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

    Neuronpedia

    INDEX
    Explanations

    words that are related to computer programming, specifically focusing on aspects such as memory management and data structures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.66
    GAN
    -0.65
    Harris
    -0.63
     Hollywood
    -0.60
    Planet
    -0.58
     America
    -0.58
     Boy
    -0.57
    ste
    -0.56
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.56
     Democrat
    -0.56
    POSITIVE LOGITS
    poons
    1.20
    paces
    1.07
    etter
    1.05
    pread
    1.05
    ilver
    1.04
    mith
    1.02
    aurus
    1.02
    pace
    1.01
    hips
    0.97
    hip
    0.93
    Act Density 0.709%

    No Known Activations