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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and phrases indicating caution or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Silk
    -0.17
     Lage
    -0.15
    ILA
    -0.14
    ila
    -0.14
    libs
    -0.14
    anj
    -0.14
     Wish
    -0.13
    ashboard
    -0.13
     toler
    -0.13
    ocked
    -0.13
    POSITIVE LOGITS
    acket
    0.15
    lis
    0.15
    uno
    0.14
    mot
    0.14
    iece
    0.14
     Carr
    0.14
    .openg
    0.14
    imet
    0.14
    ackle
    0.14
     Äijứng
    0.13
    Act Density 0.299%

    No Known Activations