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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the beginning of text content

    oai_token-act-pair · gpt-3.5-turbo

    the word "This" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onto
    -0.74
    pots
    -0.73
    adle
    -0.72
    agi
    -0.70
    ickets
    -0.69
    ãĤ¹ãĥĪ
    -0.69
    oller
    -0.68
    ques
    -0.68
    76561
    -0.67
    omo
    -0.67
    POSITIVE LOGITS
     week
    0.97
     article
    0.88
     latest
    0.88
     month
    0.86
     year
    0.83
     nifty
    0.81
     arrangement
    0.80
     infographic
    0.79
     Week
    0.78
     excerpt
    0.76
    Act Density 0.221%

    No Known Activations