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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical concepts and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BlockSize
    -0.19
     tower
    -0.16
     diagonal
    -0.16
     diagon
    -0.16
    ulfilled
    -0.15
     triangular
    -0.15
    pherical
    -0.15
    à¤Ĥà¤ľà¤¨
    -0.15
    pector
    -0.14
    ç«ĭãģ¦
    -0.14
    POSITIVE LOGITS
     curves
    0.26
     curve
    0.25
     param
    0.25
     segments
    0.22
     Curve
    0.21
     Param
    0.21
    -param
    0.21
    curve
    0.21
     segment
    0.20
    Param
    0.20
    Act Density 0.192%

    No Known Activations