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

    Neuronpedia

    INDEX
    Explanations

    scientific papers or research publications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of academic papers or research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffff
    -0.81
    cffffcc
    -0.68
    complex
    -0.61
    iak
    -0.61
    vil
    -0.59
    inventory
    -0.59
    yg
    -0.59
     destro
    -0.59
    tv
    -0.59
    awk
    -0.57
    POSITIVE LOGITS
    clip
    1.02
    Paper
    0.91
    marks
    0.85
     towels
    0.84
    papers
    0.82
    backs
    0.78
    weight
    0.78
    books
    0.77
    meal
    0.77
    worm
    0.77
    Act Density 0.018%

    No Known Activations