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

    Neuronpedia

    INDEX
    Explanations

    concepts related to freedom and expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mortar
    -0.67
    Kanpo
    -0.66
     оригіналу
    -0.65
    rungsseite
    -0.65
    يكب
    -0.65
     CreateTagHelper
    -0.64
     дописавши
    -0.63
     noses
    -0.62
    mortar
    -0.61
     briefcase
    -0.61
    POSITIVE LOGITS
     freedom
    1.78
     Freedom
    1.72
    Freedom
    1.63
    freedom
    1.52
     FREEDOM
    1.51
     freedoms
    1.42
     liberty
    1.24
    EDOM
    1.13
     liberté
    1.12
     bebas
    1.11
    Act Density 0.085%

    No Known Activations