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

    Neuronpedia

    INDEX
    Explanations

    phrases related to superlatives or rankings

    oai_token-act-pair · gpt-3.5-turbo

    references to "the world" and its various aspects or distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.85
    ality
    -0.84
    nels
    -0.83
    rade
    -0.76
    irement
    -0.76
    VP
    -0.72
    zes
    -0.71
    lp
    -0.71
    CHAT
    -0.70
    wal
    -0.70
    POSITIVE LOGITS
     largest
    1.18
     richest
    1.07
     wealthiest
    1.04
     poorest
    1.02
     fastest
    1.02
     tallest
    1.00
     finest
    0.99
     deadliest
    0.98
     toughest
    0.96
     busiest
    0.95
    Act Density 0.066%

    No Known Activations