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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "und-" suggesting negation or lack

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avn
    -0.18
    essian
    -0.15
    ximo
    -0.15
    fix
    -0.14
    711
    -0.14
    /tos
    -0.14
    Kin
    -0.14
    ãĤĤãģ£ãģ¨
    -0.14
    baÅŁ
    -0.14
    adden
    -0.14
    POSITIVE LOGITS
     und
    0.24
    eni
    0.22
     Und
    0.22
    oubtedly
    0.19
    ated
    0.18
    uly
    0.18
    Und
    0.18
    etect
    0.17
    ulating
    0.17
    ers
    0.16
    Act Density 0.007%

    No Known Activations