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

    Neuronpedia

    INDEX
    Explanations

    information on human activities, qualities, and characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to human impact on the environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raine
    -0.86
    nesday
    -0.75
    soDeliveryDate
    -0.75
    District
    -0.72
    antage
    -0.71
     reopen
    -0.70
     Rolling
    -0.69
    IDA
    -0.69
    ricular
    -0.68
    stanbul
    -0.67
    POSITIVE LOGITS
     apes
    1.43
     primates
    1.40
     mammals
    1.38
     mammalian
    1.35
     biologically
    1.31
     mammal
    1.29
     sentient
    1.28
     organisms
    1.25
     evolved
    1.23
    humans
    1.22
    Act Density 0.383%

    No Known Activations