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

    Neuronpedia

    INDEX
    Explanations

    references to physical locations or boundaries where movement occurs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "crossing"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesia
    -0.70
    wig
    -0.70
    ulously
    -0.66
    alus
    -0.65
    etic
    -0.63
    tml
    -0.63
    andum
    -0.63
     guiIcon
    -0.62
    Wan
    -0.62
    zip
    -0.62
    POSITIVE LOGITS
     crossings
    1.05
     crossing
    1.01
    roads
    0.94
    bows
    0.81
     Crossing
    0.78
     crosses
    0.77
    cross
    0.75
    engers
    0.74
    bow
    0.74
    es
    0.73
    Act Density 0.009%

    No Known Activations