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

    Neuronpedia

    INDEX
    Explanations

    references to medical qualifications and professional achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cean
    -0.15
    wand
    -0.14
    eron
    -0.14
    afort
    -0.14
    obuf
    -0.14
    ominated
    -0.14
    (norm
    -0.13
     fork
    -0.13
    roleum
    -0.13
    /context
    -0.13
    POSITIVE LOGITS
     subs
    0.18
     fellowship
    0.16
    anki
    0.16
    -training
    0.16
    ModelError
    0.15
     fellows
    0.15
    åĪĢ
    0.15
    aed
    0.14
     specialty
    0.14
    ëł
    0.14
    Act Density 0.034%

    No Known Activations