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

    Neuronpedia

    INDEX
    Explanations

    cryptocurrency-related terms

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or codes related to technical or computer science terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     HAR
    -0.80
     Hastings
    -0.73
     kinderg
    -0.72
     Bab
    -0.72
     Reck
    -0.71
     SHE
    -0.70
     Chong
    -0.70
     Aston
    -0.69
     Zed
    -0.69
     Wasteland
    -0.68
    POSITIVE LOGITS
    cs
    1.40
    pd
    1.39
    gs
    1.38
    wr
    1.32
    nl
    1.30
    ml
    1.29
    cp
    1.28
    kl
    1.27
    fs
    1.27
    ulhu
    1.26
    Act Density 0.149%

    No Known Activations