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

    Neuronpedia

    INDEX
    Explanations

    references to digital or online interactions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    defs
    -0.17
    izia
    -0.15
     Haz
    -0.15
    ae
    -0.14
    TextWriter
    -0.14
    _slug
    -0.14
     Yates
    -0.13
     Bris
    -0.13
     createState
    -0.13
     kost
    -0.13
    POSITIVE LOGITS
     activity
    0.26
     movements
    0.24
     Activity
    0.23
    activity
    0.21
     usage
    0.21
    Activity
    0.20
     history
    0.20
     Usage
    0.20
     browsing
    0.20
    usage
    0.20
    Act Density 0.107%

    No Known Activations