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

    Neuronpedia

    INDEX
    Explanations

    references to academic or technical content, particularly related to methods and results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     su
    -0.45
     n
    -0.44
    ...
    -0.43
    ши
    -0.43
     ne
    -0.42
     (
    -0.40
    nev
    -0.39
     bir
    -0.39
    шер
    -0.38
    ↵↵↵
    -0.38
    POSITIVE LOGITS
     мәкал
    1.08
     Efq
    1.06
     Eſ
    1.03
     Theſe
    1.02
     myſelf
    1.00
     houſe
    0.98
     ſche
    0.97
    __*/
    0.95
    rungsseite
    0.95
     pleaſure
    0.94
    Act Density 0.524%

    No Known Activations