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

    Neuronpedia

    INDEX
    Explanations

    dates mentioned in a specific format

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     nursing
    -0.64
     morphine
    -0.60
     strangers
    -0.60
     Misty
    -0.60
     necessities
    -0.57
     incumbent
    -0.56
     bruised
    -0.56
     effected
    -0.55
     bount
    -0.55
     rightful
    -0.55
    POSITIVE LOGITS
    anski
    0.92
    atican
    0.92
    bilt
    0.79
    hetti
    0.79
    furt
    0.79
    IUM
    0.75
    pei
    0.73
    ohm
    0.73
    geist
    0.73
    adel
    0.71
    Act Density 0.168%

    No Known Activations