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

    Neuronpedia

    INDEX
    Explanations

    references to trees in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to trees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersive
    -0.78
    glomer
    -0.74
    rontal
    -0.74
    arcer
    -0.70
    dL
    -0.70
    ensitive
    -0.68
    ombat
    -0.67
    oice
    -0.66
     Horowitz
    -0.66
    DOS
    -0.63
    POSITIVE LOGITS
     canopy
    1.18
    frog
    1.09
     trees
    1.05
     stump
    1.05
    Hug
    1.02
    beard
    1.00
     planting
    0.97
    yard
    0.96
     tree
    0.94
     trunk
    0.93
    Act Density 0.041%

    No Known Activations