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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "taken"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "taken" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulo
    -0.78
    lich
    -0.75
    tor
    -0.64
    eers
    -0.62
    tions
    -0.62
    ler
    -0.61
    tion
    -0.60
    hips
    -0.60
     regress
    -0.59
    cape
    -0.58
    POSITIVE LOGITS
     aback
    1.39
    aways
    1.04
     advantage
    0.90
     care
    0.88
     cogn
    0.86
    ãĤ¤ãĥĪ
    0.81
    OVER
    0.81
     heed
    0.80
     away
    0.79
     INTO
    0.77
    Act Density 0.034%

    No Known Activations