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

    Neuronpedia

    INDEX
    Explanations

    concepts related to societal structures and class dynamics

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

    phrases that evaluate or summarize a topic holistically using "as a whole."

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    Cyfeiriadau
    -0.48
    
    -0.48
    =$?
    -0.44
     censo
    -0.44
    angelog
    -0.43
    lossians
    -0.41
     ();
    -0.41
    }],
    -0.40
    <>();
    -0.40
    httphttps
    -0.39
    POSITIVE LOGITS
     overall
    3.34
    overall
    2.95
    Overall
    2.94
     Overall
    2.84
     generally
    2.45
    整體
    2.33
    总体
    2.28
     insgesamt
    2.20
    整体
    2.16
    OVERALL
    2.14
    Act Density 1.891%

    No Known Activations