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

    Neuronpedia

    INDEX
    Explanations

    references to themes and thematic elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     OMITBAD
    -0.62
     noqa
    -0.61
    aneo
    -0.53
     җ
    -0.52
     Kluwer
    -0.51
     elettron
    -0.51
     leggi
    -0.47
     Simón
    -0.47
    isy
    -0.47
     blancs
    -0.46
    POSITIVE LOGITS
     themes
    1.31
    themes
    1.16
     Themes
    1.09
     theme
    1.09
     Theme
    1.07
    Themes
    1.05
    THEME
    1.00
     THEME
    0.94
     thème
    0.91
    theme
    0.91
    Act Density 0.047%

    No Known Activations