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

    Neuronpedia

    INDEX
    Explanations

    patterns related to physical locations or actions happening on the ground

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "on the ground."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    士
    -0.76
    ansen
    -0.75
     caut
    -0.69
     Sins
    -0.69
    xit
    -0.67
    essee
    -0.66
    azi
    -0.65
     Picks
    -0.64
    icer
    -0.63
    uked
    -0.62
    POSITIVE LOGITS
    floor
    1.08
     floor
    1.00
    hog
    0.98
    side
    0.87
    room
    0.87
     Floor
    0.83
    fare
    0.81
    sheet
    0.80
    waves
    0.79
    plane
    0.78
    Act Density 0.017%

    No Known Activations