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

    Neuronpedia

    INDEX
    Explanations

    words related to different activities, such as cooking, racing, designing circuits, performing live, writing fiction, drumming, compiling, and riding

    oai_token-act-pair · gpt-3.5-turbo

    activities related to various forms of creative and technical pursuits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.85
    terness
    -0.81
    pling
    -0.76
    ifer
    -0.72
    henko
    -0.71
    vier
    -0.70
    alion
    -0.69
    plementation
    -0.68
    agy
    -0.66
    stood
    -0.66
    POSITIVE LOGITS
     professionally
    1.01
     outdoors
    0.94
     solo
    0.90
     indoors
    0.88
     alone
    0.84
     abroad
    0.82
     alongside
    0.79
     anymore
    0.76
     weddings
    0.73
     elsewhere
    0.71
    Act Density 0.272%

    No Known Activations