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

    Neuronpedia

    INDEX
    Explanations

    instances where the document instructs the reader to take a look at something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "take a look."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    necess
    -0.73
    upuncture
    -0.68
    ortunately
    -0.66
    coal
    -0.66
    ply
    -0.64
    claimed
    -0.63
    Chart
    -0.62
     Methods
    -0.61
    GA
    -0.61
    Staff
    -0.60
    POSITIVE LOGITS
    ahead
    0.75
    finder
    0.74
    atio
    0.71
     ãĤ
    0.70
    iger
    0.67
    iang
    0.65
    ative
    0.64
     look
    0.64
    emark
    0.63
    ãĤ¶
    0.63
    Act Density 0.016%

    No Known Activations