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

    Neuronpedia

    INDEX
    Explanations

    words related to garments or settings that are loosely fitted.

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of being loose or unrestrained

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.79
    amus
    -0.79
    ococ
    -0.77
    ãĤ´ãĥ³
    -0.76
    igraph
    -0.76
    ophers
    -0.75
    aurus
    -0.74
    illian
    -0.74
    issance
    -0.73
    oleon
    -0.72
    POSITIVE LOGITS
    leaf
    1.14
    cloth
    0.87
    fitting
    0.86
    weed
    0.85
    tails
    0.85
    tail
    0.84
    wood
    0.79
    cover
    0.79
    ness
    0.78
    wd
    0.78
    Act Density 0.016%

    No Known Activations