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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "turn" in various forms, indicating transitions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hasMoreElements
    -0.60
    makeConstraints
    -0.58
    ení
    -0.53
     niyang
    -0.52
     clearance
    -0.52
     richi
    -0.50
    IntoConstraints
    -0.49
    StringBuilder
    -0.49
    expandindo
    -0.49
     Clears
    -0.49
    POSITIVE LOGITS
     upside
    0.88
    tiles
    0.77
    arounds
    0.76
     heads
    0.76
     tables
    0.74
    tile
    0.68
     Upside
    0.64
     inward
    0.63
     around
    0.63
     lemons
    0.62
    Act Density 0.118%

    No Known Activations