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

    Neuronpedia

    INDEX
    Explanations

    references to community benefit agreements and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     >::
    -0.15
    :expr
    -0.13
     Moreno
    -0.13
    osti
    -0.13
    efe
    -0.13
    aban
    -0.12
    ::$_
    -0.12
     spokes
    -0.12
    ::*;↵
    -0.12
    تÛĮ
    -0.12
    POSITIVE LOGITS
    |
    0.64
    |↵
    0.52
    |↵↵
    0.49
    ||↵
    0.40
    |M
    0.39
    |"
    0.39
    .|
    0.39
    |\
    0.38
    |.
    0.38
    ||
    0.35
    Act Density 0.040%

    No Known Activations