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

    Neuronpedia

    INDEX
    Explanations

    references to mechanisms, particularly in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.98
    AddTagHelper
    -0.94
    fromnode
    -0.91
     Catto
    -0.89
     مشين
    -0.88
     AssemblyCulture
    -0.87
     CreateTagHelper
    -0.86
    Moz
    -0.84
    sizeCache
    -0.82
    moveToFirst
    -0.82
    POSITIVE LOGITS
     mécan
    0.89
     mechanisms
    0.89
     mechanism
    0.86
    mechan
    0.85
     meccan
    0.84
     MECHAN
    0.71
    机制
    0.71
     Mechanisms
    0.66
    Mechanisms
    0.66
     mekan
    0.66
    Act Density 0.098%

    No Known Activations