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

    Neuronpedia

    INDEX
    Explanations

    markers indicating the structure of research or scientific articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.97
     purpoſe
    -0.92
     houſe
    -0.92
     Monfieur
    -0.91
     ſeveral
    -0.91
     Majefty
    -0.87
     himſelf
    -0.85
     ſtate
    -0.85
     Efq
    -0.84
     ―――――
    -0.83
    POSITIVE LOGITS
     ‘
    0.60
    ("")]
    0.57
     “
    0.53
    ‘
    0.51
    “
    0.51
    tiously
    0.51
     limit
    0.50
     What
    0.48
    对
    0.48
    そもそも
    0.47
    Act Density 0.068%

    No Known Activations