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

    Neuronpedia

    INDEX
    Explanations

    phrases containing possessive form followed by superlative rankings

    oai_token-act-pair · gpt-3.5-turbo

    possessive constructions that refer to the world or its characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.84
    rador
    -0.74
    CHAT
    -0.73
    webkit
    -0.71
    ĪĴ
    -0.71
    lp
    -0.69
    ãĤ¡
    -0.69
    event
    -0.69
    xxx
    -0.68
    ²¾
    -0.67
    POSITIVE LOGITS
     fastest
    1.02
     largest
    0.99
     busiest
    0.95
     richest
    0.94
     wealthiest
    0.94
     newest
    0.93
     finest
    0.93
     smartest
    0.92
     biggest
    0.92
     toughest
    0.91
    Act Density 0.066%

    No Known Activations