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

    Neuronpedia

    INDEX
    Explanations

    mentions of names of people and organizations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    thood
    -0.90
    eno
    -0.85
    usa
    -0.84
    ceive
    -0.82
     beforehand
    -0.80
     besides
    -0.79
     Communism
    -0.78
    udo
    -0.74
    iffe
    -0.74
    veland
    -0.74
    POSITIVE LOGITS
     latter
    1.56
     largest
    1.40
     same
    1.38
     fastest
    1.38
     biggest
    1.37
     hardest
    1.36
     smallest
    1.36
     longest
    1.35
     oldest
    1.34
     earliest
    1.32
    Act Density 4.636%

    No Known Activations