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

    Neuronpedia

    INDEX
    Explanations

    symbols used for defining PHP variables and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ")))
    -0.65
     End
    -0.60
     en
    -0.58
    LookAnd
    -0.57
     Ade
    -0.57
     "
    -0.57
    mogorov
    -0.56
     Har
    -0.56
    ...]
    -0.56
     En
    -0.54
    POSITIVE LOGITS
    ($
    2.62
     ($
    1.69
    ($__
    1.52
    ($_
    1.45
    (($
    1.43
     ($\
    1.42
    }($
    1.42
    (_
    1.42
    ($(
    1.41
    (!$
    1.40
    Act Density 0.084%

    No Known Activations