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

    Neuronpedia

    INDEX
    Explanations

    usernames or handles

    oai_token-act-pair · gpt-3.5-turbo

    users or references to content creators on social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     UNESCO
    -0.92
     financing
    -0.91
     ÂŃ
    -0.88
     newspapers
    -0.84
     profitable
    -0.83
     backward
    -0.82
     fulfilling
    -0.82
     succession
    -0.82
     textbooks
    -0.81
     appointments
    -0.81
    POSITIVE LOGITS
    gamer
    1.29
    bear
    1.25
    guy
    1.23
    Gamer
    1.23
    crow
    1.22
    kid
    1.21
    yip
    1.20
    Gaming
    1.17
    wolf
    1.16
    maxwell
    1.16
    Act Density 0.312%

    No Known Activations