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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional situations or variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĦ¦
    -0.15
    oven
    -0.15
    æŃ©
    -0.14
    zÃŃ
    -0.14
    ugo
    -0.14
    earer
    -0.14
     ÑĦакÑĤ
    -0.13
    inan
    -0.13
    ilk
    -0.13
    TAIL
    -0.13
    POSITIVE LOGITS
    eln
    0.18
    alytics
    0.16
     otherwise
    0.16
    .onView
    0.16
    iesen
    0.16
     Dol
    0.15
     Otherwise
    0.15
    ãĥªãĤ«
    0.14
     Viktor
    0.14
    Otherwise
    0.14
    Act Density 0.168%

    No Known Activations