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

    Neuronpedia

    INDEX
    Explanations

    instances of proper nouns and specific identifiers, particularly in contextual discussions or dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.59
    E
    -0.55
    W
    -0.54
    0
    -0.52
    1
    -0.52
    S
    -0.52
    f
    -0.50
    <h2>
    -0.50
    2
    -0.49
    P
    -0.49
    POSITIVE LOGITS
    Autoritní
    1.14
    Viited
    1.02
     pleaſure
    1.00
     fubject
    0.99
     reaſon
    0.96
     juſt
    0.96
    sofá
    0.95
     ſtate
    0.93
     ſever
    0.92
    pulseira
    0.92
    Act Density 1.646%

    No Known Activations