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

    Neuronpedia

    INDEX
    Explanations

    the term "useless" and its variants indicating irrelevance or lack of utility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uto
    -0.16
    ãĥ¥
    -0.15
    oto
    -0.15
    ån
    -0.15
     Alv
    -0.14
    cep
    -0.14
    unk
    -0.14
    achel
    -0.14
    utch
    -0.14
    anitize
    -0.14
    POSITIVE LOGITS
    fully
    0.16
    .framework
    0.15
     having
    0.14
    lessly
    0.14
    lbrace
    0.13
    Criterion
    0.13
    ESA
    0.13
    æ¢Ŀ
    0.13
    NER
    0.13
    angs
    0.13
    Act Density 0.012%

    No Known Activations