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

    Neuronpedia

    INDEX
    Explanations

    proper nouns of individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    names of people and places, particularly in a legal or governmental context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĶĢâĶĢ
    -0.86
     daytime
    -0.70
    ··
    -0.65
     BOX
    -0.61
     VIDE
    -0.61
    ATIONAL
    -0.61
     ANGEL
    -0.60
     millennials
    -0.60
    FORMATION
    -0.59
    ASHINGTON
    -0.58
    POSITIVE LOGITS
    baugh
    1.30
    ley
    1.09
    love
    1.09
    gren
    1.07
    idge
    1.05
    ingham
    1.05
    inski
    1.05
    etti
    1.02
    witz
    1.02
    shall
    1.02
    Act Density 0.214%

    No Known Activations