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

    Neuronpedia

    INDEX
    Explanations

    numeric values and configuration parameters in a structured format

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Datuak
    -1.27
    Билгалдахарш
    -1.13
    RTEE
    -1.13
     protoimpl
    -1.06
    StructEnd
    -1.06
    DeleteBehavior
    -1.06
    parsedMessage
    -1.06
    sizeCache
    -1.00
    featureID
    -1.00
     CreateTagHelper
    -0.99
    POSITIVE LOGITS
    ↵↵
    0.54
    ↵
    0.49
    .
    0.43
    <eos>
    0.41
     
    0.40
    hdessä
    0.37
    ↵↵↵
    0.36
     E
    0.36
    Read
    0.34
     Einfluss
    0.34
    Act Density 0.122%

    No Known Activations