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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political, economic, or physical forces or influences

    oai_token-act-pair · gpt-3.5-turbo

    references to various forces or influences at play in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DERR
    -0.79
    ership
    -0.79
    MAL
    -0.77
    Hop
    -0.77
    STER
    -0.76
    gdala
    -0.75
    ocry
    -0.75
     Hop
    -0.70
    CHAT
    -0.69
    TIT
    -0.68
    POSITIVE LOGITS
     force
    1.05
     exerted
    1.01
     forces
    0.96
     maj
    0.92
     mobilized
    0.86
    forces
    0.81
     converge
    0.80
     recruited
    0.80
    force
    0.79
     engaged
    0.78
    Act Density 0.024%

    No Known Activations