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

    Neuronpedia

    INDEX
    Explanations

    instances related to social media posts and public controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .LayoutStyle
    -0.15
     robber
    -0.15
    Ä©
    -0.15
    avigator
    -0.14
    akh
    -0.14
    rna
    -0.14
    éļĨ
    -0.14
     stabil
    -0.14
     Py
    -0.14
     destabil
    -0.14
    POSITIVE LOGITS
    /tos
    0.15
    uard
    0.15
    911
    0.14
    unchecked
    0.14
    vio
    0.14
    fried
    0.14
    /bower
    0.13
    ym
    0.13
    DK
    0.12
    /dist
    0.12
    Act Density 0.166%

    No Known Activations