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

    Neuronpedia

    INDEX
    Explanations

    terms related to theoretical concepts and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.75
     nakalista
    -0.74
     betweenstory
    -0.66
    Personensuche
    -0.56
     PeEnEo
    -0.56
     actualité
    -0.53
     esternos
    -0.52
    nicity
    -0.51
     twij
    -0.51
     himo
    -0.51
    POSITIVE LOGITS
     method
    2.41
     approach
    2.34
     methodology
    2.13
     technique
    2.11
    method
    2.06
    approach
    1.99
     methods
    1.94
     méthode
    1.92
     Method
    1.86
     Approach
    1.85
    Act Density 1.665%

    No Known Activations