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

    Neuronpedia

    INDEX
    Explanations

    phrases related to user engagement and feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dup
    -0.16
    761
    -0.16
    zel
    -0.16
    annah
    -0.15
     Bil
    -0.14
    getParameter
    -0.14
    oÄŁ
    -0.14
    zman
    -0.14
    zer
    -0.14
    mers
    -0.14
    POSITIVE LOGITS
    eneric
    0.16
    brook
    0.15
    lander
    0.14
    Plug
    0.14
    owitz
    0.13
     Becker
    0.13
     Yuan
    0.13
    oundary
    0.13
    asic
    0.13
     ФедеÑĢалÑĮ
    0.13
    Act Density 0.151%

    No Known Activations