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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal information and its handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gap
    -0.16
    onta
    -0.16
     Gap
    -0.15
    erno
    -0.15
     gap
    -0.15
    ki
    -0.15
     LLP
    -0.14
    enheim
    -0.14
    ebin
    -0.14
    unos
    -0.14
    POSITIVE LOGITS
    ayout
    0.15
    AAF
    0.15
    ẫn
    0.14
     Marty
    0.14
    ấn
    0.14
    епÑĤи
    0.14
    /*č↵
    0.14
    arrera
    0.14
     εÏħ
    0.14
    odata
    0.14
    Act Density 0.025%

    No Known Activations