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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different ways of living or doing things

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ways of living or lifestyles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CIA
    -0.74
    Merit
    -0.71
     Birch
    -0.67
     Agents
    -0.66
    Firstly
    -0.66
     Bots
    -0.65
    fml
    -0.64
    DAQ
    -0.63
    sites
    -0.63
    bryce
    -0.63
    POSITIVE LOGITS
     dealing
    0.77
     efficiently
    0.77
     life
    0.75
     communicating
    0.74
     arithmetic
    0.71
     interpreting
    0.71
     livelihood
    0.70
     structured
    0.68
     preserving
    0.68
     constructing
    0.66
    Act Density 0.053%

    No Known Activations