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

    Neuronpedia

    INDEX
    Explanations

    discussions about the impact of technology on societal structures and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Enhancement
    -0.15
    quota
    -0.14
    uhe
    -0.14
    backward
    -0.14
    rsp
    -0.14
     intrusive
    -0.14
     Templ
    -0.13
     tob
    -0.13
     moto
    -0.13
    promotion
    -0.13
    POSITIVE LOGITS
     Joi
    0.18
     distributed
    0.18
     incentives
    0.18
     emerg
    0.18
     feedback
    0.17
     Pare
    0.17
     Distributed
    0.17
     tribal
    0.16
     network
    0.16
     recursively
    0.16
    Act Density 0.838%

    No Known Activations