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

    Neuronpedia

    INDEX
    Explanations

    newspaper-related terms and names

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    fee
    -0.95
    ayne
    -0.94
    paren
    -0.88
    acted
    -0.86
    imilar
    -0.86
    adow
    -0.85
    adders
    -0.82
    lua
    -0.81
    maxwell
    -0.81
    ucha
    -0.81
    POSITIVE LOGITS
     advertisements
    1.00
     columnist
    1.00
     tabl
    0.95
     editor
    0.95
     advertisement
    0.93
     Editors
    0.93
     publishes
    0.92
     advertis
    0.92
    lisher
    0.91
     newspapers
    0.89
    Act Density 1.503%

    No Known Activations