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

    Neuronpedia

    INDEX
    Explanations

    references to physics-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.79
     Jolie
    -0.76
     étoit
    -0.73
    SBATCH
    -0.73
     Archipelago
    -0.73
     pouvoit
    -0.71
     enfans
    -0.71
    AnchorStyles
    -0.70
     Grä
    -0.70
    ρους
    -0.69
    POSITIVE LOGITS
     Physics
    1.36
    physics
    1.33
     physics
    1.31
    Physics
    1.25
     PHYSICS
    1.15
    PHYSICS
    1.10
     physicists
    1.09
     Fiz
    0.96
     Phys
    0.90
    physic
    0.90
    Act Density 0.032%

    No Known Activations