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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to the local culture or characteristics of a region

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enas
    -0.16
    kee
    -0.16
    adlo
    -0.15
    ushman
    -0.14
    mav
    -0.14
    urette
    -0.14
    549
    -0.14
    OutOfBoundsException
    -0.14
     Eld
    -0.14
    566
    -0.14
    POSITIVE LOGITS
    ixer
    0.29
    ncia
    0.27
    cia
    0.23
    cies
    0.18
    tica
    0.18
    lisi
    0.18
    reu
    0.18
    tics
    0.17
    ix
    0.17
    mia
    0.16
    Act Density 0.003%

    No Known Activations