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

    Neuronpedia

    INDEX
    Explanations

    pertinent information related to the structure and delivery of jokes.

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

    not just

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     VERY
    0.33
    VERY
    0.31
    Non
    0.30
     nontrivial
    0.30
    Especially
    0.30
    Очень
    0.28
     NON
    0.28
     Questa
    0.28
     Quinta
    0.28
                            
    0.27
    POSITIVE LOGITS
     단순히
    0.55
     merely
    0.54
     mere
    0.46
    只是
    0.43
    แค่
    0.39
     passively
    0.36
     просто
    0.35
    Mere
    0.35
     simplemente
    0.35
     semplicemente
    0.35
    Act Density 1.524%

    No Known Activations