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

    Neuronpedia

    INDEX
    Explanations

    mentions of social dynamics and inequalities

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

    conditional statements and comparative expressions indicating change, improvement, or hypothetical scenarios.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     Besonders
    -0.30
    だけでなく
    -0.27
     super
    -0.24
     '../../../../
    -0.23
     specifically
    -0.23
     lika
    -0.23
    だけではなく
    -0.23
    よね
    -0.22
     []*
    -0.22
     conformidad
    -0.22
    POSITIVE LOGITS
     somewhat
    1.50
    somewhat
    1.49
     marginally
    1.48
     parcialmente
    1.39
    slightly
    1.39
     partially
    1.38
     Somewhat
    1.37
    Somewhat
    1.34
     immerhin
    1.34
     slightly
    1.32
    Act Density 1.466%

    No Known Activations