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

    Neuronpedia

    INDEX
    Explanations

    numerical references or identifiers related to data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SIO
    -0.91
    hhhhhhhh
    -0.89
    alaya
    -0.88
     Wirt
    -0.84
    iclo
    -0.82
    amá
    -0.80
    continence
    -0.80
     isChecked
    -0.79
    دانشنامهٔ
    -0.78
     Woodbury
    -0.76
    POSITIVE LOGITS
    4
    2.05
    5
    1.33
    6
    1.22
     @"/
    1.21
    3
    1.18
    8
    1.14
     Four
    1.04
    FOUR
    1.04
     FOUR
    1.03
    four
    1.01
    Act Density 0.838%

    No Known Activations