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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or numerical significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     and
    -0.20
    a
    -0.18
    ,
    -0.18
    æŁIJ
    -0.16
    ,a
    -0.16
    icular
    -0.16
    ä¸ĢäºĽ
    -0.15
    大éĩı
    -0.15
     Numerous
    -0.15
     with
    -0.15
    POSITIVE LOGITS
     dollars
    0.35
     pounds
    0.32
     hours
    0.31
     miles
    0.30
     acres
    0.29
     kilometers
    0.28
     kilometres
    0.28
     them
    0.27
     years
    0.27
     hectares
    0.26
    Act Density 0.056%

    No Known Activations