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

    Neuronpedia

    INDEX
    Explanations

    terms related to technology and computer science, particularly focusing on distributed systems and security protocols

    oai_token-act-pair · gpt-3.5-turbo

    terms related to systems and structures of control, particularly in the context of distribution and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sters
    -0.75
     Kinnikuman
    -0.73
    older
    -0.72
    lust
    -0.71
    ouf
    -0.71
    adier
    -0.71
    enegger
    -0.68
    oi
    -0.68
    adra
    -0.67
     ABE
    -0.67
    POSITIVE LOGITS
    paren
    0.86
     seating
    0.82
     rollout
    0.74
     housing
    0.73
     versions
    0.72
     grazing
    0.70
     BY
    0.69
     demolition
    0.69
    eals
    0.68
     transport
    0.68
    Act Density 0.243%

    No Known Activations