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

    Neuronpedia

    INDEX
    Explanations

    patterns of numerical or coded data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.95
     best
    -0.91
     лучших
    -0.84
     terbaik
    -0.80
    best
    -0.79
    AddTagHelper
    -0.78
     луч
    -0.77
    Best
    -0.76
     Best
    -0.76
     лучшие
    -0.74
    POSITIVE LOGITS
    toHave
    0.48
     VOW
    0.42
    Искәрмәләр
    0.42
    filet
    0.42
    vinger
    0.41
    fvar
    0.40
    ormány
    0.39
    éia
    0.39
    特别是
    0.39
    ahul
    0.38
    Act Density 0.490%

    No Known Activations