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

    Neuronpedia

    INDEX
    Explanations

    the use of the contraction "t" as a form of negation or absence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.12
    Билгалдахарш
    -1.10
     Theſe
    -1.06
    ſelves
    -1.00
     nahilalakip
    -0.97
    Искәрмәләр
    -0.96
     doubtnut
    -0.94
     للمعارف
    -0.92
     يتيمه
    -0.92
     Efq
    -0.89
    POSITIVE LOGITS
     I
    0.84
    I
    0.68
     (
    0.65
    ,
    0.65
     we
    0.64
     people
    0.63
     many
    0.63
     you
    0.62
    By
    0.61
     B
    0.59
    Act Density 0.294%

    No Known Activations