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

    Neuronpedia

    INDEX
    Explanations

    instances of words related to computer programming concepts and structures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zauber
    -0.46
     Götter
    -0.46
     Märchen
    -0.46
     Bibel
    -0.45
    Leod
    -0.44
     bella
    -0.43
    mpion
    -0.43
    Cormack
    -0.43
    Allister
    -0.43
     Erinner
    -0.43
    POSITIVE LOGITS
     type
    1.15
    type
    1.06
     Type
    1.05
     TYPE
    1.03
    TYPE
    1.01
     types
    1.01
    Type
    0.97
    getType
    0.95
    setType
    0.95
     Types
    0.92
    Act Density 0.100%

    No Known Activations