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

    Neuronpedia

    INDEX
    Explanations

    references to specific vehicles and related metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     برانيه
    -0.56
     bowiem
    -0.55
     kasarigan
    -0.53
     själva
    -0.53
     řek
    -0.50
     namelijk
    -0.50
     nemlig
    -0.49
     totiž
    -0.49
     infatti
    -0.48
    principalTable
    -0.48
    POSITIVE LOGITS
     version
    0.56
     Version
    0.53
    )++;
    0.52
     OK
    0.52
     Edition
    0.51
    )</
    0.49
     edition
    0.49
     slow
    0.49
    RetentionPolicy
    0.49
     defStyle
    0.49
    Act Density 1.071%

    No Known Activations