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

    Neuronpedia

    INDEX
    Explanations

    numerical values, specifically those related to quantities or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /
    -0.85
    es
    -0.74
     def
    -0.68
    )
    -0.68
    er
    -0.67
     "
    -0.67
    </strong>
    -0.65
    ly
    -0.65
     «
    -0.64
     Orrell
    -0.64
    POSITIVE LOGITS
     eighty
    1.16
     seventy
    1.10
     sixty
    1.09
     ninety
    1.09
     nineteen
    1.07
    AndEndTag
    1.06
    SourceChecksum
    1.05
     Ninety
    1.03
     cinquante
    1.03
     Theſe
    1.03
    Act Density 0.171%

    No Known Activations