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

    Neuronpedia

    INDEX
    Explanations

    instances of code formatting or technical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     示
    -0.19
    mey
    -0.18
    RAP
    -0.16
    eldon
    -0.15
    ELS
    -0.15
    ±
    -0.15
    amba
    -0.14
     Agenda
    -0.14
    iple
    -0.14
    nob
    -0.14
    POSITIVE LOGITS
    roe
    0.15
    burgh
    0.14
     intrinsic
    0.14
    adaÅŁ
    0.14
    itored
    0.14
    بÙĪد
    0.14
     Substance
    0.14
    ena
    0.14
    quist
    0.14
    ometown
    0.14
    Act Density 0.001%

    No Known Activations