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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating changes or differences in conditions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ichè
    -0.45
    createStatement
    -0.44
    intellij
    -0.41
    tium
    -0.41
    ‌
    -0.41
     grosso
    -0.41
    tableFuture
    -0.40
    sell
    -0.40
    Cancellation
    -0.40
    hip
    -0.39
    POSITIVE LOGITS
    aarrggbb
    0.84
    Rüyada
    0.81
     EconPapers
    0.72
    RegressionTest
    0.71
    AddTagHelper
    0.71
     externi
    0.70
    Personendaten
    0.68
    tonode
    0.68
    úgó
    0.68
    ftagPool
    0.68
    Act Density 0.897%

    No Known Activations