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

    Neuronpedia

    INDEX
    Explanations

    pipe characters used in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nawr
    -0.78
     Arca
    -0.75
    ensement
    -0.69
    gäng
    -0.69
    nesc
    -0.68
    ekš
    -0.68
    cob
    -0.65
     arca
    -0.65
     Treff
    -0.64
    GeneratedValue
    -0.64
    POSITIVE LOGITS
     |
    1.40
     $|
    1.31
    +|
    1.18
    ]|
    1.14
    .|
    1.12
    "|
    1.12
    $|
    1.10
    '|
    1.10
     $|\
    1.10
    {|
    1.07
    Act Density 0.085%

    No Known Activations