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

    Neuronpedia

    INDEX
    Explanations

    mentions of school-related activities and fundraising efforts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     embra
    -1.21
     dises
    -1.19
     exem
    -1.17
     dispen
    -1.15
     igno
    -1.13
     oner
    -1.12
     emphat
    -1.11
     volunte
    -1.08
     effe
    -1.07
     Sén
    -1.07
    POSITIVE LOGITS
    <bos>
    0.89
     or
    0.68
     usually
    0.64
    或者
    0.64
     или
    0.63
     your
    0.61
     you
    0.61
     yourself
    0.59
     typically
    0.59
    或
    0.59
    Act Density 0.510%

    No Known Activations