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

    Neuronpedia

    INDEX
    Explanations

    structured code snippets

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Már
    -0.48
    Tó
    -0.45
     Trade
    -0.44
     extremamente
    -0.43
    peny
    -0.42
    Avantages
    -0.42
    Allister
    -0.42
    Gabri
    -0.42
    Woj
    -0.42
    squareup
    -0.41
    POSITIVE LOGITS
    null
    0.90
     poft
    0.88
     null
    0.87
     Null
    0.87
     cabrio
    0.83
     nutella
    0.82
    Null
    0.81
    quarelle
    0.79
     inext
    0.78
    capulco
    0.77
    Act Density 0.076%

    No Known Activations