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

    Neuronpedia

    INDEX
    Explanations

    references to various types of tea and related beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spender
    -0.17
     dispens
    -0.15
    تاب
    -0.14
    ÑĢÑĥн
    -0.14
    ernel
    -0.14
    ALSE
    -0.14
    dden
    -0.13
    597
    -0.13
    bart
    -0.13
     Rash
    -0.13
    POSITIVE LOGITS
     teas
    0.21
     Broken
    0.20
     rolled
    0.20
     pek
    0.20
     tips
    0.19
     Silver
    0.19
     wir
    0.18
     Tie
    0.18
     twisted
    0.18
     leaf
    0.18
    Act Density 0.003%

    No Known Activations