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

    Neuronpedia

    INDEX
    Explanations

    references to chapters in a text or document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    evice
    -0.16
    asan
    -0.15
    éĢļ
    -0.15
    ngr
    -0.15
    PCA
    -0.14
    alf
    -0.14
    .hu
    -0.14
    Å¡k
    -0.14
     versa
    -0.14
    lixir
    -0.14
    POSITIVE LOGITS
    _argv
    0.15
     Phar
    0.14
     Hari
    0.14
    446
    0.14
    alis
    0.14
    ãģĤãĤĭ
    0.14
    adoras
    0.13
     BIOS
    0.13
     flat
    0.13
    /Area
    0.13
    Act Density 0.068%

    No Known Activations