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

    Neuronpedia

    INDEX
    Explanations

    concepts related to balance and equilibrium in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zin
    -0.18
    enames
    -0.17
    ebi
    -0.17
    ollah
    -0.16
    PACE
    -0.15
    ling
    -0.15
    lum
    -0.15
    ÑĩаÑĤ
    -0.15
    sWith
    -0.15
    tuk
    -0.14
    POSITIVE LOGITS
    balance
    0.32
     balance
    0.29
     Balance
    0.26
    (balance
    0.26
    -bal
    0.25
    bal
    0.25
     Balanced
    0.24
     bal
    0.22
     balances
    0.22
     balancing
    0.22
    Act Density 0.024%

    No Known Activations