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

    Neuronpedia

    INDEX
    Explanations

    special characters with specific numerical values that seem to be unique identifiers in the text

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the character 'Ģ'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raints
    -0.77
    ifications
    -0.63
    enegger
    -0.62
    ified
    -0.60
    papers
    -0.59
     wid
    -0.59
     birth
    -0.58
     patches
    -0.58
     papers
    -0.58
    opian
    -0.57
    POSITIVE LOGITS
    Ģ
    1.34
    âĶĢâĶĢâĶĢâĶĢ
    0.94
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.93
    λ
    0.90
    ĭ
    0.89
    OTE
    0.88
    ģ
    0.88
    ilus
    0.86
    hoe
    0.82
    âĶĢâĶĢ
    0.82
    Act Density 0.004%

    No Known Activations