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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals who have been involved in a particular community or field for a long time

    oai_token-act-pair · gpt-3.5-turbo

    references to long-term associations or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abad
    -1.11
    daq
    -0.94
    ramid
    -0.87
    ulence
    -0.85
    ammy
    -0.85
    urgy
    -0.85
    ageddon
    -0.84
    ibaba
    -0.84
    illions
    -0.84
    otle
    -0.83
    POSITIVE LOGITS
     resident
    0.99
     longtime
    0.94
     collaborator
    0.87
     friend
    0.82
     associate
    0.74
     veteran
    0.72
     member
    0.71
     pleasure
    0.70
     colleague
    0.70
     ally
    0.68
    Act Density 0.021%

    No Known Activations