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

    Neuronpedia

    INDEX
    Explanations

    numerical figures such as statistics and percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical figures and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.77
    oard
    -0.67
    Interstitial
    -0.65
    ovie
    -0.64
     VIDEOS
    -0.64
    assies
    -0.64
    cknow
    -0.64
    Whe
    -0.64
    zos
    -0.63
     ignition
    -0.63
    POSITIVE LOGITS
     estimates
    0.91
     estimate
    0.90
     totaled
    0.86
     tallied
    0.83
     averages
    0.79
     totals
    0.79
     compares
    0.76
     excludes
    0.74
     reckoned
    0.74
     figure
    0.73
    Act Density 0.095%

    No Known Activations