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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     optics
    -0.64
    enegger
    -0.64
     XCOM
    -0.61
     IPS
    -0.59
     upstairs
    -0.59
     enclosed
    -0.57
     outward
    -0.56
     eSports
    -0.56
     wik
    -0.56
     extrad
    -0.55
    POSITIVE LOGITS
    cknowled
    1.28
    cknow
    1.27
    ussie
    1.21
    verages
    1.19
    perture
    1.16
    BILITIES
    1.14
    UG
    1.07
    uctions
    1.06
    HA
    1.05
    ryan
    1.04
    Act Density 0.072%

    No Known Activations