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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals who have been associated with a group or organization for a prolonged period of time

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals who have had a long-term association or role in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abad
    -1.04
    illions
    -0.96
    daq
    -0.90
    ramid
    -0.87
    ammy
    -0.84
    ageddon
    -0.82
    urgy
    -0.80
    oÄŁ
    -0.77
    aughtered
    -0.76
    ambo
    -0.76
    POSITIVE LOGITS
     resident
    0.99
     collaborator
    0.94
     longtime
    0.93
     associate
    0.78
     smoker
    0.77
     friend
    0.76
     fixture
    0.75
     acquaintance
    0.73
     favorite
    0.72
     ally
    0.72
    Act Density 0.026%

    No Known Activations