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

    Neuronpedia

    INDEX
    Explanations

    references to lines or formatting instructions in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -1.25
     Monfieur
    -1.17
     juſt
    -0.99
     myſelf
    -0.97
    edicated
    -0.97
    bibinfo
    -0.96
     pleaſure
    -0.96
     himſelf
    -0.94
     deſt
    -0.91
     preſent
    -0.90
    POSITIVE LOGITS
     Line
    1.80
     LINE
    1.78
     line
    1.73
     lines
    1.70
    Line
    1.65
    line
    1.57
     Lines
    1.57
    LINE
    1.45
    Lines
    1.44
    lines
    1.40
    Act Density 0.118%

    No Known Activations