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

    Neuronpedia

    INDEX
    Explanations

    terms related to linearity in mathematical models or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.71
    NameInMap
    -0.68
     Monfieur
    -0.66
    },[])
    -0.66
     tartalomajánló
    -0.66
    — 
    -0.65
    protoimpl
    -0.65
     Datum
    -0.64
     Observatory
    -0.64
     ſch
    -0.62
    POSITIVE LOGITS
     linear
    2.53
     Linear
    2.40
    linear
    2.37
    Linear
    2.37
     LINEAR
    2.12
     liné
    1.96
    LINEAR
    1.88
     linearly
    1.81
    线性
    1.70
     linearity
    1.66
    Act Density 0.084%

    No Known Activations