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

    Neuronpedia

    INDEX
    Explanations

    references to sand and its various contexts or uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aandacht
    -0.64
    Callable
    -0.56
     grø
    -0.56
    internalType
    -0.54
    doj
    -0.52
     aguas
    -0.51
     piscine
    -0.50
    asible
    -0.49
    êche
    -0.48
    Dissolved
    -0.48
    POSITIVE LOGITS
     sand
    1.58
    Sand
    1.42
    sand
    1.41
     Sand
    1.39
     SAND
    1.31
    SAND
    1.15
     sandwich
    1.04
     Sandwich
    0.93
    sandwich
    0.93
     sands
    0.92
    Act Density 0.091%

    No Known Activations