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

    Neuronpedia

    INDEX
    Explanations

    phrases related to types or categories

    oai_token-act-pair · gpt-3.5-turbo

    discussions about various types of tools and features available in online platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iannopoulos
    -0.69
    fuck
    -0.68
    arenthood
    -0.67
    aign
    -0.66
     UNCLASSIFIED
    -0.64
    aeus
    -0.64
     Yiannopoulos
    -0.63
     recount
    -0.62
     acquies
    -0.62
     rupture
    -0.60
    POSITIVE LOGITS
    Types
    1.03
     Types
    1.00
     reputable
    0.99
     pros
    0.96
     disadvantages
    0.94
     inexpensive
    0.94
     easiest
    0.92
     Pros
    0.91
     beginner
    0.91
     basics
    0.90
    Act Density 0.769%

    No Known Activations