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

    Neuronpedia

    INDEX
    Explanations

    numerical or coded references in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Morse
    -0.15
     Gord
    -0.15
    eland
    -0.15
     Bak
    -0.15
    omi
    -0.14
    bert
    -0.14
    WN
    -0.14
    aste
    -0.14
     Kaplan
    -0.13
    weed
    -0.13
    POSITIVE LOGITS
    Ã¤ÃŁ
    0.16
    isine
    0.15
    iais
    0.15
     YYS
    0.15
     addCriterion
    0.15
    iliz
    0.14
    лаÑĤа
    0.14
    itag
    0.14
    orgia
    0.14
    anza
    0.14
    Act Density 0.009%

    No Known Activations