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

    Neuronpedia

    INDEX
    Explanations

    locations described with cardinal directions, such as north, east, south, and west

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic directions and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scissors
    -0.77
     Proced
    -0.71
     PowerPoint
    -0.71
     Drill
    -0.70
     actu
    -0.69
     Soda
    -0.69
     Calculator
    -0.68
     Guitar
    -0.68
     Swordsman
    -0.67
     Masquerade
    -0.67
    POSITIVE LOGITS
    east
    1.59
    west
    1.59
    south
    1.36
    facing
    1.33
    western
    1.27
    central
    1.16
    East
    1.11
    north
    1.10
    Eastern
    1.09
    astern
    1.07
    Act Density 0.038%

    No Known Activations