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

    Neuronpedia

    INDEX
    Explanations

    sections of text related to computer programming and technical details

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    stood
    -0.59
    Magikarp
    -0.54
     contingency
    -0.51
     coincidence
    -0.51
     NFC
    -0.50
     quotation
    -0.49
     laure
    -0.48
     discretion
    -0.48
     hypothal
    -0.48
     capit
    -0.48
    POSITIVE LOGITS
     abroad
    0.82
     cheaply
    0.82
     whilst
    0.81
     WITHOUT
    0.81
     concurrently
    0.79
     without
    0.78
     efficiently
    0.77
     indoors
    0.73
    enium
    0.72
     outdoors
    0.72
    Act Density 20.669%

    No Known Activations