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

    Neuronpedia

    INDEX
    Explanations

    phrases related to qualities, trends, and behavior without a specific focus on a single topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the reputation or notoriety of various entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     viz
    -0.61
     obser
    -0.58
    ?".
    -0.56
     behav
    -0.56
    would
    -0.55
    Is
    -0.54
     thereof
    -0.54
    actual
    -0.53
    tnc
    -0.53
    OTO
    -0.53
    POSITIVE LOGITS
     Dempsey
    0.58
     decentral
    0.55
     saddened
    0.55
     hugely
    0.53
     buoy
    0.53
     decentralized
    0.52
     synonymous
    0.52
    steamapps
    0.51
    ablished
    0.51
     premiere
    0.51
    Act Density 0.888%

    No Known Activations