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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "took" in text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "took" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Smile
    -0.65
     agre
    -0.63
     david
    -0.62
     includ
    -0.61
    Cong
    -0.61
     Democr
    -0.60
     ---------
    -0.59
     [+]
    -0.59
     sidebar
    -0.59
    earances
    -0.58
    POSITIVE LOGITS
    aways
    1.09
     advantage
    1.06
     aback
    1.01
     refuge
    0.98
     heed
    0.89
     care
    0.89
     precedence
    0.88
     pains
    0.83
     possession
    0.79
     precautions
    0.79
    Act Density 0.100%

    No Known Activations