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

    Neuronpedia

    INDEX
    Explanations

    possessive forms of the word "is."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upp
    -0.15
    raki
    -0.15
    ursal
    -0.14
    idge
    -0.14
    uries
    -0.14
    omal
    -0.14
    zcze
    -0.14
    Ø´ÙĪ
    -0.13
    人åĵ¡
    -0.13
    HeaderCode
    -0.13
    POSITIVE LOGITS
     sake
    0.19
     worth
    0.18
    quir
    0.16
    aston
    0.16
     gotta
    0.15
     ìŀħ
    0.14
     Alright
    0.14
     alike
    0.14
    atab
    0.14
    edn
    0.14
    Act Density 0.171%

    No Known Activations