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

    Neuronpedia

    INDEX
    Explanations

    details about theatrical productions and performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thingy
    -0.89
     crappy
    -0.88
     agak
    -0.87
     stuff
    -0.86
     pretty
    -0.83
     maybe
    -0.83
    (?)
    -0.81
     Apparently
    -0.81
     shitty
    -0.80
     seems
    -0.79
    POSITIVE LOGITS
    . 
    0.86
     seamlessly
    0.74
     impactful
    0.74
     leveraging
    0.73
    全新
    0.73
     
    0.73
     globally
    0.71
     unprecedented
    0.71
     enhancements
    0.70
     unparalleled
    0.70
    Act Density 0.536%

    No Known Activations