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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    connections between abstract concepts and their representations or implications in practical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Investor
    -0.93
    alyst
    -0.90
    Story
    -0.87
     Rivals
    -0.82
     Intervention
    -0.80
    conservative
    -0.80
    Administ
    -0.79
     Strategy
    -0.78
     Startup
    -0.78
    Developer
    -0.78
    POSITIVE LOGITS
     wooden
    1.23
     wood
    1.11
     plastic
    1.11
     metal
    1.11
     leather
    1.10
     curved
    1.07
     bamboo
    1.06
     decorative
    1.05
     clay
    1.05
     cloth
    1.03
    Act Density 0.784%

    No Known Activations