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

    Neuronpedia

    INDEX
    Explanations

    references to letters being sent or written in the context of communication or advocacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leh
    -0.18
    enk
    -0.15
     local
    -0.15
     sugar
    -0.15
    ylko
    -0.14
     sm
    -0.14
    asin
    -0.14
     Local
    -0.14
    ,
    -0.14
    sters
    -0.14
    POSITIVE LOGITS
    urg
    0.17
    asket
    0.16
    rais
    0.16
    aison
    0.15
    ToWorld
    0.15
    .$.
    0.15
    xeb
    0.15
    à¹ģà¸Ļ
    0.15
    tron
    0.15
    elow
    0.15
    Act Density 0.034%

    No Known Activations