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

    Neuronpedia

    INDEX
    Explanations

    words related to countries, the world, population, or the majority

    oai_token-act-pair · gpt-3.5-turbo

    references to the global or collective population and issues affecting them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Maid
    -0.70
     Tactics
    -0.67
     Counsel
    -0.67
     Hick
    -0.67
    icer
    -0.66
     RIS
    -0.63
     Runner
    -0.62
     Ranger
    -0.59
     Mug
    -0.59
     Compliance
    -0.58
    POSITIVE LOGITS
     perished
    0.84
     alike
    0.81
     starve
    0.78
     asleep
    0.77
     drown
    0.76
    ÃŃs
    0.75
    usercontent
    0.74
     dies
    0.73
     except
    0.71
    ele
    0.69
    Act Density 0.146%

    No Known Activations