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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "Poly" followed by a capitalized word

    oai_token-act-pair · gpt-3.5-turbo

    references to "Poly" related terms, specifically educational institutions or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATURE
    -0.80
    è¦ļéĨĴ
    -0.77
    CRIP
    -0.76
    ****************
    -0.70
    æ©
    -0.70
    éĹĺ
    -0.70
    DERR
    -0.68
    ively
    -0.68
    âĶĢâĶĢ
    -0.68
    yrs
    -0.68
    POSITIVE LOGITS
    morph
    1.03
    Poly
    1.00
    gon
    0.98
     Poly
    0.96
    ©¶æ
    0.95
    osate
    0.93
    culus
    0.88
    graph
    0.84
    nesia
    0.83
    reth
    0.82
    Act Density 0.008%

    No Known Activations