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

    Neuronpedia

    INDEX
    Explanations

    code structure elements such as classes, functions, and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.54
     John
    -0.46
     Finn
    -0.45
     sin
    -0.45
    tapp
    -0.44
    deutung
    -0.44
     court
    -0.44
    inna
    -0.43
     Sin
    -0.43
    зин
    -0.43
    POSITIVE LOGITS
     _
    1.78
    (_
    1.49
    =_
    1.46
     &_
    1.38
    :_
    1.33
    )_
    1.30
    ._
    1.28
     (_
    1.27
     *_
    1.25
    >(_
    1.24
    Act Density 0.134%

    No Known Activations