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

    Neuronpedia

    INDEX
    Explanations

    terms that convey relative relationships or proportions in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.66
     snippetHide
    -0.59
     дописавши
    -0.57
    tagHelperRunner
    -0.56
     Meksiku
    -0.53
     Biôgrafia
    -0.52
    IUrlHelper
    -0.51
    новниш
    -0.51
    ality
    -0.50
     <<<<<<<<<<<<<<
    -0.48
    POSITIVE LOGITS
     speaking
    0.57
     humidity
    0.55
     newcomer
    0.52
     importance
    0.52
     importancia
    0.46
     newcomers
    0.44
     merits
    0.44
     hablando
    0.43
     few
    0.42
     inexpensive
    0.41
    Act Density 0.159%

    No Known Activations