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

    Neuronpedia

    INDEX
    Explanations

    words related to items being untied or unraveled

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "looseness" or "loose ends."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.85
    ãĤ´ãĥ³
    -0.77
    aurus
    -0.77
    illian
    -0.74
    oleon
    -0.72
    igraph
    -0.72
    IENCE
    -0.72
    amus
    -0.71
    ococ
    -0.70
    aur
    -0.70
    POSITIVE LOGITS
    leaf
    1.13
    weed
    0.89
    nesses
    0.86
    ness
    0.82
    cloth
    0.80
     cannon
    0.79
    fitting
    0.79
     leaf
    0.78
    tail
    0.77
    tails
    0.77
    Act Density 0.012%

    No Known Activations