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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive feedback and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nger
    -0.16
     Rodrig
    -0.16
    ä»Ģ
    -0.15
    LAY
    -0.15
    asma
    -0.15
     Samp
    -0.15
    åĭ¢
    -0.14
     caret
    -0.14
    zÅij
    -0.14
    ë§Į
    -0.14
    POSITIVE LOGITS
    oud
    0.15
    yte
    0.15
    coln
    0.14
    ÙIJÙĦ
    0.14
    idia
    0.13
     indeed
    0.13
    izzy
    0.13
    дов
    0.13
     Essen
    0.13
    天åłĤ
    0.13
    Act Density 0.130%

    No Known Activations