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

    Neuronpedia

    INDEX
    Explanations

    mentions of wood and related materials

    oai_token-act-pair · gpt-3.5-turbo

    references to wood and wood-related materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orsche
    -0.71
     Fren
    -0.70
    uberty
    -0.67
    rences
    -0.66
    ansky
    -0.65
    ochet
    -0.64
     Imran
    -0.64
     aver
    -0.63
    Reason
    -0.63
    dL
    -0.62
    POSITIVE LOGITS
    working
    1.10
     pulp
    1.09
    worker
    0.98
    yard
    0.95
    grain
    0.94
    wind
    0.91
    ruff
    0.91
    blocks
    0.91
    block
    0.90
    bats
    0.90
    Act Density 0.059%

    No Known Activations