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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a specific concept, "Black Belt"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Belt" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nt
    -0.78
     mol
    -0.66
     chall
    -0.66
     reprodu
    -0.65
     reproduce
    -0.64
     step
    -0.62
    sych
    -0.61
     syn
    -0.61
    OY
    -0.61
     autistic
    -0.61
    POSITIVE LOGITS
     Belt
    4.61
    belt
    2.42
     belt
    2.15
     belts
    1.83
     Pants
    1.17
     Saban
    0.98
     Corridor
    0.96
     Ring
    0.94
     Plate
    0.93
    Ring
    0.92
    Act Density 0.009%

    No Known Activations