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

    Neuronpedia

    INDEX
    Explanations

    computer code and programming-related terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Dinosaur
    -1.15
    wagen
    -1.14
    ORED
    -1.11
    ãģĤ
    -1.06
    inarily
    -1.03
    arding
    -1.02
    stadt
    -0.99
    æ©Ł
    -0.95
    DERR
    -0.95
     actionGroup
    -0.94
    POSITIVE LOGITS
    mbol
    1.67
    nerg
    1.45
    ringe
    1.44
    lves
    1.38
    ntax
    1.37
    posium
    1.35
    rup
    1.33
    philis
    1.33
    ptoms
    1.27
    combe
    1.25
    Act Density 0.915%

    No Known Activations