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

    Neuronpedia

    INDEX
    Explanations

    first-person personal experiences and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     presum
    -0.16
    ần
    -0.15
    Ỽt
    -0.15
    udden
    -0.15
    edBy
    -0.15
    UILayout
    -0.15
     Král
    -0.15
    ografie
    -0.15
     sympath
    -0.14
    ivable
    -0.14
    POSITIVE LOGITS
     highly
    0.18
     thoroughly
    0.17
    Rating
    0.16
    olis
    0.16
     Highly
    0.15
     thorough
    0.15
     recommend
    0.15
     rate
    0.14
    mg
    0.14
     appreciated
    0.14
    Act Density 0.059%

    No Known Activations