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

    Neuronpedia

    INDEX
    Explanations

    mentions of trees

    oai_token-act-pair · gpt-3.5-turbo

    references to trees and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glomer
    -0.91
    arcer
    -0.80
    rontal
    -0.76
    ione
    -0.71
    ities
    -0.71
    oice
    -0.69
    abwe
    -0.69
    farious
    -0.68
    olitan
    -0.66
    ersive
    -0.64
    POSITIVE LOGITS
     canopy
    1.14
    frog
    1.04
    beard
    1.02
     trees
    1.02
     tree
    0.95
    Hug
    0.95
    yard
    0.93
     stump
    0.92
     Trees
    0.91
     trunk
    0.90
    Act Density 0.024%

    No Known Activations