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

    Neuronpedia

    INDEX
    Explanations

    terminology and metrics related to circuits and their performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LEncoder
    -0.62
    quels
    -0.54
    […]
    -0.48
    Демографія
    -0.45
    MDB
    -0.45
    конец
    -0.44
    pédie
    -0.44
    cutt
    -0.44
     Many
    -0.43
     long
    -0.43
    POSITIVE LOGITS
     averaging
    1.12
     averaged
    1.06
     totaling
    1.05
     averages
    1.04
     totalling
    1.04
     totalled
    0.96
     totaled
    0.95
     amounting
    0.94
     average
    0.91
     estimated
    0.88
    Act Density 0.921%

    No Known Activations