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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating predictions or future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sometimes
    -0.64
    sometimes
    -0.57
     often
    -0.55
    有时
    -0.55
    后来
    -0.54
     Sometimes
    -0.54
     Wikimedijinoj
    -0.53
    often
    -0.51
    Sometimes
    -0.50
     иногда
    -0.50
    POSITIVE LOGITS
     hopefully
    1.28
     Hopefully
    1.22
    Hopefully
    1.21
    hopefully
    1.15
    Fingers
    1.09
     Fingers
    1.01
    fingers
    0.96
     fingers
    0.92
    Expect
    0.91
    🤞
    0.90
    Act Density 0.581%

    No Known Activations