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

    Neuronpedia

    INDEX
    Explanations

    phrases concerning personally identifiable information and its collection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antt
    -0.14
     Sm
    -0.13
    eniable
    -0.13
    eya
    -0.13
     Yön
    -0.13
    zÄħd
    -0.13
    cher
    -0.13
    anou
    -0.13
    éĻµ
    -0.13
     Cru
    -0.12
    POSITIVE LOGITS
    oby
    0.14
    Carthy
    0.14
    ?=.*
    0.14
    еÑĢÑĤи
    0.14
     Stard
    0.14
    оÑħ
    0.14
    аÑģÑĤи
    0.14
    kees
    0.14
     Wid
    0.13
    _COMPILE
    0.13
    Act Density 0.032%

    No Known Activations