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

    Neuronpedia

    INDEX
    Explanations

    references to a specific event or performance titled "play" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "play" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    «ĺ
    -0.74
    pora
    -0.67
     Unic
    -0.65
    FFFF
    -0.64
     Apost
    -0.63
    ħĭ
    -0.62
     burst
    -0.61
     hus
    -0.61
    £ı
    -0.60
     abst
    -0.59
    POSITIVE LOGITS
    wright
    1.39
    ername
    1.10
    plays
    1.02
    maker
    1.02
    books
    1.01
    testers
    0.98
    wr
    0.97
    offs
    0.94
    fulness
    0.93
    keeper
    0.93
    Act Density 0.036%

    No Known Activations