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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data types and values in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    by
    -0.60
    a
    -0.55
    av
    -0.54
     	e
    -0.54
    mogat
    -0.53
    k
    -0.53
    b
    -0.53
    made
    -0.53
    us
    -0.52
    ch
    -0.52
    POSITIVE LOGITS
    Integer
    2.40
     Integer
    2.35
     integer
    1.93
    integer
    1.87
     integers
    1.65
    INTEGER
    1.58
    getInteger
    1.50
     INTEGER
    1.43
    integers
    1.28
    整数
    1.10
    Act Density 0.080%

    No Known Activations