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

    Neuronpedia

    INDEX
    Explanations

    HTML elements and formatting tags within a text document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML tags and <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.68
    WithIOException
    -0.57
     propOrder
    -0.56
    ########.
    -0.56
     "..\..\..\
    -0.54
     "..\..\
    -0.54
    ̈́
    -0.53
     EconPapers
    -0.52
    SequentialGroup
    -0.50
     IBOutlet
    -0.48
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.63
     explaining
    0.47
     étoit
    0.45
     pointing
    0.43
     étoient
    0.40
     contó
    0.38
    AccessorTable
    0.36
    ChrTalk
    0.36
    Explain
    0.36
     explain
    0.36
    Act Density 0.014%

    No Known Activations