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

    Neuronpedia

    INDEX
    Explanations

    references to supplementary information, figures, or tables

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    Supply
    -1.38
     supply
    -1.33
     SUPPLY
    -1.33
     Supply
    -1.30
    supply
    -1.23
     suppress
    -1.16
    SUPPLY
    -1.16
     Supplies
    -1.14
     suppression
    -1.12
     Suppression
    -1.12
    POSITIVE LOGITS
    supp
    1.11
     CreateTagHelper
    0.70
    FieldDescriptor
    0.60
    dern
    0.59
     committed
    0.56
    ➟
    0.55
    prepareStatement
    0.52
    phir
    0.50
     bere
    0.50
    мб
    0.50
    Act Density 0.005%

    No Known Activations