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

    Neuronpedia

    INDEX
    Explanations

    keywords related to electric components and specifications.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz
    New Auto-Interp
    Negative Logits
     hadron
    0.31
     olig
    0.31
     shoreline
    0.31
     chalc
    0.30
     aspen
    0.30
     sedentary
    0.30
     flasks
    0.30
    스는
    0.29
     viciss
    0.29
     cylinders
    0.29
    POSITIVE LOGITS
    ↵
    0.50
    ↵↵
    0.46
    ↵↵↵
    0.38
    ù
    0.37
          
    0.35
              
    0.35
     Usually
    0.34
    "]
    0.33
    ”
    0.33
    ↵↵↵↵
    0.33
    Act Density 1.329%

    No Known Activations