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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to heights or levels, especially when they are above a certain threshold

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    arry
    -0.75
    iasco
    -0.71
    obi
    -0.70
    eddy
    -0.66
    Untitled
    -0.64
     Syndrome
    -0.62
    Orig
    -0.62
     Interview
    -0.61
    iew
    -0.60
     Cust
    -0.59
    POSITIVE LOGITS
     higher
    3.30
    higher
    2.94
    Higher
    2.75
     Higher
    2.60
     lower
    2.32
     highest
    1.81
     greater
    1.78
    lower
    1.73
     high
    1.67
     larger
    1.63
    Act Density 0.019%

    No Known Activations