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

    Neuronpedia

    INDEX
    Explanations

    references to wooden materials or structures

    oai_token-act-pair · gpt-3.5-turbo

    references to wooden objects and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arenthood
    -0.77
    luent
    -0.75
    inion
    -0.74
    egal
    -0.74
    politics
    -0.73
    dL
    -0.72
    eal
    -0.72
    INA
    -0.72
    doms
    -0.71
    States
    -0.71
    POSITIVE LOGITS
     wooden
    1.12
     bamboo
    0.95
     coffin
    0.94
     plaque
    0.93
     plank
    0.91
     spoon
    0.90
     furniture
    0.85
     decoration
    0.85
     stret
    0.85
     beams
    0.83
    Act Density 0.016%

    No Known Activations