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

    Neuronpedia

    INDEX
    Explanations

    phrases related to future outcomes or plans with contrasting possibilities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Yor
    -0.74
     Sul
    -0.73
     Sie
    -0.73
     Clara
    -0.72
     Candy
    -0.72
     typing
    -0.70
     RTX
    -0.70
     Syd
    -0.69
     inhabit
    -0.69
     sightings
    -0.69
    POSITIVE LOGITS
     stalled
    1.04
     aimed
    1.03
     counterproductive
    1.01
     costing
    1.01
     undone
    0.99
     unconstitutional
    0.98
     underway
    0.98
     funded
    0.98
     undertaken
    0.97
     financed
    0.96
    Act Density 0.892%

    No Known Activations