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

    Neuronpedia

    INDEX
    Explanations

    references to specific "positions" or "placement" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stone
    -0.46
     dish
    -0.43
     particle
    -0.42
     dishes
    -0.41
     techniques
    -0.40
    TRIBUN
    -0.40
     coating
    -0.40
     Stone
    -0.40
     ViewPager
    -0.39
     European
    -0.38
    POSITIVE LOGITS
    Positioning
    1.01
    positioning
    1.00
     positioned
    0.98
     positioning
    0.96
     Positioning
    0.95
     Positions
    0.77
     POSITION
    0.75
     posicion
    0.75
     Position
    0.73
     positions
    0.72
    Act Density 0.275%

    No Known Activations