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

    Neuronpedia

    INDEX
    Explanations

    references to names and terminology related to identity and designation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avis
    -0.15
    jsp
    -0.15
    irit
    -0.15
    avy
    -0.14
    avage
    -0.14
    owitz
    -0.14
     Ning
    -0.14
     aVar
    -0.13
    atican
    -0.13
    afd
    -0.13
    POSITIVE LOGITS
     name
    0.22
     åIJįåīį
    0.18
    -name
    0.18
    name
    0.17
    縮
    0.17
     tit
    0.16
     titles
    0.16
     Diss
    0.16
    åIJįåīį
    0.16
     tên
    0.16
    Act Density 0.396%

    No Known Activations