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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of light and illumination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.57
    principalColumn
    -0.51
    anganese
    -0.51
    stateProvider
    -0.50
     colectiva
    -0.50
    éndolo
    -0.48
     Tuple
    -0.48
    SBATCH
    -0.48
     consigo
    -0.47
     tapis
    -0.47
    POSITIVE LOGITS
     LIGHT
    1.15
     Light
    1.13
    Light
    1.10
    LIGHT
    1.05
     light
    1.03
    light
    0.99
     Licht
    0.84
     Lights
    0.82
    ligh
    0.81
     LIGHTS
    0.81
    Act Density 0.297%

    No Known Activations