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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.88
     دیکھیے
    -0.85
     NDL
    -0.80
     Theſe
    -0.75
     doubtnut
    -0.75
     Yose
    -0.74
    NewRow
    -0.73
     Houſe
    -0.72
    findpost
    -0.72
     Beſ
    -0.72
    POSITIVE LOGITS
     $\
    2.18
    $\
    1.47
     ($\
    1.23
     $(\
    1.20
    {$\
    1.09
    }{$\
    1.08
     $=\
    0.99
    ="\
    0.94
     $|\
    0.91
     $\{\
    0.91
    Act Density 0.215%

    No Known Activations