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

    Neuronpedia

    INDEX
    Explanations

    timestamps in the format hours:minutes matching the pattern "59" at the end

    oai_token-act-pair · gpt-3.5-turbo

    numeric timestamps or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.95
    rison
    -0.80
     Flavoring
    -0.79
    hammad
    -0.76
    abwe
    -0.73
     sprung
    -0.73
    xon
    -0.72
    ilater
    -0.72
    imity
    -0.72
    staking
    -0.70
    POSITIVE LOGITS
    dfx
    1.10
    ULT
    0.91
    427
    0.89
    328
    0.87
    327
    0.86
    468
    0.86
    324
    0.85
    428
    0.85
    MJ
    0.82
    00
    0.81
    Act Density 0.021%

    No Known Activations