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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases indicating location or presence

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Published
    -0.87
    leans
    -0.66
    chell
    -0.66
    Voice
    -0.64
     accumulated
    -0.63
    lean
    -0.63
    izoph
    -0.62
    Completed
    -0.62
     undertaken
    -0.62
     contemporaries
    -0.61
    POSITIVE LOGITS
     lieu
    1.13
    efficiency
    1.08
     vain
    1.07
     disguise
    1.00
     front
    0.96
     spite
    0.94
     order
    0.94
    escap
    0.94
    anity
    0.94
    animate
    0.93
    Act Density 0.384%

    No Known Activations