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

    Neuronpedia

    INDEX
    Explanations

    terms related to solar eclipses

    oai_token-act-pair · gpt-3.5-turbo

    themes related to solar eclipses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raq
    -0.81
    heastern
    -0.76
    Solid
    -0.76
    iability
    -0.75
    sburgh
    -0.75
    anguages
    -0.75
    CHA
    -0.72
    ongh
    -0.71
    imilation
    -0.71
    omo
    -0.70
    POSITIVE LOGITS
     eclipse
    1.41
     eclips
    1.04
     Eclipse
    1.01
    clipse
    1.00
     cones
    0.87
    bows
    0.84
     glasses
    0.82
     orb
    0.80
     canopy
    0.73
    eering
    0.72
    Act Density 0.041%

    No Known Activations