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

    Neuronpedia

    INDEX
    Explanations

    technical terms and abbreviations related to computing and documents like "RP" and "LP"

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of media or formats related to "RP" and "LP"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hold
    -0.78
    flies
    -0.75
    taboola
    -0.75
    gie
    -0.72
    bite
    -0.70
    ãĥ³ãĤ¸
    -0.69
    ãĤ¤ãĥĪ
    -0.69
    âĸ¬
    -0.66
    avia
    -0.65
     Britann
    -0.63
    POSITIVE LOGITS
    olicy
    1.27
    odcast
    1.14
    rint
    1.14
    arser
    1.14
    ropri
    1.11
    ORTS
    1.07
    ossible
    1.06
    ixel
    1.03
    ublic
    1.03
    retty
    1.00
    Act Density 0.020%

    No Known Activations