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

    Neuronpedia

    INDEX
    Explanations

    titles or names, particularly related to movies or events

    oai_token-act-pair · gpt-3.5-turbo

    titles and references related to the Star Wars franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ++++++++++++++++
    -0.69
    rawdownloadcloneembedreportprint
    -0.62
    Enlarge
    -0.57
    âķIJâķIJ
    -0.55
    ĵĺ
    -0.51
    ï¸ı
    -0.51
    ------------------------------------------------
    -0.50
     ILCS
    -0.50
    hots
    -0.50
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.49
    POSITIVE LOGITS
     bri
    0.58
    rique
    0.56
     degraded
    0.50
     accessories
    0.50
     rul
    0.49
     equivalents
    0.49
    oiler
    0.48
     Citiz
    0.47
     muse
    0.46
    iola
    0.45
    Act Density 2.740%

    No Known Activations