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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values, functions, and programmatic structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <(),
    -0.27
    ,[],
    -0.26
    ("",
    -0.26
    ({},
    -0.24
     "",
    -0.24
    ([],
    -0.23
    !,
    -0.23
    .*,
    -0.23
     {},
    -0.23
    ={},
    -0.22
    POSITIVE LOGITS
    <?>
    0.20
     _)
    0.16
    att
    0.15
    es
    0.15
    (_)
    0.14
     Beaver
    0.14
    uard
    0.14
    wick
    0.14
    <?>>
    0.14
    aga
    0.13
    Act Density 0.122%

    No Known Activations