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

    Neuronpedia

    INDEX
    Explanations

    numerical values and percentages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     &___
    -0.79
     <<<<<<<<<<<<<<
    -0.64
     intptr
    -0.62
    👏👏
    -0.62
    wahlen
    -0.60
    λικά
    -0.60
     Compagn
    -0.60
     gathers
    -0.60
     Ayo
    -0.59
    יבות
    -0.59
    POSITIVE LOGITS
     téléphonique
    0.63
    zeiti
    0.62
     hvilken
    0.61
     aDecoder
    0.60
    mTitle
    0.57
     متعلقه
    0.56
     للمعارف
    0.56
     coûts
    0.55
     boî
    0.55
     multic
    0.55
    Act Density 0.131%

    No Known Activations