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

    Neuronpedia

    INDEX
    Explanations

    references to ladders or rung structures, often in a metaphorical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ladder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    -0.56
     "
    -0.50
    ↵↵↵
    -0.46
     OK
    -0.45
     
    -0.45
    <b>
    -0.44
    Â
    -0.44
     (
    -0.44
     doInBackground
    -0.43
     Wil
    -0.42
    POSITIVE LOGITS
     Ladder
    1.36
     ladder
    1.32
    Ladder
    1.27
     ladders
    1.23
    ladder
    1.20
     escalera
    0.98
    Ladd
    0.96
     Ladd
    0.96
     enfans
    0.94
     escaleras
    0.90
    Act Density 0.002%

    No Known Activations