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

    Neuronpedia

    INDEX
    Explanations

    references to high-definition (HD) technology

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ingen
    -0.95
    notations
    -0.91
    hift
    -0.86
    ortium
    -0.83
    enegger
    -0.75
    terday
    -0.73
    notation
    -0.70
    =-=-
    -0.70
     Schumer
    -0.68
    bara
    -0.68
    POSITIVE LOGITS
    PE
    1.07
    TV
    1.03
    Ds
    1.00
    CP
    0.89
    RI
    0.87
    HR
    0.84
    VI
    0.76
    visor
    0.76
    FS
    0.75
    AUD
    0.74
    Act Density 0.032%

    No Known Activations