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

    Neuronpedia

    INDEX
    Explanations

    phrases describing actions or events happening on the ground

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ground."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansen
    -0.81
    士
    -0.76
    anos
    -0.67
    entric
    -0.66
     caut
    -0.65
    atron
    -0.64
    orters
    -0.64
    uked
    -0.64
    Prof
    -0.63
    xit
    -0.63
    POSITIVE LOGITS
     floor
    0.98
    floor
    0.97
    hog
    0.93
    sheet
    0.89
    sheets
    0.86
    raid
    0.83
     Floor
    0.82
    side
    0.79
     footing
    0.79
    plane
    0.78
    Act Density 0.014%

    No Known Activations