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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significance or noteworthy attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.17
    =
    -0.15
    Âł
    -0.15
     target
    -0.15
    1
    -0.15
     b
    -0.15
    *
    -0.14
     cont
    -0.14
    TI
    -0.14
     bos
    -0.14
    POSITIVE LOGITS
    Touches
    0.18
    .xz
    0.18
    rej
    0.15
    @nate
    0.15
    /lic
    0.15
    #
    0.15
    Ùħج
    0.15
     gratuites
    0.15
    OutOfRangeException
    0.15
    ekyll
    0.14
    Act Density 0.656%

    No Known Activations