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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating noteworthy events or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NavController
    -0.15
    ëĦIJ
    -0.15
    leck
    -0.14
    730
    -0.13
    pras
    -0.13
    asti
    -0.13
    versible
    -0.13
    NotFoundError
    -0.13
    Oops
    -0.13
    ursive
    -0.13
    POSITIVE LOGITS
     odd
    0.65
     unusual
    0.59
     strange
    0.58
     weird
    0.52
    å¥ĩ
    0.49
     Strange
    0.47
     peculiar
    0.47
    odd
    0.47
    Odd
    0.46
     Odd
    0.45
    Act Density 0.884%

    No Known Activations