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

    Neuronpedia

    INDEX
    Explanations

    numeric data and numerical relationships in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sixth
    -0.24
     six
    -0.22
     Sixth
    -0.22
    six
    -0.21
     seventh
    -0.20
     Six
    -0.20
     fifth
    -0.18
    åħŃ
    -0.18
    -six
    -0.18
     seven
    -0.18
    POSITIVE LOGITS
    2
    0.28
    Û²
    0.15
    heimer
    0.15
    jang
    0.14
    urus
    0.14
     dvÄĽma
    0.14
    Wunused
    0.14
    apes
    0.14
    两
    0.14
    adr
    0.14
    Act Density 0.110%

    No Known Activations