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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ometimes
    -0.15
    ppo
    -0.15
    often
    -0.15
    ÄĽk
    -0.14
    amespace
    -0.14
    kaar
    -0.14
    оказ
    -0.14
    /wiki
    -0.14
    ä¾ĭ
    -0.14
     sometimes
    -0.14
    POSITIVE LOGITS
     expect
    0.38
     fingers
    0.31
     Expect
    0.30
     Hopefully
    0.30
     expects
    0.30
     will
    0.29
     hopefully
    0.28
    Hopefully
    0.27
    Expect
    0.27
     stay
    0.27
    Act Density 0.509%

    No Known Activations