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

    Neuronpedia

    INDEX
    Explanations

    terms related to uniqueness and identity verification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SaÄŁ
    -0.15
    åĵ¡
    -0.15
     Presence
    -0.15
    allo
    -0.14
     Teeth
    -0.14
    ker
    -0.14
     sick
    -0.14
     mũi
    -0.14
     Obr
    -0.14
     Ecc
    -0.14
    POSITIVE LOGITS
    Reserved
    0.17
     tavs
    0.16
    emons
    0.15
     uniqueness
    0.14
    èģ
    0.14
    azole
    0.14
    LETED
    0.14
    念
    0.13
    erno
    0.13
    LAR
    0.13
    Act Density 0.023%

    No Known Activations