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

    Neuronpedia

    INDEX
    Explanations

    references to weight or intensity, particularly relating to the term "heavy"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -1.05
    Hochspringen
    -0.79
     QName
    -0.70
    MessageTagHelper
    -0.68
     Trustees
    -0.66
     незавершена
    -0.66
     Roost
    -0.65
     trustees
    -0.65
    uluş
    -0.65
    Aloe
    -0.63
    POSITIVE LOGITS
     Heavy
    1.26
    Heavy
    1.25
     heavy
    1.24
    heavy
    1.20
     HEAVY
    1.19
     heaviest
    1.05
    AVY
    1.02
     Heav
    1.02
     Schwer
    0.96
    heav
    0.96
    Act Density 0.056%

    No Known Activations