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

    Neuronpedia

    INDEX
    Explanations

    references to trees

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     hek
    -0.79
     klap
    -0.69
     stik
    -0.68
     traktor
    -0.67
     kram
    -0.66
     pareti
    -0.64
     plak
    -0.61
     republi
    -0.59
     puto
    -0.59
     kras
    -0.59
    POSITIVE LOGITS
     tree
    1.45
    tree
    1.35
     Tree
    1.34
     trees
    1.33
    Tree
    1.31
     TREE
    1.24
     Trees
    1.22
    trees
    1.19
    Trees
    1.16
    TREE
    1.15
    Act Density 0.087%

    No Known Activations