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

    Neuronpedia

    INDEX
    Explanations

    references to fictional works or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ！）
    -0.61
    ！】
    -0.58
    ftagPool
    -0.57
    ？】
    -0.57
    RuleContext
    -0.57
     $)
    -0.56
    occuper
    -0.55
    %]
    -0.55
     _)
    -0.55
    |]
    -0.54
    POSITIVE LOGITS
    ".
    1.16
    "
    1.09
    ”
    1.06
    ”.
    1.01
    "!
    1.00
    ""
    0.99
    "\\
    0.95
    ”!
    0.92
    "</
    0.92
    ",
    0.90
    Act Density 0.485%

    No Known Activations