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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "apple" and its variations in contexts related to movement or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    suje
    -0.49
    goi
    -0.47
    msubsup
    -0.47
    RIEL
    -0.44
    NewReader
    -0.44
     Loop
    -0.43
    anillo
    -0.43
    podar
    -0.42
    śle
    -0.42
     loop
    -0.42
    POSITIVE LOGITS
     Balance
    1.08
     balance
    1.02
     équilibre
    1.00
     imbalance
    0.98
    balance
    0.97
     tipping
    0.96
    Balance
    0.94
     unbalanced
    0.93
     balances
    0.93
     Balancing
    0.92
    Act Density 0.306%

    No Known Activations