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

    Neuronpedia

    INDEX
    Explanations

    words related to economic and political concepts

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and suffixes related to various conditions and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.77
    ĸļ
    -0.75
    Ward
    -0.75
     Kinnikuman
    -0.74
    paid
    -0.72
    _>
    -0.72
    staff
    -0.71
    Weather
    -0.70
    rador
    -0.70
    erver
    -0.69
    POSITIVE LOGITS
     behaviour
    0.86
     tendencies
    0.81
     behavior
    0.79
     lifestyles
    0.78
     youth
    0.77
     youths
    0.74
     behaviours
    0.73
     activities
    0.73
     professions
    0.72
     substances
    0.72
    Act Density 0.232%

    No Known Activations