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

    Neuronpedia

    INDEX
    Explanations

    positive sentiment and friendly interactions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ĨĴ
    -0.78
    geant
    -0.74
    hran
    -0.67
    »Ĵ
    -0.66
     IMAGES
    -0.65
     Phant
    -0.62
    ãĤ¼
    -0.60
    ãĤ®
    -0.59
    xiety
    -0.58
    */(
    -0.58
    POSITIVE LOGITS
     cord
    1.08
    lessly
    1.02
     Cord
    0.95
    oba
    0.78
     cords
    0.78
    ovan
    0.73
    elo
    0.71
    elia
    0.69
    iously
    0.69
    wood
    0.68
    Act Density 5.949%

    No Known Activations