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

    Neuronpedia

    INDEX
    Explanations

    mentions of numerical values, particularly pertaining to the quantity or age

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /apt
    -0.16
    ±Ð¾ÑĤ
    -0.16
    DER
    -0.15
     lạc
    -0.15
    erties
    -0.15
    è
    -0.14
    Ïĥει
    -0.14
    achel
    -0.14
    egis
    -0.14
    еÑĢи
    -0.14
    POSITIVE LOGITS
    -five
    0.28
    -one
    0.27
    -two
    0.26
    -four
    0.24
    -three
    0.24
    -first
    0.24
    -nine
    0.23
    odd
    0.23
    -eight
    0.23
    -One
    0.23
    Act Density 0.036%

    No Known Activations