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

    Neuronpedia

    INDEX
    Explanations

    phrases related to research activities

    oai_token-act-pair · gpt-3.5-turbo

    actions related to academic research and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urus
    -0.67
    animate
    -0.66
     fitt
    -0.64
     doom
    -0.63
     clipboard
    -0.57
     Tale
    -0.54
     negro
    -0.54
     innocence
    -0.54
     misses
    -0.54
    ibles
    -0.54
    POSITIVE LOGITS
     jointly
    1.08
    actionDate
    0.93
     partly
    0.81
     overseen
    0.78
     principally
    0.77
     mainly
    0.74
     Cosponsors
    0.74
     chiefly
    0.73
     largely
    0.72
     anonymously
    0.71
    Act Density 0.239%

    No Known Activations