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

    Neuronpedia

    INDEX
    Explanations

    sentences with specific patterns, such as "X is Y" or "Y in Z"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of causality and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.66
    etc
    -0.65
    urrencies
    -0.63
     mosqu
    -0.60
    ussia
    -0.56
     alot
    -0.55
     cryptocurrencies
    -0.55
     cryptoc
    -0.55
     Marijuana
    -0.53
     Trafford
    -0.53
    POSITIVE LOGITS
    sequent
    0.79
    Instead
    0.68
    Correction
    0.67
     subsequent
    0.64
     afterward
    0.60
    éĸ
    0.58
     recal
    0.57
     thereafter
    0.56
     predecessor
    0.56
     hadn
    0.55
    Act Density 1.782%

    No Known Activations