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

    Neuronpedia

    INDEX
    Explanations

    proper names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mara
    -0.17
    ughs
    -0.16
    geist
    -0.16
    Mate
    -0.15
     Cait
    -0.15
    323
    -0.14
     Meghan
    -0.14
     dro
    -0.14
    zeich
    -0.14
    oug
    -0.14
    POSITIVE LOGITS
     Lim
    0.34
    Lim
    0.29
     Wong
    0.28
     Ng
    0.26
     Yap
    0.25
     Chan
    0.25
     Seah
    0.24
     lim
    0.22
    Chan
    0.22
     Kelvin
    0.21
    Act Density 0.094%

    No Known Activations