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

    Neuronpedia

    INDEX
    Explanations

    comparative and superlative adjectives or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.60
    StructEnd
    -0.49
     Houſe
    -0.48
    XmlEnum
    -0.47
    enderror
    -0.43
    pexpr
    -0.42
     externi
    -0.42
    twimg
    -0.42
     архивлан
    -0.42
    AndroidJUnit
    -0.42
    POSITIVE LOGITS
     better
    1.13
    better
    1.05
     Better
    1.05
    Better
    1.03
     BETTER
    0.96
     harder
    0.96
     clearer
    0.95
     happier
    0.94
     brighter
    0.94
     sharper
    0.94
    Act Density 1.185%

    No Known Activations