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

    Neuronpedia

    INDEX
    Explanations

    titles of books, movies, or other works

    oai_token-act-pair · gpt-3.5-turbo

    titles or names of creative works and their associated elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aneously
    -0.83
    ties
    -0.79
     exception
    -0.77
    rique
    -0.71
    istically
    -0.70
    ctor
    -0.69
    ded
    -0.68
    tops
    -0.66
    leases
    -0.65
    aments
    -0.64
    POSITIVE LOGITS
    hift
    1.49
    mith
    1.47
    peed
    1.39
    pread
    1.33
    ystem
    1.31
    pring
    1.28
    pace
    1.28
    chool
    1.24
    hip
    1.24
    afety
    1.18
    Act Density 0.287%

    No Known Activations