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

    Neuronpedia

    INDEX
    Explanations

    distinct tokens or identifiers in structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    1
    -0.58
    -
    -0.54
    3
    -0.53
    4
    -0.51
    2
    -0.50
    ...
    -0.48
    0
    -0.47
     (
    -0.47
    8
    -0.47
     or
    -0.46
    POSITIVE LOGITS
    Datuak
    1.40
     kaarangay
    1.36
    Personendaten
    1.34
    TagMode
    1.33
    InjectAttribute
    1.28
    ंदीखरीदारी
    1.25
    ValueStyle
    1.24
     EconPapers
    1.23
     beginnetje
    1.22
    Autoritní
    1.21
    Act Density 0.090%

    No Known Activations