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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive surprise or unexpected enjoyment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anneer
    -0.15
    egt
    -0.15
     future
    -0.15
     пÑĢави
    -0.14
     flo
    -0.14
     Joh
    -0.14
    buie
    -0.14
    ļ
    -0.14
     sund
    -0.14
    ene
    -0.13
    POSITIVE LOGITS
     dedim
    0.18
    СÐŀ
    0.17
     decided
    0.17
    ainen
    0.16
     داش
    0.16
    olis
    0.15
    ÄĽÅĻ
    0.15
    _macros
    0.14
    _PS
    0.14
    .openg
    0.14
    Act Density 0.299%

    No Known Activations