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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs related to strength and power

    oai_token-act-pair · gpt-3.5-turbo

    aspects related to complex concepts and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Swanson
    -0.65
    Course
    -0.61
     Chong
    -0.58
    Exc
    -0.58
     Stack
    -0.57
    BuyableInstoreAndOnline
    -0.57
     Canaan
    -0.57
    PIN
    -0.57
     Somers
    -0.56
    TIT
    -0.56
    POSITIVE LOGITS
    ment
    1.26
    xual
    1.21
    cial
    1.16
    cies
    1.13
    ments
    1.13
    ration
    1.12
    tion
    1.08
    aign
    1.08
    ciation
    1.07
    ially
    1.07
    Act Density 0.425%

    No Known Activations