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

    Neuronpedia

    INDEX
    Explanations

    economic terms or references

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    netflix
    -0.85
    tower
    -0.79
    lain
    -0.79
    ery
    -0.77
    ivas
    -0.74
    rose
    -0.74
    etts
    -0.74
    iguous
    -0.73
    umbn
    -0.73
    xual
    -0.72
    POSITIVE LOGITS
     downturn
    1.26
     hardship
    0.97
     prosperity
    0.92
     inequality
    0.92
     illiter
    0.91
     incentives
    0.89
     growth
    0.88
     stimulus
    0.88
     recession
    0.88
     sanctions
    0.87
    Act Density 0.040%

    No Known Activations