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

    Neuronpedia

    INDEX
    Explanations

    words related to different categories or types of things

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    orius
    -0.86
    opsis
    -0.80
    NER
    -0.74
    edia
    -0.71
    eka
    -0.71
    orney
    -0.70
    iffe
    -0.69
    inion
    -0.69
    URRENT
    -0.69
    Ħ¢
    -0.69
    POSITIVE LOGITS
     goodies
    0.85
     imaginable
    0.83
     varied
    0.80
     surprises
    0.79
    hots
    0.77
     ranging
    0.75
     havoc
    0.72
     kinds
    0.72
     shapes
    0.71
     complicated
    0.71
    Act Density 1.069%

    No Known Activations