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

    Neuronpedia

    INDEX
    Explanations

    phrases related to change and improvement over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     genom
    -0.46
     She
    -0.45
     Türkei
    -0.42
    蔵
    -0.41
    водства
    -0.41
    Converted
    -0.40
     gemein
    -0.40
     devoirs
    -0.40
    Serialization
    -0.40
    She
    -0.39
    POSITIVE LOGITS
    клопе
    0.95
     שוליים
    0.84
     things
    0.84
     kasarigan
    0.80
     snippetHide
    0.79
    featureID
    0.79
     <>",
    0.79
     trajets
    0.79
     Roskov
    0.78
    things
    0.77
    Act Density 0.285%

    No Known Activations