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

    Neuronpedia

    INDEX
    Explanations

    details about different locations where the person has lived or visited

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe personal experiences and life events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     takedown
    -0.65
     elector
    -0.55
     ®
    -0.55
     trademarks
    -0.54
     Actions
    -0.53
     Lethal
    -0.53
     deterrence
    -0.53
     infographic
    -0.53
     [+]
    -0.52
     definitively
    -0.52
    POSITIVE LOGITS
    girlfriend
    0.71
     dorm
    0.70
     babys
    0.69
     sewing
    0.69
     rented
    0.69
     mornings
    0.68
    dq
    0.67
    ornings
    0.66
    aturdays
    0.65
     roomm
    0.64
    Act Density 1.600%

    No Known Activations