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

    Neuronpedia

    INDEX
    Explanations

    Roman numerals

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confidentiality
    -0.70
     interference
    -0.67
     whine
    -0.67
     representation
    -0.66
     assurance
    -0.65
     transparency
    -0.65
     Priority
    -0.64
     hed
    -0.63
     convenience
    -0.63
     contingency
    -0.63
    POSITIVE LOGITS
    ³³³³³³³³
    1.06
    Contents
    1.05
    ³³³³
    1.04
    ³³³³³³³³³³³³³³³³
    1.02
    ³³³
    1.01
    posted
    0.93
    Born
    0.92
    Phot
    0.91
    âĵĺ
    0.88
    ³³
    0.88
    Act Density 0.492%

    No Known Activations