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

    Neuronpedia

    INDEX
    Explanations

    phrases related to "highest" and "greatest" values or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bigger
    -0.66
    er
    -0.63
     fact
    -0.62
    ed
    -0.61
     Dorn
    -0.59
     menengah
    -0.58
     closer
    -0.57
    出版年
    -0.55
     tirantes
    -0.55
     Thiago
    -0.54
    POSITIVE LOGITS
     highest
    2.24
    highest
    2.10
     Highest
    1.97
    Highest
    1.96
     lowest
    1.80
    lowest
    1.70
     Lowest
    1.56
    Lowest
    1.44
     widest
    1.27
     longest
    1.21
    Act Density 0.070%

    No Known Activations