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

    Neuronpedia

    INDEX
    Explanations

    references to temperature and heat-related descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jScrollPane
    -0.57
    SupportActionBar
    -0.57
     الرياضيه
    -0.57
    seamnă
    -0.56
     benchmarking
    -0.55
     useParams
    -0.54
    teau
    -0.54
     bench
    -0.52
    WriteTagHelper
    -0.52
    OIS
    -0.51
    POSITIVE LOGITS
     warm
    0.66
    Warm
    0.58
    warm
    0.55
     Warm
    0.55
     WARM
    0.54
     warmed
    0.46
    WARM
    0.45
    温
    0.43
    Hot
    0.43
     quente
    0.42
    Act Density 0.464%

    No Known Activations