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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical locations and concrete settings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    FTWARE
    -0.70
    HTTP
    -0.62
    aceutical
    -0.61
    available
    -0.58
     benefited
    -0.57
     WRITE
    -0.56
    Russ
    -0.56
    Pac
    -0.56
    fill
    -0.56
    Berry
    -0.55
    POSITIVE LOGITS
     least
    1.49
    onement
    1.13
    mosp
    1.04
    roph
    1.03
    yp
    1.00
    las
    0.97
    abase
    0.97
    hens
    0.97
     times
    0.94
     halftime
    0.91
    Act Density 0.426%

    No Known Activations