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

    Neuronpedia

    INDEX
    Explanations

    keywords related to official agreements or procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to formal agreements and procedural activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Benz
    -0.66
    Ł
    -0.60
     Shack
    -0.57
    League
    -0.55
    âĸ¬
    -0.55
     Estate
    -0.53
     Raleigh
    -0.53
    Args
    -0.53
    Brother
    -0.53
     Beet
    -0.53
    POSITIVE LOGITS
    afety
    0.99
    poons
    0.96
    uggest
    0.93
     ranging
    0.93
    pring
    0.90
    heet
    0.88
    mith
    0.88
    poon
    0.88
    ometimes
    0.86
    pread
    0.83
    Act Density 0.338%

    No Known Activations