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

    Neuronpedia

    INDEX
    Explanations

    references to combining or using various elements to create something new

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that suggest a continuation or addition of ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DEN
    -0.74
    ĨĴ
    -0.74
    meet
    -0.74
    ieth
    -0.72
    eus
    -0.67
    CLASSIFIED
    -0.67
    ADVERTISEMENT
    -0.67
    arious
    -0.66
    ilty
    -0.65
     "$:/
    -0.63
    POSITIVE LOGITS
     shove
    1.04
     toss
    0.99
     put
    0.98
     combine
    0.89
     rearr
    0.88
     spit
    0.87
     tossed
    0.86
     apply
    0.86
     recomb
    0.86
     sprinkle
    0.85
    Act Density 0.212%

    No Known Activations