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

    Neuronpedia

    INDEX
    Explanations

    the continuous form of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    findpost
    -0.91
    fecture
    -0.81
    protoc
    -0.77
     BoxDecoration
    -0.75
     disambiguazione
    -0.75
    prefixer
    -0.73
    Liens
    -0.73
     Aras
    -0.72
    ViewFeatures
    -0.71
    Moe
    -0.70
    POSITIVE LOGITS
     venne
    0.72
     veniva
    0.70
     oleh
    0.69
     vengono
    0.69
     wordt
    0.69
    dymyr
    0.68
    ····
    0.68
     worden
    0.68
     viene
    0.67
     ถูก
    0.66
    Act Density 0.068%

    No Known Activations