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

    Neuronpedia

    INDEX
    Explanations

    physics-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to physics and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aina
    -0.76
    ged
    -0.74
    oway
    -0.72
    HCR
    -0.71
    ging
    -0.70
    atches
    -0.70
    attery
    -0.69
    atche
    -0.68
    ibaba
    -0.67
    inating
    -0.66
    POSITIVE LOGITS
     physicist
    1.06
     physicists
    1.06
     physics
    0.92
    ysics
    0.86
    ERN
    0.81
     physic
    0.81
     Physics
    0.80
     equations
    0.76
    OTOS
    0.73
     simulations
    0.72
    Act Density 0.045%

    No Known Activations