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

    Neuronpedia

    INDEX
    Explanations

    references to specific lines or linear representations in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Campbell
    -0.43
    superuser
    -0.43
    mutlich
    -0.42
     poroz
    -0.42
     Scha
    -0.41
     desay
    -0.41
     Great
    -0.41
     Balth
    -0.41
    appspot
    -0.41
     Erst
    -0.40
    POSITIVE LOGITS
    Line
    1.33
     Line
    1.30
     line
    1.23
     LINE
    1.23
    line
    1.20
    LINE
    1.15
    Lines
    1.04
     Lines
    1.03
    lines
    1.02
     lines
    0.98
    Act Density 0.182%

    No Known Activations