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

    Neuronpedia

    INDEX
    Explanations

    references to public and private distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hlen
    -0.15
    à¹ĥหà¸į
    -0.14
    endi
    -0.14
    inem
    -0.14
    ält
    -0.14
    unky
    -0.14
    _PAD
    -0.14
    uts
    -0.13
    iba
    -0.13
    abar
    -0.13
    POSITIVE LOGITS
     private
    1.00
     Private
    0.84
    private
    0.83
     PRIVATE
    0.75
    Private
    0.74
    ç§ģ
    0.71
    -private
    0.70
     privately
    0.66
    	private
    0.65
    _private
    0.65
    Act Density 0.128%

    No Known Activations