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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udo
    -0.17
    cntl
    -0.15
     Cald
    -0.15
    grim
    -0.15
     Ú¯ÙĨ
    -0.15
    ù
    -0.15
     Affero
    -0.14
    cil
    -0.14
    Sock
    -0.14
    cdn
    -0.14
    POSITIVE LOGITS
     =
    0.18
     either
    0.15
     Hopkins
    0.15
    >#
    0.15
    elm
    0.14
     Mona
    0.14
     mon
    0.14
    steller
    0.14
     Pro
    0.14
    elay
    0.14
    Act Density 0.158%

    No Known Activations