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

    Neuronpedia

    INDEX
    Explanations

    numeric values or numeric sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anean
    -0.17
    -sdk
    -0.15
    lag
    -0.15
    io
    -0.15
    леÑĢ
    -0.15
    ober
    -0.15
    embed
    -0.14
    клад
    -0.13
    assic
    -0.13
    434
    -0.13
    POSITIVE LOGITS
    kaar
    0.18
    adera
    0.16
    stag
    0.14
    ceipt
    0.14
    .nih
    0.14
    HLT
    0.13
    _apps
    0.13
    ãĤ¦ãĥĪ
    0.13
    zas
    0.13
    apan
    0.13
    Act Density 0.011%

    No Known Activations