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

    Neuronpedia

    INDEX
    Explanations

    expressions related to freedom or lack of restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    free from, free of, free to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ItemBackground
    -0.57
    DebuggerNonUser
    -0.41
    EndGlobalSection
    -0.41
     المعيارى
    -0.40
    adaptiveStyles
    -0.39
     recent
    -0.37
     препратки
    -0.37
    principalColumn
    -0.37
     récente
    -0.37
    styleType
    -0.36
    POSITIVE LOGITS
     free
    1.20
    free
    1.11
     FREE
    1.10
    FREE
    1.06
    Free
    0.99
     Free
    0.98
     libres
    0.94
     libre
    0.94
     freedom
    0.90
     свобод
    0.86
    Act Density 0.025%

    No Known Activations