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

    Neuronpedia

    INDEX
    Explanations

    either isolated words or phrases without a clear common theme

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Lumpur
    -0.81
    eering
    -0.76
     indemn
    -0.74
     nuts
    -0.73
     redress
    -0.72
     oven
    -0.70
     Gaal
    -0.69
     metic
    -0.68
     proced
    -0.67
     palm
    -0.67
    POSITIVE LOGITS
    meaning
    1.24
    which
    1.21
    along
    1.20
    feat
    1.19
    among
    1.19
    advertisement
    1.18
    these
    1.17
    perhaps
    1.17
    that
    1.16
    particularly
    1.16
    Act Density 14.156%

    No Known Activations