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

    Neuronpedia

    INDEX
    Explanations

    specific expressions of emotion or descriptive language associated with experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wner
    -0.17
    erties
    -0.15
    ye
    -0.15
    canf
    -0.15
    /System
    -0.14
    ç¶
    -0.14
    éal
    -0.14
    aret
    -0.14
    agnar
    -0.14
    .sem
    -0.14
    POSITIVE LOGITS
    cia
    0.17
    amin
    0.17
    .setViewport
    0.17
    มà¸Ń
    0.16
    enberg
    0.16
     Lev
    0.16
    ιά
    0.15
     Booker
    0.14
     Maz
    0.14
     blind
    0.14
    Act Density 0.003%

    No Known Activations