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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases related to technological features and digital experiences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jackets
    -0.90
     Torrent
    -0.80
     Survivors
    -0.77
     circle
    -0.77
     LOT
    -0.75
     Centauri
    -0.74
     Venice
    -0.74
     Noise
    -0.72
     Slave
    -0.70
     Velocity
    -0.69
    POSITIVE LOGITS
    defined
    1.28
    assembled
    1.25
    generated
    1.22
    designed
    1.22
    produced
    1.21
    developed
    1.21
    connected
    1.20
    trained
    1.20
    installed
    1.18
    accessible
    1.18
    Act Density 0.042%

    No Known Activations