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

    Neuronpedia

    INDEX
    Explanations

    phrases related to transformation or transitions into new forms or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    explique
    -0.45
    grunn
    -0.42
    RANGE
    -0.42
    Cevap
    -0.41
     introduced
    -0.40
     avut
    -0.40
     înce
    -0.39
    ofed
    -0.39
    introduced
    -0.39
     sə
    -0.38
    POSITIVE LOGITS
    WriteTagHelper
    0.89
     AssemblyCulture
    0.89
    ########.
    0.88
     autorytatywna
    0.87
    BeginContext
    0.86
     transférez
    0.85
     ujednoznacz
    0.80
     transfieras
    0.79
    ✨:
    0.75
    ImageContext
    0.74
    Act Density 0.478%

    No Known Activations