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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, often with possessive forms

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms and references to people's names or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dates
    -0.78
    seekers
    -0.70
    Downloadha
    -0.66
     Egyptians
    -0.64
    ifact
    -0.62
     Israelis
    -0.61
    paio
    -0.61
     Koreans
    -0.61
    CDC
    -0.60
     psychologists
    -0.60
    POSITIVE LOGITS
     midst
    1.47
     vicinity
    1.14
     stead
    1.08
     backyard
    1.07
     orbit
    1.03
     wake
    1.02
     eyes
    1.02
     favour
    0.98
     footsteps
    0.98
     vein
    0.96
    Act Density 0.223%

    No Known Activations