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

    Neuronpedia

    INDEX
    Explanations

    words related to gaming and entertainment

    oai_token-act-pair · gpt-3.5-turbo

    significant nouns related to entertainment, specifically games, films, and various other entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilaterally
    -0.76
     Helpful
    -0.75
    ????????
    -0.65
    ECA
    -0.63
    Ô
    -0.62
     Saying
    -0.61
    azeera
    -0.60
    Ĥ¬
    -0.60
    --------------------------------------------------------
    -0.59
    ntil
    -0.59
    POSITIVE LOGITS
     itself
    1.24
     underwent
    1.11
    's
    1.04
     boasts
    1.00
     debuted
    0.99
     retains
    0.96
     consists
    0.94
     comprises
    0.90
     lacks
    0.90
     weighs
    0.89
    Act Density 0.250%

    No Known Activations