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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onomía
    -0.37
     parlé
    -0.35
    Eres
    -0.30
    Is
    -0.30
    Tener
    -0.29
     rechts
    -0.28
    setPreferred
    -0.28
    I
    -0.27
    Pre
    -0.27
     defaultstate
    -0.27
    POSITIVE LOGITS
     nonUne
    0.67
    RTEX
    0.66
    InitVars
    0.66
     препратки
    0.66
    FormTagHelper
    0.63
     lenker
    0.61
    rrggbb
    0.60
    TestingModule
    0.60
    ViewFeatures
    0.59
     initComponents
    0.59
    Act Density 0.001%

    No Known Activations