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

    Neuronpedia

    INDEX
    Explanations

    numbers or codes with the term "tes"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "test" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemTracker
    -0.74
    ressive
    -0.64
     profile
    -0.64
     CVE
    -0.63
    olicy
    -0.63
     coefficient
    -0.62
    iggins
    -0.61
    emort
    -0.60
     extreme
    -0.60
    regon
    -0.60
    POSITIVE LOGITS
    terness
    1.20
    ques
    1.05
    ters
    1.05
    tes
    1.03
    chet
    0.96
    boro
    0.96
    heet
    0.94
    aurus
    0.93
    pler
    0.93
    pe
    0.91
    Act Density 0.012%

    No Known Activations