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

    Neuronpedia

    INDEX
    Explanations

    Twitter usernames

    oai_token-act-pair · gpt-3.5-turbo

    the closing parentheses in text, indicating a format related to social media interactions or posts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icion
    -0.79
    omorphic
    -0.74
    othermal
    -0.67
    ients
    -0.66
     climbers
    -0.66
    blers
    -0.66
    perate
    -0.64
    indal
    -0.63
    olars
    -0.62
    houses
    -0.62
    POSITIVE LOGITS
     October
    0.88
     September
    0.88
     August
    0.82
     November
    0.81
     June
    0.79
    September
    0.79
     December
    0.78
     May
    0.78
    October
    0.78
     February
    0.77
    Act Density 0.032%

    No Known Activations