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

    Neuronpedia

    INDEX
    Explanations

    instances of high numerical values or metrics related to weight and measurements, potentially indicating statistical comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bizarre
    -0.45
    —
    -0.44
     tắm
    -0.42
    рованного
    -0.42
     peculiar
    -0.42
     «
    -0.42
     reduction
    -0.41
    とする
    -0.41
    思議
    -0.40
    翼
    -0.39
    POSITIVE LOGITS
    enumi
    7.66
    enumii
    4.61
    findpost
    1.44
     CreateTagHelper
    1.41
    ValueStyle
    1.37
    AndEndTag
    1.33
     AssemblyCompany
    1.32
     MainAxisSize
    1.31
    CloseOperation
    1.25
     EconPapers
    1.22
    Act Density 0.003%

    No Known Activations