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

    Neuronpedia

    INDEX
    Explanations

    references to rights or entitlements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uben
    -0.14
    ến
    -0.14
     Ware
    -0.14
    ÑĢÑĸд
    -0.14
    uple
    -0.14
    onym
    -0.14
    pars
    -0.14
    rol
    -0.14
    ارÙĩ
    -0.14
     Op
    -0.13
    POSITIVE LOGITS
     reserved
    0.46
     Reserved
    0.41
    reserved
    0.36
     reserve
    0.35
    Reserved
    0.33
     RESERVED
    0.31
     reserves
    0.29
    _reserved
    0.29
     Reserve
    0.28
     reserv
    0.25
    Act Density 0.004%

    No Known Activations