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

    Neuronpedia

    INDEX
    Explanations

    copyright information or references in text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    eday
    -0.94
    dot
    -0.84
    abase
    -0.80
    aeper
    -0.80
    xon
    -0.79
    poon
    -0.78
    perties
    -0.77
    imei
    -0.77
    iband
    -0.75
    ihu
    -0.75
    POSITIVE LOGITS
     Belfast
    0.86
     AFP
    0.82
     Rebels
    0.75
     ©
    0.75
     Provided
    0.74
     Copyright
    0.73
     Reuters
    0.72
     Cardiff
    0.72
     Image
    0.72
     Surveillance
    0.72
    Act Density 0.028%

    No Known Activations