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

    Neuronpedia

    INDEX
    Explanations

    states or countries

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.68
    ispers
    -0.66
    xon
    -0.65
     Levels
    -0.65
    eus
    -0.61
    assies
    -0.60
     roofs
    -0.59
    racuse
    -0.59
    ses
    -0.58
    undreds
    -0.58
    POSITIVE LOGITS
     indeed
    1.04
     nonetheless
    1.01
     whose
    0.93
     devoid
    0.92
     unto
    0.87
     nevertheless
    0.83
     riddled
    0.83
     capable
    0.79
     surrounded
    0.78
     deserving
    0.78
    Act Density 0.216%

    No Known Activations