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

    Neuronpedia

    INDEX
    Explanations

    information related to coding, programming, and technical instructions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    othal
    -0.45
     hallucinations
    -0.45
    aceae
    -0.45
     scept
    -0.44
     Canaver
    -0.43
    loss
    -0.43
     EW
    -0.43
     decap
    -0.42
     electrodes
    -0.41
     pans
    -0.41
    POSITIVE LOGITS
     tradem
    0.57
    SourceFile
    0.54
    ĨĴ
    0.52
    PORT
    0.51
     Telephone
    0.50
    âĸ¬
    0.50
    taboola
    0.48
    gmail
    0.48
     pione
    0.47
    «ĺ
    0.47
    Act Density 14.983%

    No Known Activations