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

    Neuronpedia

    INDEX
    Explanations

    instances of rankings or standings in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upe
    -0.17
    ListOf
    -0.15
    taire
    -0.15
     oku
    -0.15
    _WAKE
    -0.15
    tem
    -0.15
    #ac
    -0.15
     Elias
    -0.14
    iž
    -0.14
    UDGE
    -0.14
    POSITIVE LOGITS
     Aval
    0.15
    rik
    0.14
     Everyday
    0.14
    anza
    0.14
    Bound
    0.14
     homework
    0.13
    anske
    0.13
    umb
    0.13
     atmos
    0.13
     n
    0.13
    Act Density 0.011%

    No Known Activations