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

    Neuronpedia

    INDEX
    Explanations

    references to academic studies and their methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     którzy
    -0.43
    :✨
    -0.42
     gdyby
    -0.39
    Collegamenti
    -0.38
     kyllä
    -0.36
     ktorí
    -0.34
     Öffentlichkeit
    -0.34
     których
    -0.34
    ppure
    -0.34
    ledem
    -0.34
    POSITIVE LOGITS
    ,
    2.78
     ,
    0.93
    ，
    0.91
    ،
    0.85
    *,
    0.84
    ™,
    0.84
    ®,
    0.84
    ,
    0.82
    (),
    0.82
    !,
    0.79
    Act Density 16.806%

    No Known Activations