modulus
    -0.15
    è·Ŀ
    -0.15
     çķ
    -0.15
    abet
    -0.15
    ãĥ¼ãĥģ
    -0.14
    agnost
    -0.14
    enda
    -0.13
    маÑħ
    -0.13
    unei
    -0.13
    SearchTree
    -0.13
    POSITIVE LOGITS
     town
    0.27
     foot
    0.25
     shop
    0.25
     shopping
    0.24
     Shop
    0.24
     regenerate
    0.23
     shops
    0.23
     regenerated
    0.23
     trader
    0.22
     Shopping
    0.22
    Act Density 0.021%

    No Known Activations