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

    Neuronpedia

    INDEX
    Explanations

    automotive features and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     compact
    -0.16
    iets
    -0.16
    arios
    -0.16
     Compact
    -0.15
    compact
    -0.15
    tplib
    -0.14
    828
    -0.14
    itten
    -0.13
    anning
    -0.13
     oper
    -0.13
    POSITIVE LOGITS
     interior
    0.23
     exterior
    0.22
     upgrades
    0.21
     Exterior
    0.21
     trim
    0.19
     package
    0.19
     packages
    0.19
     delete
    0.19
     Interior
    0.19
    Interior
    0.18
    Act Density 0.042%

    No Known Activations