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

    Neuronpedia

    INDEX
    Explanations

    statements related to legal proceedings and testimonies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tikang
    -0.74
     Aussi
    -0.70
    GEBURTS
    -0.69
    RegressionTest
    -0.62
     Савезне
    -0.62
    хьтан
    -0.60
     <<<<<<<<<<<<<<
    -0.58
    RegistryLite
    -0.57
    RefNanny
    -0.55
    Datuak
    -0.55
    POSITIVE LOGITS
     somebody
    0.52
     tomorrow
    0.52
    somebody
    0.51
    tomorrow
    0.51
     amanhã
    0.50
     even
    0.50
    حتى
    0.49
     yesterday
    0.49
     problemet
    0.49
     ourselves
    0.48
    Act Density 0.043%

    No Known Activations