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

    Neuronpedia

    INDEX
    Explanations

    references to linear and affine mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IVEREF
    -0.57
    httphttps
    -0.54
    -0.53
     ostavi
    -0.51
    MemoryWarning
    -0.50
    govina
    -0.47
    FunctionFlags
    -0.47
    SharedDtor
    -0.47
     Wikimedijinoj
    -0.46
    ictwo
    -0.45
    POSITIVE LOGITS
     linear
    0.66
    linear
    0.54
    Linear
    0.50
     linearly
    0.48
     Linear
    0.47
     للمعارف
    0.47
     LINEAR
    0.47
     simple
    0.44
     rectangular
    0.43
     HasFactory
    0.40
    Act Density 1.463%

    No Known Activations