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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that convey a sense of authority and reliability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amental
    -0.15
    اÙħبر
    -0.15
    .epam
    -0.15
    emento
    -0.15
    öm
    -0.15
    erson
    -0.14
     Sez
    -0.14
    \Container
    -0.14
    endum
    -0.14
    readcr
    -0.13
    POSITIVE LOGITS
    ãĥĸ
    0.16
    astes
    0.16
    anzi
    0.15
    AtA
    0.14
    ysi
    0.14
    olie
    0.14
    polator
    0.14
     Rossi
    0.14
     Rag
    0.14
     rust
    0.14
    Act Density 0.001%

    No Known Activations