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

    Neuronpedia

    INDEX
    Explanations

    topics related to different subjects such as education, government, politics, health, and more

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various topics and categories in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otos
    -0.90
    ript
    -0.74
    yrus
    -0.74
     promise
    -0.73
    atur
    -0.72
     corrid
    -0.71
    xes
    -0.71
     pent
    -0.69
    atten
    -0.68
     testament
    -0.66
    POSITIVE LOGITS
    Topics
    1.18
    afety
    0.91
    matter
    0.78
    hedral
    0.75
    Questions
    0.74
    encies
    0.73
     Emer
    0.71
     EVENT
    0.69
     Include
    0.67
     Flavoring
    0.67
    Act Density 0.014%

    No Known Activations