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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal or political events and actions

    oai_token-act-pair · gpt-3.5-turbo

    end-of-text markers in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minist
    -0.64
     endeavour
    -0.62
    tons
    -0.61
     endeav
    -0.60
     everyday
    -0.60
     illusion
    -0.60
    iates
    -0.56
    colour
    -0.56
     CLASS
    -0.56
     adventures
    -0.56
    POSITIVE LOGITS
    Asked
    0.91
    Earlier
    0.80
    Shape
    0.80
     REUTERS
    0.79
    Meanwhile
    0.79
    PHOTOS
    0.77
     Asked
    0.76
    Newsletter
    0.74
    Speaking
    0.74
    Contribut
    0.73
    Act Density 0.442%

    No Known Activations