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

    Neuronpedia

    INDEX
    Explanations

    references to pages in academic documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InstanceOf
    -0.17
    reb
    -0.16
    ible
    -0.15
     wr
    -0.15
    976
    -0.15
    orro
    -0.14
    ehr
    -0.14
    ceb
    -0.14
    397
    -0.13
    ichert
    -0.13
    POSITIVE LOGITS
    íĻ©
    0.17
    lington
    0.15
    ylon
    0.15
    yre
    0.14
    dess
    0.14
    YLON
    0.13
     kapit
    0.13
     desar
    0.13
    tees
    0.13
    uche
    0.13
    Act Density 0.033%

    No Known Activations