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

    Neuronpedia

    INDEX
    Explanations

    terms relevant to statistical analysis and citations in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnitTesting
    -0.56
     Computers
    -0.55
     Wire
    -0.54
     Tog
    -0.53
    wire
    -0.52
     <<<<<<<<<<<<<<
    -0.52
     pthread
    -0.51
    WIRE
    -0.51
    Personendaten
    -0.51
    rodo
    -0.50
    POSITIVE LOGITS
     Kendall
    0.58
     linkovi
    0.52
     Hurricane
    0.52
     Riz
    0.52
     Juju
    0.52
    Hurricane
    0.51
     Rhy
    0.50
     Subtitle
    0.49
     subtitle
    0.49
    Flammability
    0.49
    Act Density 1.706%

    No Known Activations