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

    Neuronpedia

    INDEX
    Explanations

    actions and interactions between people

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    amaz
    -0.76
    tained
    -0.70
     Been
    -0.66
    pired
    -0.66
    ceivable
    -0.65
    umbn
    -0.65
    printed
    -0.63
    Þ
    -0.62
     Powered
    -0.62
    pared
    -0.61
    POSITIVE LOGITS
     consequently
    1.10
     reap
    1.07
     vice
    1.05
     manipulate
    1.04
     sometimes
    1.04
     thus
    1.03
     therefore
    1.03
     thereby
    0.98
     communicate
    0.98
     behave
    0.97
    Act Density 0.309%

    No Known Activations