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

    Neuronpedia

    INDEX
    Explanations

    quantities and numerical references within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eter
    -0.16
    otope
    -0.15
    esel
    -0.14
    nist
    -0.13
    usercontent
    -0.13
    s
    -0.13
    ertas
    -0.13
    bau
    -0.13
    imas
    -0.13
    etter
    -0.13
    POSITIVE LOGITS
    -dimensional
    0.20
    -thirds
    0.18
     dozen
    0.17
    -way
    0.16
    ancy
    0.15
    instein
    0.15
    /to
    0.14
    lava
    0.14
    -digit
    0.14
    agers
    0.14
    Act Density 0.183%

    No Known Activations