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

    Neuronpedia

    INDEX
    Explanations

    instances of citation formatting and references in academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    998
    -0.17
    olute
    -0.16
    ména
    -0.15
    iage
    -0.14
    lius
    -0.14
    motion
    -0.14
     Stamina
    -0.14
    948
    -0.14
    sock
    -0.14
    mile
    -0.14
    POSITIVE LOGITS
    ÑĨик
    0.15
    _av
    0.15
    ubes
    0.14
     Nh
    0.14
    iets
    0.14
     Massachusetts
    0.14
     Directed
    0.14
    orman
    0.14
     Laur
    0.14
     Aval
    0.14
    Act Density 0.006%

    No Known Activations