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

    Neuronpedia

    INDEX
    Explanations

    the concept of happiness and references to gas in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
      
    -0.43
    -
    -0.43
    –
    -0.42
     “
    -0.40
    ↵
    -0.40
    co
    -0.38
    al
    -0.38
     
    -0.37
    /
    -0.37
     Pinto
    -0.36
    POSITIVE LOGITS
    ftagPool
    0.94
     queſta
    0.92
    ंदीखरीदारी
    0.92
    <unused79>
    0.89
    <unused23>
    0.88
    <unused14>
    0.88
    <unused28>
    0.88
    majánló
    0.88
    [@BOS@]
    0.88
    <unused8>
    0.88
    Act Density 0.299%

    No Known Activations