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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vana
    -0.89
    words
    -0.85
    earchers
    -0.79
    mates
    -0.78
    agra
    -0.76
    devices
    -0.76
    drivers
    -0.75
    ells
    -0.75
    aways
    -0.74
    nexus
    -0.74
    POSITIVE LOGITS
     Sch
    1.08
     Berg
    1.04
     Gonz
    1.03
     Ernst
    1.03
     Klopp
    1.02
     Jensen
    1.00
     Klein
    1.00
     Schneider
    0.98
     Luk
    0.98
     Karl
    0.98
    Act Density 0.190%

    No Known Activations