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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rüyada
    -0.62
    MessageTagHelper
    -0.57
     EconPapers
    -0.53
     itself
    -0.49
     ourselves
    -0.48
     ModelExpression
    -0.48
     himself
    -0.47
    InSection
    -0.46
     themselves
    -0.46
    webElementGuid
    -0.45
    POSITIVE LOGITS
     reminding
    0.60
     letting
    0.52
    featureID
    0.52
     noticing
    0.47
    GenerationType
    0.47
     reminder
    0.47
     taking
    0.47
     allowing
    0.47
    AccessorTable
    0.47
     sparing
    0.46
    Act Density 0.140%

    No Known Activations