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

    Neuronpedia

    INDEX
    Explanations

    personal details or stories related to individuals and their experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their personal experiences or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     coron
    -0.61
    present
    -0.59
    Insert
    -0.58
    eus
    -0.57
    idelines
    -0.56
     Ministers
    -0.56
    respective
    -0.56
     infall
    -0.55
    worthiness
    -0.55
     suppl
    -0.55
    POSITIVE LOGITS
     grandson
    0.77
     granddaughter
    0.74
    veland
    0.72
     homeowner
    0.72
     biking
    0.71
     classmate
    0.68
     volunteering
    0.66
     shop
    0.65
     bicy
    0.65
     cowork
    0.65
    Act Density 1.099%

    No Known Activations