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

    Neuronpedia

    INDEX
    Explanations

    syntax structures related to variable assignments and state changes in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.56
     estekak
    -0.55
    intios
    -0.47
    SharedCtor
    -0.47
     OMITBAD
    -0.46
    FailureListener
    -0.46
     odkazy
    -0.43
    ſchaft
    -0.43
    utnik
    -0.43
    enumii
    -0.43
    POSITIVE LOGITS
     true
    2.92
     True
    2.52
    true
    2.45
    True
    2.34
     TRUE
    2.23
    TRUE
    2.05
     truth
    1.73
     vrai
    1.71
     verdadeiro
    1.68
     vraie
    1.66
    Act Density 0.519%

    No Known Activations