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

    Neuronpedia

    INDEX
    Explanations

    phrases related to education, programming, and international events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    hood
    -0.74
    ĪĴ
    -0.73
     Gins
    -0.72
    MENTS
    -0.67
     Sawyer
    -0.64
     DSL
    -0.64
     Himal
    -0.63
     balloons
    -0.62
    wich
    -0.61
    ĸļ
    -0.61
    POSITIVE LOGITS
    ourt
    1.25
    olor
    1.25
    entric
    1.24
    ulum
    1.22
    ategory
    1.20
    henko
    1.20
    chio
    1.20
    ount
    1.19
    rete
    1.18
    ulture
    1.18
    Act Density 1.754%

    No Known Activations