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

    Neuronpedia

    INDEX
    Explanations

    dates indicating significant events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    elong
    -0.92
    avorite
    -0.88
    Brew
    -0.86
    kef
    -0.85
    bread
    -0.85
    agy
    -0.82
    amins
    -0.80
    phia
    -0.80
    worldly
    -0.80
    imore
    -0.78
    POSITIVE LOGITS
     partName
    1.25
     onwards
    1.02
     Kass
    1.01
     GMT
    0.99
     Admission
    0.87
     Countdown
    0.86
     Eid
    0.84
     sidx
    0.84
     CST
    0.83
     Accord
    0.83
    Act Density 0.530%

    No Known Activations