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

    Neuronpedia

    INDEX
    Explanations

    mentions of the concept of something being created or comprised of various components

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    assis
    -0.58
    CLOSE
    -0.57
    ities
    -0.56
    hov
    -0.55
    idon
    -0.54
     CPC
    -0.53
    iveness
    -0.53
     GPA
    -0.52
     Cul
    -0.52
    isks
    -0.52
    POSITIVE LOGITS
     payable
    1.09
     available
    0.92
     redundant
    0.88
     obsolete
    0.87
     possible
    0.85
     famous
    0.85
     aware
    0.84
    usable
    0.81
    lyn
    0.80
     landfall
    0.78
    Act Density 0.061%

    No Known Activations