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

    Neuronpedia

    INDEX
    Explanations

    phrases related to quantity or number occurrence

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases indicating novelty, significance, or substantial quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    someone
    -0.95
    expression
    -0.85
    brance
    -0.79
    =~
    -0.76
    rology
    -0.75
    antry
    -0.74
    uber
    -0.74
    ablishment
    -0.74
    culture
    -0.73
    urgy
    -0.72
    POSITIVE LOGITS
     paragraphs
    1.17
     categories
    1.15
     pairs
    1.10
     pillars
    1.08
     slots
    1.06
     bedrooms
    1.05
     halves
    1.05
     editions
    1.04
     phases
    1.03
     finalists
    1.02
    Act Density 0.296%

    No Known Activations