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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical concepts and properties, particularly regarding sparsity, linearity, and symmetry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words ending in "-ity" that denote abstract qualities or properties.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    \{\\
    -0.51
     Signalez
    -0.49
     Chwiliwch
    -0.49
    tagPool
    -0.49
    Personensuche
    -0.49
    webElementXpaths
    -0.44
    Autoritní
    -0.42
     defaultstate
    -0.42
     jadx
    -0.41
    ंदीखरीदारी
    -0.40
    POSITIVE LOGITS
    giaan
    0.54
    transQ
    0.53
     AssemblyVersion
    0.52
    tiba
    0.51
     tinggi
    0.48
    ritus
    0.46
     Westmoreland
    0.46
    Hardness
    0.46
    terness
    0.46
     Hardness
    0.46
    Act Density 0.767%

    No Known Activations