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

    Neuronpedia

    INDEX
    Explanations

    questions and statements about relationships and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    licken
    -0.17
    reta
    -0.15
    iez
    -0.14
     undoubtedly
    -0.14
     hopefully
    -0.14
     Ryder
    -0.14
    tec
    -0.14
    anki
    -0.14
     pragma
    -0.13
     indeed
    -0.13
    POSITIVE LOGITS
     whenever
    0.26
     seems
    0.24
     seem
    0.24
    Whenever
    0.23
     Whenever
    0.22
     lately
    0.21
    ë§Īëĭ¤
    0.21
     every
    0.21
     seemingly
    0.21
     seemed
    0.20
    Act Density 0.376%

    No Known Activations