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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "thing"

    oai_token-act-pair · gpt-3.5-turbo

    the abstract concept of "thing" used repeatedly in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Gaza
    -0.64
     anonymity
    -0.64
     crest
    -0.62
    NetMessage
    -0.62
    avorite
    -0.61
    ãĥ©ãĥ³
    -0.60
    assetsadobe
    -0.60
     SERVICE
    -0.59
    incinn
    -0.58
     Telecommunications
    -0.58
    POSITIVE LOGITS
    iverse
    1.26
     happening
    0.94
     happened
    0.94
     happ
    0.85
    hots
    0.85
    ional
    0.83
     happens
    0.83
     happen
    0.81
    meal
    0.80
     Called
    0.80
    Act Density 0.050%

    No Known Activations