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

    Neuronpedia

    INDEX
    Explanations

    specific words related to spatial relationships and actions involving objects in space

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    âĦ¢:
    -0.82
    buster
    -0.77
     based
    -0.73
    -$
    -0.70
     spearheaded
    -0.70
     along
    -0.70
     relies
    -0.69
    iliate
    -0.69
    verage
    -0.69
    Europe
    -0.69
    POSITIVE LOGITS
     slightest
    1.27
     same
    1.08
     dreaded
    1.04
     whole
    1.03
     remainder
    1.01
     entirety
    0.98
     rest
    0.97
     proverbial
    0.96
     latter
    0.96
     smallest
    0.94
    Act Density 0.739%

    No Known Activations