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

    Neuronpedia

    INDEX
    Explanations

    structural or architectural features and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     klu
    -0.15
    afia
    -0.14
    สà¸ķ
    -0.13
     gros
    -0.13
    reau
    -0.13
    fur
    -0.13
    ihan
    -0.12
     primal
    -0.12
     bytearray
    -0.12
     Contracts
    -0.12
    POSITIVE LOGITS
     tower
    0.29
     skys
    0.29
     buildings
    0.27
     towers
    0.27
     castle
    0.27
     dirig
    0.25
     mountain
    0.25
     structure
    0.24
     Tower
    0.24
     structures
    0.24
    Act Density 0.099%

    No Known Activations