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

    Neuronpedia

    INDEX
    Explanations

    references to news sources or headlines

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "U" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Noir
    -0.90
     CPC
    -0.78
     CDs
    -0.72
     bottleneck
    -0.69
     Preferred
    -0.66
     offline
    -0.63
     Bach
    -0.62
     Solitaire
    -0.62
     Pioneer
    -0.62
     jams
    -0.62
    POSITIVE LOGITS
    seless
    1.22
    prising
    1.15
    nexpected
    1.14
    PDATED
    1.11
    pperc
    1.02
    berman
    1.02
    ntil
    1.01
    raviolet
    1.00
    zbek
    0.99
    CLA
    0.99
    Act Density 0.042%

    No Known Activations