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

    Neuronpedia

    INDEX
    Explanations

    words related to automation and technological processes

    oai_token-act-pair · gpt-3.5-turbo

    words related to automated processes or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lust
    -0.87
    aders
    -0.75
    issues
    -0.72
     Nieto
    -0.71
    appers
    -0.71
    some
    -0.70
    asso
    -0.69
    osaurs
    -0.69
    storms
    -0.68
    én
    -0.68
    POSITIVE LOGITS
    rive
    0.90
    irect
    0.76
     versions
    0.75
    escription
    0.75
     BY
    0.73
    eals
    0.73
     version
    0.73
    urally
    0.71
    paren
    0.71
    ocument
    0.69
    Act Density 0.131%

    No Known Activations