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

    Neuronpedia

    INDEX
    Explanations

    references to domestic help and servants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erli
    -0.16
    arih
    -0.15
    ané
    -0.14
    ÑĸÑģно
    -0.14
    .mvp
    -0.14
    Æ°á»Ľng
    -0.14
    ุม
    -0.14
    IRC
    -0.14
    /assert
    -0.13
     thụ
    -0.13
    POSITIVE LOGITS
     Fat
    0.18
     Provid
    0.17
     fat
    0.15
     Rossi
    0.15
     hire
    0.15
     sor
    0.15
     un
    0.14
     Fil
    0.14
    inas
    0.14
     wen
    0.14
    Act Density 0.274%

    No Known Activations