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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities, dates, or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Italij
    -0.46
     vodi
    -0.45
     kapturem
    -0.45
     desertcart
    -0.45
     extranjero
    -0.44
     desmotivaciones
    -0.43
     compréhen
    -0.42
    -0.42
     gră
    -0.42
     ganchillo
    -0.40
    POSITIVE LOGITS
     Raw
    1.00
     RAW
    0.90
    Raw
    0.88
    RAW
    0.81
     raw
    0.73
     Smack
    0.73
     WWE
    0.72
    raw
    0.71
    Smack
    0.65
    WWE
    0.64
    Act Density 0.259%

    No Known Activations