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

    Neuronpedia

    INDEX
    Explanations

    words related to distraction or being distracted

    oai_token-act-pair · gpt-3.5-turbo

    references to distraction and the act of distracting others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cko
    -0.74
    iders
    -0.73
    anne
    -0.70
    nai
    -0.64
    gs
    -0.63
    holm
    -0.63
    conn
    -0.62
    WER
    -0.61
     Ibid
    -0.60
    fred
    -0.59
    POSITIVE LOGITS
     attention
    0.90
     distract
    0.81
    ingly
    0.80
    aline
    0.79
     distractions
    0.78
     distracting
    0.78
    icult
    0.76
     distracted
    0.75
     distraction
    0.73
    raints
    0.73
    Act Density 0.043%

    No Known Activations