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

    Neuronpedia

    INDEX
    Explanations

    terms related to perturbations in a mathematical or physical context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Архівовано
    -0.59
     MiG
    -0.59
     Fea
    -0.58
    ChildScrollView
    -0.57
     tann
    -0.56
     Crows
    -0.56
     Redondo
    -0.56
     Aiken
    -0.56
     Blackwood
    -0.54
     widows
    -0.53
    POSITIVE LOGITS
     perturbations
    1.37
     Pert
    1.33
    pertur
    1.24
    Pert
    1.15
     perturbation
    1.14
    urbation
    1.06
     perturbed
    1.03
    perturb
    1.02
     pert
    1.01
     pertur
    1.00
    Act Density 0.004%

    No Known Activations