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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty, opinions, or speculative thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     opak
    -0.17
    .helpers
    -0.15
    µľ
    -0.14
     occasionally
    -0.14
    оказ
    -0.14
    omanip
    -0.14
    often
    -0.14
    izzle
    -0.14
    ometimes
    -0.13
    ä¸įå¾Ĺ
    -0.13
    POSITIVE LOGITS
     expect
    0.35
     odds
    0.29
     unless
    0.28
     will
    0.27
     given
    0.27
     Odds
    0.27
     expecting
    0.26
     Expect
    0.25
     expectation
    0.24
     expects
    0.24
    Act Density 0.385%

    No Known Activations