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

    Neuronpedia

    INDEX
    Explanations

    references to tree-related entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of trees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glomer
    -0.81
    rontal
    -0.73
    dL
    -0.70
    ione
    -0.70
    Demand
    -0.70
    Digital
    -0.69
    anson
    -0.69
    agonists
    -0.68
     Stanton
    -0.67
    resso
    -0.64
    POSITIVE LOGITS
     tree
    1.28
     trees
    1.25
     Tree
    1.20
     Trees
    1.15
     canopy
    1.07
    Tree
    1.05
    tree
    0.98
    beard
    0.93
     stump
    0.92
    frog
    0.92
    Act Density 0.012%

    No Known Activations