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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols related to integrals and derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.71
     estekak
    -0.67
     WaitForSeconds
    -0.66
     فريبيس
    -0.62
     cleft
    -0.59
     surla
    -0.58
     bromide
    -0.57
     \\
    -0.57
     proudest
    -0.57
     uLocal
    -0.57
    POSITIVE LOGITS
    躇
    0.51
    لاثة
    0.51
     autorytatywna
    0.49
    WriteBarrier
    0.47
    itania
    0.45
     mo
    0.45
     par
    0.44
    ,
    0.41
    rigues
    0.40
     her
    0.40
    Act Density 1.320%

    No Known Activations