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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to various topics, such as finance, medical procedures, animals, and more

    oai_token-act-pair · gpt-3.5-turbo

    topics related to health and economics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.69
    Gro
    -0.65
    Screenshot
    -0.62
    Merit
    -0.62
    Secure
    -0.60
    lihood
    -0.60
    ãĥĥãĥī
    -0.59
     Gut
    -0.59
    FUN
    -0.59
     Honor
    -0.58
    POSITIVE LOGITS
    ensis
    0.73
    riages
    0.70
    ateurs
    0.69
    otomy
    0.69
    atism
    0.67
    agall
    0.66
    tarians
    0.65
     multiplication
    0.65
    etting
    0.64
     exists
    0.63
    Act Density 0.736%

    No Known Activations