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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions related to equations and fractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.58
     intern
    -0.53
    cookieParser
    -0.52
    anmoins
    -0.51
    urture
    -0.50
    berton
    -0.50
    nat
    -0.48
     وتسجيلات
    -0.48
     bì
    -0.48
    enido
    -0.48
    POSITIVE LOGITS
     से
    0.90
    frac
    0.82
     whoſe
    0.76
     itſelf
    0.74
     himſelf
    0.73
     themſelves
    0.71
     Waray
    0.70
     myſelf
    0.69
    GoogleApiClient
    0.67
    neſs
    0.66
    Act Density 0.112%

    No Known Activations