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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical movement of people from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "moved"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oys
    -0.75
    omial
    -0.69
    iciency
    -0.67
    oured
    -0.67
    lain
    -0.65
    inges
    -0.63
    icum
    -0.62
    aez
    -0.62
    sung
    -0.62
    acha
    -0.61
    POSITIVE LOGITS
     forward
    0.78
     swiftly
    0.78
     away
    0.74
     toward
    0.73
    Motion
    0.72
    brates
    0.70
    ATHER
    0.70
    restricted
    0.68
    ebus
    0.68
    objects
    0.68
    Act Density 0.037%

    No Known Activations