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

    Neuronpedia

    INDEX
    Explanations

    references to decision-making processes and political candidates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following tokens that begin a line

    np_acts-logits-general · gemini-2.0-flash

    informal dismissive language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]='\
    -0.57
    MutableLiveData
    -0.56
    开口道
    -0.55
     gage
    -0.53
     communiquez
    -0.53
    clusive
    -0.52
    iset
    -0.51
    vician
    -0.51
    EndContext
    -0.50
    ゎ
    -0.50
    POSITIVE LOGITS
     stuff
    1.16
     thingy
    1.08
     STUFF
    0.93
     mierda
    0.89
    Stuff
    0.87
     shit
    0.86
     Stuff
    0.85
     goddamn
    0.85
     darn
    0.84
     fucking
    0.83
    Act Density 0.733%

    No Known Activations