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

    Neuronpedia

    INDEX
    Explanations

    mentions of literary or artistic masterpieces

    oai_token-act-pair · gpt-3.5-turbo

    references to significant literary works or creations described as masterpieces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     causal
    -0.66
    abe
    -0.61
     peninsula
    -0.58
     Himal
    -0.57
     ropes
    -0.57
     causation
    -0.57
    alia
    -0.56
     Breed
    -0.55
     cream
    -0.55
     sled
    -0.55
    POSITIVE LOGITS
     penned
    0.87
    ngth
    0.86
    ="/
    0.82
    Writer
    0.82
     Gutenberg
    0.82
    Reloaded
    0.79
    代
    0.79
     manuscripts
    0.77
     Journals
    0.77
    =""
    0.75
    Act Density 0.044%

    No Known Activations