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

    Neuronpedia

    INDEX
    Explanations

    key-value pairs in JSON-like data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -1.13
    ')}}"
    -0.88
    '])){
    -0.83
    ']))
    -0.80
    windowFixed
    -0.79
    ]));
    -0.78
     betweenstory
    -0.78
    WriteBarrier
    -0.75
    '])->
    -0.75
    ')}}
    -0.75
    POSITIVE LOGITS
    all
    0.48
    od
    0.45
    stretchr
    0.45
    nal
    0.43
    بور
    0.39
    ALL
    0.39
    ost
    0.39
    chowa
    0.39
     rodea
    0.38
    I
    0.38
    Act Density 0.141%

    No Known Activations