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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to engineering or medical models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.17
     Gang
    -0.17
    robat
    -0.16
    -0.15
     auxiliary
    -0.14
    uky
    -0.14
     Hive
    -0.14
     rak
    -0.14
     gang
    -0.14
    issance
    -0.14
    POSITIVE LOGITS
     loading
    0.27
     biome
    0.26
     loads
    0.26
     Loads
    0.25
     Loading
    0.25
     Load
    0.24
    -loading
    0.24
     load
    0.24
     unloaded
    0.23
    loads
    0.22
    Act Density 0.010%

    No Known Activations