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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of the term "gres" at varying strengths

    oai_token-act-pair · gpt-3.5-turbo

    names of people and references to the PostgreSQL database system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     supervised
    -0.75
     subp
    -0.64
     worker
    -0.63
    adem
    -0.60
     hiding
    -0.60
     Pand
    -0.60
     Workers
    -0.60
    Bah
    -0.60
     faked
    -0.59
     Outs
    -0.59
    POSITIVE LOGITS
    ences
    1.02
    nesota
    1.02
    ãĤ¡
    0.93
    otaur
    0.92
    abeth
    0.88
    entials
    0.87
    ential
    0.86
    bia
    0.85
    udence
    0.85
    sburg
    0.84
    Act Density 0.028%

    No Known Activations