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

    Neuronpedia

    INDEX
    Explanations

    instances of specific mathematical notations and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.00
     raiſ
    -0.99
    Kanpo
    -0.96
     myſelf
    -0.94
     ویکی‌پدیای
    -0.86
     themſelves
    -0.84
    BufferException
    -0.83
     houſe
    -0.83
     Efq
    -0.82
     Monfieur
    -0.81
    POSITIVE LOGITS
    mathcal
    2.69
    mathscr
    1.02
     Merz
    0.68
    mathfrak
    0.66
     Kla
    0.66
     Castell
    0.61
    Shen
    0.60
    igraphic
    0.58
     Aguas
    0.58
     Catt
    0.55
    Act Density 0.201%

    No Known Activations