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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases related to digital interfaces and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ÂŃ
    -0.14
     leakage
    -0.14
     Han
    -0.14
    ANDROID
    -0.13
    ause
    -0.13
    ioni
    -0.13
    ilio
    -0.13
     I
    -0.13
     and
    -0.13
     Ä
    -0.13
    POSITIVE LOGITS
     ,↵
    0.19
    mpar
    0.16
    oka
    0.16
    åĨĨ
    0.15
     ,č↵
    0.15
    æĮģ
    0.14
    engu
    0.14
    udit
    0.14
    \↵
    0.14
     ,
    0.14
    Act Density 0.149%

    No Known Activations