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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "ref" followed by various suffixes like "ree", "ug", "use", "ract", "ometer", and so on

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to ice, freezing, and the concept of reusing or repurposing materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Merit
    -0.82
    人
    -0.71
    Jr
    -0.70
    Ub
    -0.68
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
    TAG
    -0.64
    Cru
    -0.63
     Sabha
    -0.63
     Lumpur
    -0.62
    dev
    -0.62
    POSITIVE LOGITS
    itory
    0.80
    ascript
    0.80
    issance
    0.75
    ysis
    0.72
     reuse
    0.72
    ance
    0.70
    ctions
    0.66
    ndum
    0.66
    alkyrie
    0.64
    nyder
    0.63
    Act Density 0.034%

    No Known Activations