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

    Neuronpedia

    INDEX
    Explanations

    references to organizational tools and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardy
    -0.17
    azon
    -0.15
     Watkins
    -0.15
    opak
    -0.15
    weit
    -0.14
    ires
    -0.14
    aca
    -0.14
    noc
    -0.14
    irts
    -0.13
     Energ
    -0.13
    POSITIVE LOGITS
    fwrite
    0.17
     recording
    0.17
     dood
    0.17
     WRITE
    0.16
     Recording
    0.16
     fwrite
    0.16
     pens
    0.15
     Write
    0.15
    WRITE
    0.15
     McGu
    0.15
    Act Density 0.158%

    No Known Activations