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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating complexity and emotional or situational intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     demikian
    -0.88
     již
    -0.86
     אשר
    -0.82
    mektedir
    -0.82
     nunmehr
    -0.81
     vermag
    -0.78
    )");
    -0.75
     endast
    -0.75
     erworben
    -0.75
     lze
    -0.74
    POSITIVE LOGITS
     stuff
    1.34
     guys
    1.33
     guy
    1.10
     crappy
    1.05
     dudes
    1.05
     everybody
    1.05
    Guys
    1.02
    guys
    1.01
     weird
    1.01
     kids
    1.00
    Act Density 0.508%

    No Known Activations