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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize frequency or repetition

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate frequency, specifically terms like "often" and "sometimes."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogun
    -0.80
    amins
    -0.76
    oples
    -0.74
    eday
    -0.70
    regate
    -0.68
    udi
    -0.63
    letico
    -0.62
     Fighters
    -0.62
    anth
    -0.62
    jriwal
    -0.62
    POSITIVE LOGITS
     overlooked
    1.39
     cited
    1.31
     mistaken
    1.29
     referred
    1.29
     misunderstood
    1.28
     forgotten
    1.23
    entimes
    1.20
     portrayed
    1.15
     confused
    1.14
     seen
    1.14
    Act Density 0.105%

    No Known Activations