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

    Neuronpedia

    INDEX
    Explanations

    instances where someone knows something or the concept of knowledge

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    amazon
    -0.67
    ksh
    -0.67
     representing
    -0.66
    razil
    -0.66
    iffe
    -0.64
    zilla
    -0.63
     owing
    -0.62
    Edit
    -0.61
    lette
    -0.61
     suppose
    -0.61
    POSITIVE LOGITS
     extent
    1.17
     basics
    1.14
     exact
    1.12
     same
    1.10
     entirety
    1.10
     difference
    1.09
     entire
    1.07
     slightest
    1.06
     beginnings
    1.04
    oret
    1.03
    Act Density 0.245%

    No Known Activations