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

    Neuronpedia

    INDEX
    Explanations

    terms related to growth or increase in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ke
    -0.52
    ItemGroup
    -0.51
     mão
    -0.51
     pezzo
    -0.50
     ensaio
    -0.50
     apaixon
    -0.50
     dago
    -0.49
     dintr
    -0.49
    Gossip
    -0.49
     nimic
    -0.48
    POSITIVE LOGITS
     increased
    1.49
    Increased
    1.43
    increased
    1.37
     Increased
    1.34
     improved
    1.31
    improved
    1.26
    Improved
    1.21
     Improved
    1.19
     decreased
    1.13
     enhanced
    1.09
    Act Density 0.250%

    No Known Activations