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

    Neuronpedia

    INDEX
    Explanations

    types of wood

    oai_token-act-pair · gpt-3.5-turbo

    references to wood and its various forms or uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aver
    -0.77
    uberty
    -0.72
     Fren
    -0.69
    inen
    -0.66
    orsche
    -0.64
    ONT
    -0.63
    oresc
    -0.63
     Friedman
    -0.62
     Sunshine
    -0.60
     Merkel
    -0.59
    POSITIVE LOGITS
    working
    1.17
    ruff
    1.05
    worker
    1.05
    grain
    1.03
    wind
    1.02
    wood
    1.00
    work
    0.98
    \\\\\\\\
    0.98
     pulp
    0.97
    workers
    0.95
    Act Density 0.019%

    No Known Activations