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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical or abstract forces

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of forces and influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mbuds
    -0.80
     Hop
    -0.74
    Accessory
    -0.73
    DERR
    -0.69
    cott
    -0.69
    MAL
    -0.69
    namese
    -0.67
     Liberties
    -0.67
    missions
    -0.65
    TIT
    -0.65
    POSITIVE LOGITS
     exerted
    1.07
     maj
    0.96
     force
    0.94
     Awakens
    0.81
     multiplier
    0.76
     forces
    0.76
     propelled
    0.76
    force
    0.76
     propel
    0.75
    fact
    0.73
    Act Density 0.026%

    No Known Activations